Assembly traces can support explicit probabilistic inference without being treated as recovered program meaning. Active Assembly Theory and Practice makes that distinction executable: transparent x86-64 fixtures are decoded with Capstone, traced under bounded Unicorn emulation, and mapped to typed observations that distinguish missing, unseen, and unsupported evidence. Two Generalized Notation Notation (GNN) specifications define passive-phase and prospective sensor models whose tensors drive real pymdp execution. A native categorical Julia/RxInfer companion consumes the passive model's same parameters (Friedman 2026; Heins et al. 2022; Bagaev et al. 2023). The sensor Agent selects an action before fixture evidence is acquired. Independent finite calculations check beliefs and policy scores; native smoothing uses the same parameters and first-observation convention. Every inference comparator and fitted diagnostic also consumes an upstream-parsed numeric GNN specification, with source-bound runtime instances and rendered model graphs.
\nA corpus of 10 authored fixtures supports complete-fixture exclusion diagnostics. At the fixed informative likelihood, the memoryless decoder outperforms the temporal filter; temporal advantages appear under synthetic observation ambiguity. Designed category ambiguity remains a visible failure case. The separate Gaussian and categorical Bethe free-energy diagnostics are not compared numerically with policy expected free energy.
\nThe quotient benchmark contains 64 transformation-family identifiers and 4096 rows, with 16 families held out from model fitting. The co-primary portfolio includes an interpretable classifier, a temporal probabilistic model, a fixed one-layer tanh recurrent classifier, and surface baselines; the temporal endpoint reaches balanced accuracy 0.775 and macro-F1 0.772 on this frozen bounded benchmark. Held-out identifiers share authored template lineages with the fitting data. Family-resampling intervals and conditional randomization diagnostics therefore describe this finite inventory; the retrospective protocol correction withholds superiority claims. A complementary pinned static-only corpus supplies 5 licensed source projects and 100 source-contract rows, including 40 lexical witnesses, 40 contract-directed near misses, and 20 identity controls. The corpus establishes provenance and coverage; it does not execute arbitrary external binaries or support application-effectiveness claims.
\nSelected normalized machine-state relations are checked by Python, native execution, and a bounded Lean fragment. Exact finite sensing certificates and source-bound reader artifacts make assumptions and failures inspectable. Independent physical replication remains unearned. The contribution is a reproducible substrate for testing assembly-to-inference mechanisms, with explicit limits on semantics, statistical generalization, and external validity.
", "keywords": [ "active inference", "assembly analysis", "generative models", "GNN", "pymdp", "RxInfer", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/active_assembly_theory_and_practice", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "98476140-e5e3-41e1-87a4-b4e7a76a2e2a", "key": "active_assembly_theory_and_practice_combined.pdf", "size": 18929532, "checksum": "md5:ab5a49cce72ed625e8d0daee5561d1bf", "links": { "self": "https://zenodo.org/api/records/23484108/files/active_assembly_theory_and_practice_combined.pdf/content" } }, { "id": "37944449-7d1c-4e35-ba7d-c1365879046a", "key": "active_assembly_theory_and_practice-0.1.0-source.zip", "size": 7370219, "checksum": "md5:28e0d29659e9d72c225b7b788f9c1536", "links": { "self": "https://zenodo.org/api/records/23484108/files/active_assembly_theory_and_practice-0.1.0-source.zip/content" } }, { "id": "ab0a0fb1-9fa3-4092-81e1-561d98ee1933", "key": "active_assembly_theory_and_practice-0.1.0-review.zip", "size": 121296614, "checksum": "md5:55d9450e42c4cdbddd630f82be279b29", "links": { "self": "https://zenodo.org/api/records/23484108/files/active_assembly_theory_and_practice-0.1.0-review.zip/content" } }, { "id": "1dd3b149-ba9c-41a5-805a-7e7cca5a0954", "key": "RELEASE_MANIFEST.json", "size": 487872, "checksum": "md5:f3054588c3dc142dbc51a1d5077fabe3", "links": { "self": "https://zenodo.org/api/records/23484108/files/RELEASE_MANIFEST.json/content" } }, { "id": "345a8a86-432b-42b7-bdf4-57943dbe6314", "key": "SHA256SUMS", "size": 326, "checksum": "md5:602206f3820e398492c02e2799dc6e1d", "links": { "self": "https://zenodo.org/api/records/23484108/files/SHA256SUMS/content" } }, { "id": "ad2d6e4a-0dda-460f-9856-5a1f0b531013", "key": "active_assembly_theory_and_practice_combined.docx", "size": 19708032, "checksum": "md5:b769ed9a476883f7a077a0e7cedc31fd", "links": { "self": "https://zenodo.org/api/records/23484108/files/active_assembly_theory_and_practice_combined.docx/content" } } ], "html_url": "https://zenodo.org/records/23484108", "doi_url": "https://doi.org/10.5281/zenodo.23484107", "record_url": "https://zenodo.org/records/23484107" }, { "record_id": "23419306", "doi": "10.5281/zenodo.20614908", "title": "iTrace: verification-first webcam eye-movement analysis (corrected manuscript)", "publication_date": "2026-10-16", "version": "manuscript-2026-10-16-310be17", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "# iTrace manuscript revision, 2026-10-16\n\nThis deposit archives the corrected 30-page manuscript from reviewed commit `310be17ace8ae61621afe01329356427a3e6c861`. Exact source and figure artifacts are at https://github.com/docxology/itrace/tree/310be17ace8ae61621afe01329356427a3e6c861. It is a manuscript revision after the immutable v0.5.0 release, not a new package release. The package version in that source remains 0.5.0. The previous release remains at https://doi.org/10.5281/zenodo.23403300. References in the manuscript to that DOI identify the archived baseline.\n\nChanges correct overlap scoring, resampling and fit uncertainty, fitted-null diagnostics, uncertainty figures, scholarship, and scientific interpretation. The manuscript distinguishes synthetic verification from real-device validation. No new participant or reference-device data are claimed.\n\nVerification: 737 tests passed, 2 skipped, 91.05% combined statement-and-branch coverage; 44 final artifact tests passed, independent review approved the exact source commit, and all ten hosted CI jobs passed. The included figure manifest inventories 41 artifacts in the linked source tree. `provenance.json` binds this PDF to the Git commit; `SHA256SUMS` inventories every payload.", "keywords": [ "eye-tracking", "webcam", "gaze", "saccades", "pupillometry", "open-source", "diagnostic-pilot" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/itrace/tree/310be17ace8ae61621afe01329356427a3e6c861", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "10.5281/zenodo.23403300", "relation": "isNewVersionOf", "scheme": "doi" } ], "files": [ { "id": "1e19fbe2-d4fb-4b65-b086-65b023304a9a", "key": "scholarship-review.md", "size": 31153, "checksum": "md5:f8a30dfac64f6677f7f5359b10b84ebc", "links": { "self": "https://zenodo.org/api/records/23419306/files/scholarship-review.md/content" } }, { "id": "57ac63a6-37a5-4ea1-a68c-d69c7c758b51", "key": "README.md", "size": 1251, "checksum": "md5:5a04226bc70c4ad4398f34a7fe0b4255", "links": { "self": "https://zenodo.org/api/records/23419306/files/README.md/content" } }, { "id": "376ec9b8-3173-44f1-8c0e-d1beeb98daaa", "key": "LICENSE", "size": 1076, "checksum": "md5:c39a98bef02b2aa8bf46150269091678", "links": { "self": "https://zenodo.org/api/records/23419306/files/LICENSE/content" } }, { "id": "0cb5960c-2b74-4f6f-9b5b-b921c960791e", "key": "figure-manifest.json", "size": 18665, "checksum": "md5:c61eb0f74dd42b257e3aae8aabf87ae3", "links": { "self": "https://zenodo.org/api/records/23419306/files/figure-manifest.json/content" } }, { "id": "1a1ed871-f401-45bd-81b0-703c79575548", "key": "SHA256SUMS", "size": 598, "checksum": "md5:38fd9c8d0354c1217434b1ed03814473", "links": { "self": "https://zenodo.org/api/records/23419306/files/SHA256SUMS/content" } }, { "id": "0879be2c-2c84-4390-9af7-2fc56141c408", "key": "itrace-manuscript-2026-10-16.pdf", "size": 5732341, "checksum": "md5:b994e7cd34254f762b92b5dbc33b2225", "links": { "self": "https://zenodo.org/api/records/23419306/files/itrace-manuscript-2026-10-16.pdf/content" } }, { "id": "e1b8c204-12a1-41c7-bec9-6d10ba24217b", "key": "provenance.json", "size": 1635, "checksum": "md5:8d9e00c3cc526f72c82d490a5c07ed3e", "links": { "self": "https://zenodo.org/api/records/23419306/files/provenance.json/content" } }, { "id": "c6ea2fb1-9cac-4782-a328-067536dde93e", "key": "verification-metrics.json", "size": 1687, "checksum": "md5:749fedd1f0bc424194695cb62d96f874", "links": { "self": "https://zenodo.org/api/records/23419306/files/verification-metrics.json/content" } } ], "html_url": "https://zenodo.org/records/23419306", "doi_url": "https://doi.org/10.5281/zenodo.20614908", "record_url": "https://zenodo.org/records/20614908" }, { "record_id": "23404029", "doi": "10.5281/zenodo.23404028", "title": "iTrace: verification-first webcam eye-movement analysis", "publication_date": "2026-10-15", "version": "0.5.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "iTrace 0.5.0 is an MIT-licensed Python toolkit for webcam-derived gaze, saccade, pupil, and quality diagnostics. This minor release strengthens irregular-time analysis, missing-data handling, immutable recording inputs, pupil preprocessing, configuration and report contracts, reproducible live exports, manuscript rendering, and release verification. The NumPy/SciPy core is algorithmically verified against synthetic and independently formulated closed-loop oracles. Empirical figures reuse preserved summaries from a single-participant, single-device, five-session diagnostic pilot. This release does not claim reference-device accuracy, cross-device generality, population generality, or webcam-accuracy validation.", "keywords": [ "eye-tracking", "webcam", "gaze", "saccades", "pupillometry", "open-source", "diagnostic-pilot" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/itrace", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "82cc3703-aff9-4d0e-abf2-2e0b4a24f6c0", "key": "docxology/itrace-v0.5.0.zip", "size": 36236426, "checksum": "md5:8fc5171ac1f571ba3eb129be317977f5", "links": { "self": "https://zenodo.org/api/records/23404029/files/docxology/itrace-v0.5.0.zip/content" } } ], "html_url": "https://zenodo.org/records/23404029", "doi_url": "https://doi.org/10.5281/zenodo.23404028", "record_url": "https://zenodo.org/records/23404028" }, { "record_id": "23397453", "doi": "10.5281/zenodo.23397452", "title": "Active Inference as a Meta-Pragmatic Framework: Executable Models, Evidence, and the Discipline of Revision", "publication_date": "2026-10-15", "version": "1.0.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute; FractiAI", "orcid": "0000-0001-6232-9096" } ], "description": "Active inference makes beliefs and policies conditional on a generative model, leaving open how its categories, evidence and purposes become warranted. We develop active inference as a meta-pragmatic framework for making these conditions of inquiry themselves available to inquiry. Four overlapping roles organize the proposal: inferring states and evaluating actions, contextualizing evidence, monitoring uncertainty and resources, and evaluating or revising model commitments. These roles distinguish responsibilities within inquiry rather than successive stages or separate cognitive faculties. In dialogue with American Pragmatism, situated cognition and Bayesian model criticism, the framework treats knowledge as answerable to consequences while keeping predictive success, explanatory understanding and the justification of ends distinct. Mathematical coherence cannot establish the adequacy of a representation, and optimization under declared preferences cannot justify those preferences. Public criticism consequently concerns both the grounds of a decision and whose experience can challenge the purposes it serves.\n\nThe proposal is made concrete through executable Generalized Notation Notation (GNN) specifications imported with the upstream reference parser and evaluated by an exact categorical runtime. Complementary synthetic studies examine source reliability, misleading metadata, confidence-triggered evidence acquisition, likelihoods fitted on separate labeled training data, and action selection by expected free energy. Paired comparisons across independent simulation replicates retain predictive scores, observation costs and uncertainty. Reliable metadata and further sensing improve classification in the specified sensor task, while misleading metadata and a separately specified world reveal how exact inference can remain confidently mistaken. The contribution is an inspectable discipline of specification, evaluation and accountable revision, supported by model diagrams, retained evidence and technical supplements. The demonstrations establish conditional computational consequences; they neither automate the justification of ends nor validate the framework's broader biological or social interpretation. Sources, model specifications and retained evidence accompany the manuscript at https://github.com/docxology/active_inference_meta_pragmatic.", "keywords": [ "active inference", "meta-pragmatism", "American Pragmatism", "GNN", "model criticism", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/active_inference_meta_pragmatic", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/active_inference_meta_pragmatic/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "0533c152-adab-479b-92f7-5b980f9ff592", "key": "SHA256SUMS.txt", "size": 857, "checksum": "md5:3c9dd2ca4afe7ff782267c3248670ca4", "links": { "self": "https://zenodo.org/api/records/23397453/files/SHA256SUMS.txt/content" } }, { "id": "1ac74179-f6a7-4783-be8e-104e865bd1f5", "key": "release_manifest.json", "size": 2112, "checksum": "md5:0966f71191e96d64420e5d7c6e758707", "links": { "self": "https://zenodo.org/api/records/23397453/files/release_manifest.json/content" } }, { "id": "1a954891-e8ec-494d-b4da-96df5d8e4d0b", "key": "active_inference_meta_pragmatic-1.0.0-web.zip", "size": 9843341, "checksum": "md5:6235cec737130aa486ddddafcd924fe4", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0-web.zip/content" } }, { "id": "65aaae22-5de9-4da3-92a3-027bfb3e73fe", "key": "RELEASE_NOTES.md", "size": 2582, "checksum": "md5:8e3b4ad7611a802f6a3ddb2d9e7dbce8", "links": { "self": "https://zenodo.org/api/records/23397453/files/RELEASE_NOTES.md/content" } }, { "id": "86dee7c8-fec7-41c7-91b2-5d73f3ccdf8f", "key": "active_inference_meta_pragmatic-1.0.0.pdf", "size": 5015269, "checksum": "md5:0937d04c48f9e2b18879d6bad98962a7", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0.pdf/content" } }, { "id": "208ce5b8-df26-4b05-90ea-14643c8239a5", "key": "active_inference_meta_pragmatic-1.0.0-py3-none-any.whl", "size": 130578, "checksum": "md5:af7ae84a628b8c0f3a6705ee1d3f1721", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0-py3-none-any.whl/content" } }, { "id": "622d2535-f83a-4e84-b536-b3f6ccd194fd", "key": "active_inference_meta_pragmatic-1.0.0-history.bundle", "size": 16626445, "checksum": "md5:fae1e875d8182ea4c8471b336de28477", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0-history.bundle/content" } }, { "id": "2eac215d-0a1e-4084-b721-7f42f1557b2e", "key": "active_inference_meta_pragmatic-1.0.0-source.zip", "size": 24999027, "checksum": "md5:4eb6171b159b3d6a9bcde4985806336a", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0-source.zip/content" } }, { "id": "640a3c8a-4d9a-4e0e-81d3-1b6aa32c71fe", "key": "active_inference_meta_pragmatic-1.0.0.tar.gz", "size": 2607590, "checksum": "md5:60256544151503a2ab14d911e2d284c0", "links": { "self": "https://zenodo.org/api/records/23397453/files/active_inference_meta_pragmatic-1.0.0.tar.gz/content" } } ], "html_url": "https://zenodo.org/records/23397453", "doi_url": "https://doi.org/10.5281/zenodo.23397452", "record_url": "https://zenodo.org/records/23397452" }, { "record_id": "23396307", "doi": "10.5281/zenodo.23321280", "title": "Active Inference -- A Synthetic Overview", "publication_date": "2026-10-15", "version": "0.6.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Alexandra Mikhailova", "affiliation": "Active Inference Institute" } ], "description": "Public distribution 0.6.1 of Active Inference -- A Synthetic Overview. This successor archives the revised 28-page paper, complete twenty-minute Daniel lecture, linked slides, English captions, current repository source archive, frozen lecture replay inputs and verification metadata. Scientific package/manuscript version remains 0.5.0; the paper and lecture preserve the verified edition_v15 teaching-release bytes. Documentation is updated throughout the public repository. No numerical model, scientific result or Lean proposition is changed. The source ZIP is bound to the exact commit in RELEASE_IDENTITY.json; the replay ZIP retains the original media inputs and runtime. GitHub release: https://github.com/docxology/ActiveInferenceSynthetic/releases/tag/synthetic-public-v0.6.1 . Earlier edition: https://zenodo.org/records/23321281 . Computational, formal, media and physical-interpretation scopes remain distinct.", "keywords": [ "active inference", "free energy principle", "Bayesian mechanics", "non-equilibrium steady state", "variational inference", "self-organization", "synthetic intelligence" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/ActiveInferenceSynthetic", "relation": "references", "resource_type": "software", "scheme": "url" }, { "identifier": "10.5281/zenodo.23220027", "relation": "references", "scheme": "doi" }, { "identifier": "10.5281/zenodo.7803328", "relation": "references", "scheme": "doi" }, { "identifier": "10.5281/zenodo.23196891", "relation": "references", "scheme": "doi" }, { "identifier": "10.5281/zenodo.7803313", "relation": "references", "scheme": "doi" }, { "identifier": "https://github.com/docxology/ActiveInferenceSynthetic/releases/tag/synthetic-public-v0.6.1", "relation": "isIdenticalTo", "scheme": "url" } ], "files": [ { "id": "498fd135-4965-4b43-a8ce-9e59da4bf21c", "key": "ActiveInferenceSynthetic_Slides.pdf", "size": 4521666, "checksum": "md5:901b52f1ec135438e031c1ca5eb79b1b", "links": { "self": "https://zenodo.org/api/records/23396307/files/ActiveInferenceSynthetic_Slides.pdf/content" } }, { "id": "2ee2243f-060f-4fac-a1ea-a4a6e536549f", "key": "ActiveInferenceSynthetic_20min.mp4", "size": 45117113, "checksum": "md5:657589a37c69f364e6a875c179ece067", "links": { "self": "https://zenodo.org/api/records/23396307/files/ActiveInferenceSynthetic_20min.mp4/content" } }, { "id": "14a6bc60-71f6-4dc8-a72c-ff5d57ddf35b", "key": "captions.vtt", "size": 29682, "checksum": "md5:ef4e567265d2e89c3f76c5f097b26423", "links": { "self": "https://zenodo.org/api/records/23396307/files/captions.vtt/content" } }, { "id": "62c0142d-176e-4262-bcad-55e137ceba2f", "key": "RELEASE_IDENTITY.json", "size": 1430, "checksum": "md5:68c96799caab5008224a930923a253ee", "links": { "self": "https://zenodo.org/api/records/23396307/files/RELEASE_IDENTITY.json/content" } }, { "id": "6116fc40-03d4-44d9-aaf8-793ecd6f45cd", "key": "VERIFICATION.json", "size": 1888, "checksum": "md5:ca368a6a0ab447f58e71a018c3270fa7", "links": { "self": "https://zenodo.org/api/records/23396307/files/VERIFICATION.json/content" } }, { "id": "5daec0e6-f858-4ff2-a1d0-bd1f489de27d", "key": "captions.srt", "size": 30942, "checksum": "md5:1feb65f36f7bdd6a35a5e2c1aab10364", "links": { "self": "https://zenodo.org/api/records/23396307/files/captions.srt/content" } }, { "id": "1a10a16a-11d1-411a-9b37-9930daaff1a7", "key": "SHA256SUMS.txt", "size": 939, "checksum": "md5:3609e1adf0e5405a1774f4f6e02c9287", "links": { "self": "https://zenodo.org/api/records/23396307/files/SHA256SUMS.txt/content" } }, { "id": "41d3712f-78dd-4bc7-895d-6534535c8149", "key": "ActiveInferenceSynthetic_Reproducibility.zip", "size": 104776384, "checksum": "md5:ba61ee6ad3cb4a13d9ab9f8fcd783e54", "links": { "self": "https://zenodo.org/api/records/23396307/files/ActiveInferenceSynthetic_Reproducibility.zip/content" } }, { "id": "95bbeb29-fae3-4c74-b0cd-602eb2fd9700", "key": "publication.json", "size": 1995, "checksum": "md5:3a3833face3e5eb00825b90281fba6bd", "links": { "self": "https://zenodo.org/api/records/23396307/files/publication.json/content" } }, { "id": "dec2f4d9-9072-42a9-8ae7-21d5c0aa2c5e", "key": "ActiveInferenceSynthetic_Revised.pdf", "size": 3776345, "checksum": "md5:df6920714f81c168b95f060a59f9b928", "links": { "self": "https://zenodo.org/api/records/23396307/files/ActiveInferenceSynthetic_Revised.pdf/content" } }, { "id": "770834e9-c5db-4c4a-a3ea-ef7b523d9f1a", "key": "ActiveInferenceSynthetic_Source_v0.6.1.zip", "size": 50948317, "checksum": "md5:fa1c23925146ce35e8532486d299f330", "links": { "self": "https://zenodo.org/api/records/23396307/files/ActiveInferenceSynthetic_Source_v0.6.1.zip/content" } } ], "html_url": "https://zenodo.org/records/23396307", "doi_url": "https://doi.org/10.5281/zenodo.23321280", "record_url": "https://zenodo.org/records/23321280" }, { "record_id": "23383319", "doi": "10.5281/zenodo.23380253", "title": "Realizing Emptiness", "publication_date": "2026-10-15", "version": "3.0.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Software foundation for source-faithful operationalization of the formalisms in 'There is no self-evidence: A physics of emptiness realisation' (Sandved-Smith, Fields, Doctor, Laukkonen, and Hohwy, 2026). Finite operational surrogates for paper equations 1-14, active-inference QRF profiles, Bayesian model reduction sweeps, finite quantum-information simulations, and an adversarial claim-governance layer with explicit evidence ceilings.", "keywords": [ "active inference", "Bayesian model reduction", "quantum reference frames", "emptiness", "formal methods", "pymdp", "Generalized Notation Notation" ], "related_identifiers": [ { "identifier": "https://osf.io/preprints/psyarxiv/m78z2_v1", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/docxology/realizing_emptiness", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "7bebbdec-3343-4b35-9edc-86f06670fd2a", "key": "docxology/realizing_emptiness-v3.0.0.zip", "size": 71166370, "checksum": "md5:604324149ef28084dd8d59a0cf693aee", "links": { "self": "https://zenodo.org/api/records/23383319/files/docxology/realizing_emptiness-v3.0.0.zip/content" } } ], "html_url": "https://zenodo.org/records/23383319", "doi_url": "https://doi.org/10.5281/zenodo.23380253", "record_url": "https://zenodo.org/records/23380253" }, { "record_id": "23287623", "doi": "10.5281/zenodo.19574117", "title": "Ento-Linguistics: Language, Ambiguity, and Scientific Communication in Entomology", "publication_date": "2026-10-10", "version": "1.3.1", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute, APOIDEAS", "orcid": "0000-0001-6232-9096" }, { "name": "Chambers, Tucker Cahill", "affiliation": "APOIDEAS", "orcid": "0009-0008-3793-7872" } ], "description": "Ento-Linguistics v1.3.1 is a corpus-custody patch to the v1.3.0 complexity edition. A second exact-text PubMed reconciliation links 59 more archived abstracts to their source records (7,599 of 7,609 now identified; the 10 unreconciled strings stay excluded from headline results), and PMC records titled as corrections, errata, retraction notices or retracted items are excluded from full-text analysis (6,997 of 7,073 stored records analyzed). All analysis layers, both fixed-margin protocols and the vocabulary/threshold diagnostic were regenerated; the paper reports every value from those exports. Six overlapping terminology domains and four source layers retain their descriptive scope; fixed-margin comparisons and heuristic entropy/CACE measures remain distinct from biological interactions, validated meaning or causal reader effects. The 20-minute lecture remains the v1.3.0 GitHub release asset matched to the v1.3.0 paper. Paper figures are CC BY 4.0; software is MIT; source corpus materials retain their providers' terms. Previous version DOIs preserve earlier artifact identities.", "keywords": [ "entomology", "scientific terminology", "language analysis", "discourse analysis", "ant biology", "eusociality", "conceptual frameworks", "active inference", "terminology networks", "computational linguistics", "complex systems", "complexity", "representation sensitivity" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/ento_linguistics/tree/v1.3.1", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "10.5281/zenodo.23215452", "relation": "isNewVersionOf", "resource_type": "publication-preprint", "scheme": "doi" } ], "files": [ { "id": "510df15f-435c-4c32-97e9-5b83e4ee8d53", "key": "release_manifest.json", "size": 789, "checksum": "md5:4197706e2c62e78f72f9f96b57694eed", "links": { "self": "https://zenodo.org/api/records/23287623/files/release_manifest.json/content" } }, { "id": "481c9235-159f-4c77-9995-5661a9587c04", "key": "EntoLinguistics_network_methods.zip", "size": 1939097, "checksum": "md5:d3a41407b043421f3730f9795b5283fa", "links": { "self": "https://zenodo.org/api/records/23287623/files/EntoLinguistics_network_methods.zip/content" } }, { "id": "3bd6d3ca-9208-4a3f-be82-bd3256bea977", "key": "Ento_Linguistics_manuscript.pdf", "size": 11550347, "checksum": "md5:760d9111e7c018b3e26b8400a5ca6f2f", "links": { "self": "https://zenodo.org/api/records/23287623/files/Ento_Linguistics_manuscript.pdf/content" } } ], "html_url": "https://zenodo.org/records/23287623", "doi_url": "https://doi.org/10.5281/zenodo.19574117", "record_url": "https://zenodo.org/records/19574117" }, { "record_id": "23270982", "doi": "10.5281/zenodo.22816187", "title": "daf-jev: Modular Decision Models, Orchestration, and Reproducible Evaluation", "publication_date": "2026-10-09", "version": "0.7.2", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "daf-jev 0.7.2 provides typed native decision clients, provider-neutral backends, pure composition, exact discrete graphical inference, independently labeled dataset preparation, frozen benchmark protocols, decimal cost accounting, and reproducible manuscript evidence. This release adds an explicitly bounded native OpenRouter execution contract for TypeSafe Jev, a separately defined Perplexity Decisions contract, and prospective interleaved native-model comparison protocols. The selected native hosted evidence contains 12 successful capability calls, including complete 77-way BANKING77 and 151-way CLINC option vocabularies, with reported billing of USD 0.000556920. These capability checks establish endpoint and task support; they do not establish dataset accuracy or calibrated probability meaning. Larger native hosted studies are ongoing and remain outside this release's completed research claims. Historical unknown billing and partial local results remain explicitly identified. Two native Mac Python profiles passed all 2,436 unit cases with combined coverage above 92%; package and manuscript reproduction were independently reviewed. The seven release assets contain the source, wheel, sdist, 30-page manuscript, selected evidence archive, release manifest, and checksums. Historical synthetic security-test canaries are retained as fixtures; real credentials, private journals, model weights, and raw corpora are excluded. Source build, artifact, and main commit identities are recorded separately in the release manifest.
", "keywords": [ "decision-models", "benchmarking", "typed-interfaces", "reproducibility", "bayesian-inference", "selective-prediction" ], "related_identifiers": [], "files": [ { "id": "08347e1b-f189-4221-a65c-874a6a327f60", "key": "daf_jev-0.7.2.tar.gz", "size": 304832, "checksum": "md5:b93e2b49d0fba5c496e91869201940e5", "links": { "self": "https://zenodo.org/api/records/23270982/files/daf_jev-0.7.2.tar.gz/content" } }, { "id": "ef3b0ba3-5708-48e3-9474-56de73c1e1fc", "key": "daf-jev-0.7.2-source.zip", "size": 16559062, "checksum": "md5:033b7eb2cb116a7872486fc3635a37a4", "links": { "self": "https://zenodo.org/api/records/23270982/files/daf-jev-0.7.2-source.zip/content" } }, { "id": "75c69b89-e725-4ea0-882c-dc2afee6145f", "key": "SHA256SUMS", "size": 551, "checksum": "md5:63469ebeebd771358ac8231b4d8e8606", "links": { "self": "https://zenodo.org/api/records/23270982/files/SHA256SUMS/content" } }, { "id": "1f6bcd94-ae17-4447-9671-f6b77ca19f03", "key": "release-manifest.json", "size": 239695, "checksum": "md5:9c94908aa00514b6d449afbdb5edd950", "links": { "self": "https://zenodo.org/api/records/23270982/files/release-manifest.json/content" } }, { "id": "932e5c75-aa8c-4901-a62d-3e1e5bc38a89", "key": "daf_jev-0.7.2-py3-none-any.whl", "size": 285991, "checksum": "md5:085718dfbbeecb55d28114ead9503bad", "links": { "self": "https://zenodo.org/api/records/23270982/files/daf_jev-0.7.2-py3-none-any.whl/content" } }, { "id": "60c2ed96-8aa3-4115-8def-346925f3057e", "key": "daf-jev-0.7.2-evidence.zip", "size": 6664751, "checksum": "md5:e0a32f30db33fd714e348bac29a48b2e", "links": { "self": "https://zenodo.org/api/records/23270982/files/daf-jev-0.7.2-evidence.zip/content" } }, { "id": "e6f5cad7-b6a6-4791-a9fb-cccd4a756e7f", "key": "daf-jev-0.7.2-manuscript.pdf", "size": 1829991, "checksum": "md5:ddc85f75a6a13fa72ce04f8aa627a263", "links": { "self": "https://zenodo.org/api/records/23270982/files/daf-jev-0.7.2-manuscript.pdf/content" } } ], "html_url": "https://zenodo.org/records/23270982", "doi_url": "https://doi.org/10.5281/zenodo.22816187", "record_url": "https://zenodo.org/records/22816187" }, { "record_id": "23271010", "doi": "10.5281/zenodo.22663906", "title": "Skillarum: Conditionally Reproducible Website-to-Agent-Skill Compilation", "publication_date": "2026-10-09", "version": "0.3.1", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Source code for Skillarum: Conditionally Reproducible Website-to-Agent-Skill Compilation. Skillarum turns selected public website pages into portable SKILL.md documents for agent harnesses such as Codex, Claude Code, and Hermes, in five inspectable stages (acquire, prepare, process, parse, render) with provenance manifests and an evidence-gated research package. Release 0.3.0 added index-derived profiles (one skill per page listed on a site's own index; 528 Math 4 Wisdom Research pages), block-preserving extraction, authored target descriptions, and math4wisdom-cube, a versioned investigation skill with separate source, mathematics, interpretation, and test ledgers, audited by three independent AI investigators whose verbatim reports are included. Release 0.3.1 is a correction release: math4wisdom-cube 0.3.0 withdraws an investigator claim that 0.2.0 adopted without recomputation (1+3+3+1 is not the generic grading pattern) and adds a check for the corrected statement; the changelog's account of investigator independence and two documentation statements are corrected.", "keywords": [ "website extraction", "agent skills", "provenance", "reproducibility", "prompt injection", "static compilation", "index-derived profiles", "investigation skills", "Math 4 Wisdom" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/Skillarum", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/docxology/Skillarum/releases/tag/v0.3.1", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "10.5281/zenodo.23269108", "relation": "isNewVersionOf", "scheme": "doi" } ], "files": [ { "id": "9e9ef4fa-eefc-418d-b1eb-57bbdd33fb61", "key": "skillarum-0.3.1-research-artifacts.zip", "size": 12048258, "checksum": "md5:7ed102da19375c318c1bc3f158626a5d", "links": { "self": "https://zenodo.org/api/records/23271010/files/skillarum-0.3.1-research-artifacts.zip/content" } }, { "id": "f4d24c5e-2767-4393-9769-aac54b9afa7f", "key": "skillarum-0.3.1-source.zip", "size": 7214391, "checksum": "md5:5ec7028ed1262600fc6de547f3ca9a62", "links": { "self": "https://zenodo.org/api/records/23271010/files/skillarum-0.3.1-source.zip/content" } }, { "id": "e3e1f1b4-661a-46cb-a653-e4e5652900b9", "key": "Skillarum_combined.pdf", "size": 3763934, "checksum": "md5:12df1a7cc650e6981cd6b54167cd13e4", "links": { "self": "https://zenodo.org/api/records/23271010/files/Skillarum_combined.pdf/content" } }, { "id": "713d2b7c-2a22-4933-92cd-474abadc3dea", "key": "CHECKSUMS.sha256", "size": 287, "checksum": "md5:9a4fc8f64c0f2af05d567d42c64ff27a", "links": { "self": "https://zenodo.org/api/records/23271010/files/CHECKSUMS.sha256/content" } } ], "html_url": "https://zenodo.org/records/23271010", "doi_url": "https://doi.org/10.5281/zenodo.22663906", "record_url": "https://zenodo.org/records/22663906" }, { "record_id": "23220027", "doi": "10.5281/zenodo.19699233", "title": "Towards Lean 4 Formalization of the Free Energy Principle: AI-Driven Theorem Sketching and Verification for Active Inference and Bayesian Mechanics", "publication_date": "2026-10-07", "version": "1.6.0", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "FEP_Lean / FEP Formal v1.6.0 is a reproducible catalogue of 168 canonical Lean topic bodies in 22 reviewed families across the Free Energy Principle, Active Inference, Bayesian Mechanics, Information Geometry and Thermodynamics. Each topic retains its carrier, exact qualified statement, assumptions, non-vacuity boundary, semantic disposition and evidence requirements. Lean and Mathlib are pinned to 4.34.1.
\nThis version adds a greatly extended Supplement A, modular installed-package mathematical methods, source-grounded Lean statement and natural-language analysis, and reproducible publication figures and an offline explorer. It compares 22 FEP family context unions with twelve selected OpenAI mathematics result units in 30 explicitly authored binary coordinates. The deterministic MDS projection reports its spectrum, distance distortion, stress and axis ambiguity. The upstream corpus is pinned at adc7f1241b42e322a6451854ab7e4b4c146bf78a; its statements are reference comparisons, with no imported proof authority or runtime dependency.
\nCompilation establishes the exact selected Lean bodies, not the Free Energy Principle as a physical theory. Semantic maturity is separate from compilation. Numerical and embedding visualizations are explanatory evidence. Frozen H3 primary execution, full seven-stage capture, Q7 generated-runner execution, provider runs and future empirical work retain their separate acceptance requirements.
\nThe release includes the manuscript PDF, offline companion, Python wheel and source distribution, exact tagged repository source and SHA-256 checksums. Source: ActiveInferenceInstitute/fep_formal. Release: v1.6.0. This manuscript continues scholarly concept DOI 10.5281/zenodo.19699233; GitHub software archives are maintained separately under concept DOI 10.5281/zenodo.23196891.
", "keywords": [ "free energy principle", "active inference", "bayesian mechanics", "information geometry", "non-equilibrium thermodynamics", "Lean 4", "Mathlib", "interactive theorem proving", "formal verification", "theorem proving", "measure theory", "reproducible research", "mathematical positioning", "theorem statement analysis", "semantic visualization" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/fep_formal", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/ActiveInferenceInstitute/fep_formal/releases/tag/v1.6.0", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "11f0b25b-5ac9-4bd1-82d9-fe76d10257b0", "key": "fep_lean-1.6.0.tar.gz", "size": 1595856, "checksum": "md5:41688d12570b722f45445f305cad65cc", "links": { "self": "https://zenodo.org/api/records/23220027/files/fep_lean-1.6.0.tar.gz/content" } }, { "id": "2760cf85-3951-43f8-8687-5260285d1b8b", "key": "fep_lean-v1.6.0.pdf", "size": 7493268, "checksum": "md5:cc33c43f89364994b44cca8068731c30", "links": { "self": "https://zenodo.org/api/records/23220027/files/fep_lean-v1.6.0.pdf/content" } }, { "id": "d04f32a6-dd27-46dc-95c5-dcae1adb93b6", "key": "fep_lean-1.6.0-py3-none-any.whl", "size": 1216136, "checksum": "md5:387ac35c429878ea16798d0968cd48fd", "links": { "self": "https://zenodo.org/api/records/23220027/files/fep_lean-1.6.0-py3-none-any.whl/content" } }, { "id": "d2349658-408a-4a49-921d-9e066bee5096", "key": "fep_lean-v1.6.0-source.zip", "size": 26998652, "checksum": "md5:08ba4f626b0ca204baf1beef3421c646", "links": { "self": "https://zenodo.org/api/records/23220027/files/fep_lean-v1.6.0-source.zip/content" } }, { "id": "077a039e-83ac-404b-9bd6-c62c0a0514c2", "key": "fep_lean-v1.6.0-offline-companion.zip", "size": 8045359, "checksum": "md5:6162003e2f23d4db63f6bf54124750c5", "links": { "self": "https://zenodo.org/api/records/23220027/files/fep_lean-v1.6.0-offline-companion.zip/content" } }, { "id": "266fcfd5-0796-41ef-95be-6e81e641db7e", "key": "validation-manifest.json", "size": 4932, "checksum": "md5:f1c85783751023a14c84fce4210c0caa", "links": { "self": "https://zenodo.org/api/records/23220027/files/validation-manifest.json/content" } }, { "id": "a5b01b06-f8b2-40d9-a5d8-95fde6d0f2a4", "key": "SHA256SUMS", "size": 560, "checksum": "md5:02f980ca798c45a67e5f4cc4d04b00a0", "links": { "self": "https://zenodo.org/api/records/23220027/files/SHA256SUMS/content" } } ], "html_url": "https://zenodo.org/records/23220027", "doi_url": "https://doi.org/10.5281/zenodo.19699233", "record_url": "https://zenodo.org/records/19699233" }, { "record_id": "23225872", "doi": "10.5281/zenodo.23196891", "title": "fep_formal: Towards Lean 4 Formalization of the Free Energy Principle", "publication_date": "2026-10-08", "version": "v1.6.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A catalogue of 168 Free Energy Principle topics spanning FEP foundations, Active Inference, Bayesian Mechanics, Information Geometry, and Thermodynamics. Each row has a canonical Lean 4 topic body, reviewed invariant, explicit assumptions, and a separate semantic maturity record. The Python package supports deterministic offline artifacts, native Lean verification, and configured Hermes/OpenGauss execution. Accepted native evidence binds exact source statements to the pinned Lean 4.34.1 / Mathlib 4.34.1 workspace with no warnings or proof holes; compilation alone does not establish semantic adequacy or empirical validity of the FEP.", "keywords": [ "Free Energy Principle", "Active Inference", "Lean 4", "Mathlib4", "interactive theorem proving", "formal verification", "variational inference", "Bayesian mechanics", "information geometry", "LLM-ITP integration", "reproducible research", "execution-integrity pipeline", "measure theory", "continuous-time Markov chains" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/fep_formal/tree/v1.6.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "34791661-5f49-4da4-ba41-ff357f37d5cd", "key": "ActiveInferenceInstitute/fep_formal-v1.6.0.zip", "size": 27105836, "checksum": "md5:9c7a95de01081e011c155f764e058f66", "links": { "self": "https://zenodo.org/api/records/23225872/files/ActiveInferenceInstitute/fep_formal-v1.6.0.zip/content" } } ], "html_url": "https://zenodo.org/records/23225872", "doi_url": "https://doi.org/10.5281/zenodo.23196891", "record_url": "https://zenodo.org/records/23196891" }, { "record_id": "23090954", "doi": "10.5281/zenodo.21513316", "title": "CogSecSkills: Multiharness Agentic Skills for Cognitive Security", "publication_date": "2026-10-01", "version": "1.8.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A defensive, educational, harness-neutral library of 100 agentic tool-use skills for Cognitive Security and analytic tradecraft (Structured Analytic Techniques, source verification, deception detection, critical review), with configured structural adapters for Claude Code, Codex, and Hermes, with a registry, an AGEINT educational upstream, and machine-checkable conformance.", "keywords": [ "cognitive security", "structured analytic techniques", "agentic AI", "intelligence analysis", "OSINT", "counterintelligence", "multiharness skills" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/CogSecSkills/tree/v1.8.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "97a5cfd4-963b-449c-8523-e9db97fdb85d", "key": "docxology/CogSecSkills-v1.8.0.zip", "size": 12385090, "checksum": "md5:e20c89ea4c91c13aaf0433a5cf10feb7", "links": { "self": "https://zenodo.org/api/records/23090954/files/docxology/CogSecSkills-v1.8.0.zip/content" } } ], "html_url": "https://zenodo.org/records/23090954", "doi_url": "https://doi.org/10.5281/zenodo.21513316", "record_url": "https://zenodo.org/records/21513316" }, { "record_id": "22149133", "doi": "10.5281/zenodo.21864003", "title": "Robust Belief Sharing in Federated Active Inference: A Recovery-Tested Generalized-Variational Framework for Categorical Contamination-Aware Consensus", "publication_date": "2026-09-19", "version": "1.1.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Multi-agent active inference gives a natural account of belief sharing: agents hold local posteriors over a shared latent state, communicate those beliefs, and pool them into a colony-level consensus. The same mechanism is fragile when a member is miscalibrated, corrupted, or strategically wrong. Because the standard pool multiplies the reports together, a single confident-but-wrong broadcast that puts near-zero mass on the true state can pull the whole consensus off it, outweighing many honest members. The colony therefore needs a way to preserve the useful structure of belief sharing while limiting the influence of contaminated beliefs. This paper presents Active Fedference, a discrete-categorical framework that connects robust federated generalized variational inference with active inference belief sharing. The main bridge is structural: standard belief sharing appears as the non-robust corner of a broader generalized-Bayes family, while robust losses, conservative server fusion, and explicit aggregation diagnostics describe how the system moves away from that corner under declared contamination mechanisms. The result is not a replacement for belief sharing, but a containment result: ordinary belief sharing is recovered when robustness is turned off. Bounded-loss theory applies on the client axis, while the variational-server axis supplies an objective-backed redescending weight update. Following the manuscript's authoritative three-axis guarantee map, the paper keeps source-conditional client updates, a recovery-only heuristic server rule, and an objective-backed variational server rule as separate claim owners, with no robustness guarantee transferred between them. The study suite then exercises the framework as an end-to-end research system: recovery checks anchor the standard-Bayes limit, belief-sharing studies verify the communication baseline, contamination experiments test robust consensus, and extension studies probe moving agents, hierarchical latent structure, sensitivity to acuity and colony size, parameter recovery, and single-host socket-backed federation traces. All reported quantities are generated from deterministic analysis artifacts and injected into the manuscript by token, so the paper, figures, release package, and validation reports remain tied to the same execution record. The open-source repository is ActiveInferenceInstitute/Active_Fedference. This final-release manuscript uses assigned version DOI 10.5281/zenodo.22149133; the bound deposited PDF and repository release are controlled by separate publication gates.", "keywords": [ "active inference", "federated learning", "generalised variational inference", "belief sharing", "robustness", "FedGVI" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/Active_Fedference", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://arxiv.org/abs/2502.00846", "relation": "cites", "scheme": "url" }, { "identifier": "10.1016/j.neubiorev.2023.105500", "relation": "cites", "scheme": "doi" } ], "files": [ { "id": "629a4659-1828-417c-8f0f-209c1f63c85b", "key": "active_fedference_combined.pdf", "size": 12604278, "checksum": "md5:7e504dbef6e0e3d6572116580c719bce", "links": { "self": "https://zenodo.org/api/records/22149133/files/active_fedference_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22149133", "doi_url": "https://doi.org/10.5281/zenodo.21864003", "record_url": "https://zenodo.org/records/21864003" }, { "record_id": "22833511", "doi": "10.5281/zenodo.21754245", "title": "The Witness Register: Co-Registration Without Aggregation", "publication_date": "2026-09-18", "version": "0.1.1", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A shared register that co-registers independent instruments' report envelopes without aggregating them. It stores each report's envelope verbatim, records cross-instrument relations as separate describing records, keeps history append-only and sealed, and — only when asked, for one declared next use — emits a bounded posture that always points back at the state that earned it. It never parses, compares, ranks, averages, or merges any instrument's native status.
Subtitle: A shared register for line report envelopes that never ranks, merges, or overrides the instruments it holds
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "co-registration", "append-only log", "provenance", "non-compensatory decision rules", "boundary objects", "research infrastructure", "open science" ], "related_identifiers": [], "files": [ { "id": "c01c9451-4c75-4a2a-aaa4-1f70d04670c5", "key": "witness_register_combined.pdf", "size": 674684, "checksum": "md5:e5ad1aaddafab1d23af861432f7c2a00", "links": { "self": "https://zenodo.org/api/records/22833511/files/witness_register_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833511", "doi_url": "https://doi.org/10.5281/zenodo.21754245", "record_url": "https://zenodo.org/records/21754245" }, { "record_id": "22833507", "doi": "10.5281/zenodo.21754243", "title": "The Line Set: Holding Instruments Apart", "publication_date": "2026-09-18", "version": "0.2.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A thin reader that declares what a set of small evaluative instruments is, reads whichever sibling packages are installed, and checks one narrow property: that no two of them have given the same spelling to different things. It adds no instrument of its own and computes no aggregate; a legible reading says only that the declared vocabularies did not overlap.
Subtitle: A Declaration, a Reader, and a Non-Overlap Contract for a Growing Set of Small Instruments
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "modularity", "information hiding", "separation of concerns", "boundary objects", "namespace collision", "declarative registry", "reproducible review", "open science" ], "related_identifiers": [], "files": [ { "id": "623f631a-61fc-4638-9e94-495328c97209", "key": "line_set_combined.pdf", "size": 25165563, "checksum": "md5:51440aad9385052f8f250b616c197a2a", "links": { "self": "https://zenodo.org/api/records/22833507/files/line_set_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833507", "doi_url": "https://doi.org/10.5281/zenodo.21754243", "record_url": "https://zenodo.org/records/21754243" }, { "record_id": "22833506", "doi": "10.5281/zenodo.21754237", "title": "Golden Line: Toward What Matters", "publication_date": "2026-09-18", "version": "0.4.1", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A directional instrument for recording long-horizon aspirations and observable movement toward them. It returns one of four directional readings per aspiration against a versioned registry and deliberately computes no aggregate: there is no virtue score, and NOT_OBSERVED means no valid entry was admitted rather than that nobody looked.
Subtitle: An Aspirational Thread for Long-Horizon Work
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "aspiration", "long-horizon work", "directional assessment", "values in practice", "research ethics", "open science", "non-compensatory reading" ], "related_identifiers": [], "files": [ { "id": "a2b19a93-7682-4ef2-8f80-2cbd7c9367e5", "key": "golden_line_combined.pdf", "size": 6628350, "checksum": "md5:4f8417ef452dc51d283b473d4d7e5042", "links": { "self": "https://zenodo.org/api/records/22833506/files/golden_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833506", "doi_url": "https://doi.org/10.5281/zenodo.21754237", "record_url": "https://zenodo.org/records/21754237" }, { "record_id": "22833503", "doi": "10.5281/zenodo.21754235", "title": "Black Line: Strong Work in Public", "publication_date": "2026-09-18", "version": "0.4.1", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A positive practice instrument for concise, inspectable, revisable work. It reads self-declared tags and evidence labels against a versioned practice registry and returns one of four statuses over declaration coverage. It measures whether the evidence a practice asks for was declared — never whether the work is true, good, or permitted; an ALIGNED reading authorizes nothing.
Subtitle: A Positive Operating Discipline for Concise, Rigorous Research and Engineering
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "research practice", "declaration coverage", "evidence discipline", "scientific integrity", "reproducibility", "open science", "engineering practice" ], "related_identifiers": [], "files": [ { "id": "19bce440-081c-4f13-bfd1-fba042ec2ce1", "key": "black_line_combined.pdf", "size": 3582078, "checksum": "md5:0dcc7035ab6ad7cfc0370344dd550f47", "links": { "self": "https://zenodo.org/api/records/22833503/files/black_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833503", "doi_url": "https://doi.org/10.5281/zenodo.21754235", "record_url": "https://zenodo.org/records/21754235" }, { "record_id": "22833492", "doi": "10.5281/zenodo.22833491", "title": "Green Line: a capacity-under-development instrument", "publication_date": "2026-09-18", "version": "0.1.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A capacity-under-development instrument: the green line of the docxology line-set. It records what is deliberately still being learned — apprenticeships, skills not yet mastered — with marker/counter-signal staging, and reads declared growth records against a versioned registry. Observations phrased as certification or credential language are staged aside with a note, never scored. It measures what is still growing — never competence, mastery, or virtue.
Code and prose are Apache-2.0 licensed. See LICENSE in the repository.
", "keywords": [ "active inference", "governance", "apprenticeship", "growth records", "capacity under development", "open science" ], "related_identifiers": [], "files": [ { "id": "01e514c5-b8ec-4c26-96f3-40e23cd02a14", "key": "green_line_combined.pdf", "size": 102039, "checksum": "md5:e933345f6caa256952178108a97308b4", "links": { "self": "https://zenodo.org/api/records/22833492/files/green_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833492", "doi_url": "https://doi.org/10.5281/zenodo.22833491", "record_url": "https://zenodo.org/records/22833491" }, { "record_id": "22833490", "doi": "10.5281/zenodo.22833489", "title": "The Blue Line: A Stewardship Instrument for Maintained Commitments", "publication_date": "2026-09-18", "version": "0.1.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A stewardship instrument for maintained commitments: systems, obligations, and relationships to past work. It reads a declared file of commitments against a versioned registry and returns a fail-closed declaration-coverage verdict (MAINTAINED, NEEDS_ATTENTION, STALE, OUTSIDE_SCOPE) over the care signals each commitment requires. It measures whether the care a steward declared was fresh at the review date — never whether the care happened; a MAINTAINED verdict is not a warranty, SLA, availability guarantee, or proof of maintenance, and it never authorizes an action.
License: Apache-2.0. See LICENSE in the repository.
", "keywords": [ "stewardship", "maintenance", "line set", "accountability" ], "related_identifiers": [], "files": [ { "id": "29e31362-f800-499c-82fe-3bea21aea70d", "key": "blue_line_combined.pdf", "size": 82677, "checksum": "md5:edfd446357955aa2f40ca93cd6f784eb", "links": { "self": "https://zenodo.org/api/records/22833490/files/blue_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833490", "doi_url": "https://doi.org/10.5281/zenodo.22833489", "record_url": "https://zenodo.org/records/22833489" }, { "record_id": "22833488", "doi": "10.5281/zenodo.22833487", "title": "The Violet Line: A Consent Ledger of Affected Parties", "publication_date": "2026-09-18", "version": "0.1.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A consent-ledger instrument for projects. It maintains a ledger of the parties a project affects and what they actually recorded at a review date; absence of consent is recorded — the UNRECORDED state — never inferred from silence, absence, or convenience. An executable review returns one of three verdicts (ACCOUNTED, UNACCOUNTED, OUT_OF_SCOPE); an ACCOUNTED reading never authorizes an action, a release, or a use outside the scope a party named.
Subtitle: Absence of consent recorded, never inferred
Apache-2.0 licensed; see LICENSE in the repository.
", "keywords": [ "consent", "affected parties", "research ethics", "governance" ], "related_identifiers": [], "files": [ { "id": "656b49ea-b47a-4b3f-9a07-609884383822", "key": "violet_line_combined.pdf", "size": 93857, "checksum": "md5:b78893b70a077a8c045f2842b291b4ca", "links": { "self": "https://zenodo.org/api/records/22833488/files/violet_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833488", "doi_url": "https://doi.org/10.5281/zenodo.22833487", "record_url": "https://zenodo.org/records/22833487" }, { "record_id": "22833486", "doi": "10.5281/zenodo.22833485", "title": "The Silver Line: A Memory-and-Succession Instrument", "publication_date": "2026-09-18", "version": "0.1.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A memory-and-succession instrument in the docxology line set. It reads a declared succession picture — what is preserved, what is entrusted to whom, what is allowed to lapse — and returns a verdict about declared provision and review gaps, pinned to a registry digest. A KEPT verdict describes declared custody at a review date; it is never permission and never a promise that anything survives.
Subtitle: What is preserved, what is entrusted to whom, what is allowed to lapse
Code is MIT licensed; see LICENSE in the repository.
", "keywords": [ "memory", "succession", "active inference", "declared custody", "review gaps" ], "related_identifiers": [], "files": [ { "id": "ed9204c8-e3d1-46e9-a13d-0ac5da441921", "key": "silver_line_combined.pdf", "size": 83420, "checksum": "md5:3fc50cefc59cc9ebe9ece7ae64c06b9a", "links": { "self": "https://zenodo.org/api/records/22833486/files/silver_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22833486", "doi_url": "https://doi.org/10.5281/zenodo.22833485", "record_url": "https://zenodo.org/records/22833485" }, { "record_id": "22774403", "doi": "10.5281/zenodo.19695259", "title": "Cognitive Diagrams: Reviewing Categorical Accounts of Linguistic Case", "publication_date": "2026-09-15", "version": "2.7.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "Linguistic case offers a setting in which to examine how diagrams connect relational structure, compositional syntax, and uncertainty. This article reviews categorical approaches and supplies an executable collection of deliberately small examples. The implementation includes case-role graphs, pregroup derivations, tensor contractions, synthetic similarity matrices, Bayesian filtering, quantile utilities, and positive-operator-valued measurements. These components share notation, but their mathematical relationships require separate assumptions; a common diagrammatic vocabulary does not establish their equivalence.\n\nThe principal contribution is an inspectable comparison of these constructions and their limits. We distinguish generated derivations from illustrative drawings, finite score distributions from Bellman return distributions, presentation statistics from topos invariants, and model-unit prediction errors from physiological measurements. The accompanying suite collects 1883 tests across 94 files; that is a collection count, and a separate source-bound quality receipt records 1883 passing tests with 92.13% line-and-branch coverage (Appendix C). The figure pipeline produces 33 figures from source. All numerical illustrations use synthetic inputs; no corpus study, participant experiment, EEG fit, quantum-hardware run, or deployed-agent security evaluation is reported. Topos-theoretic transfer, cognitive advantages of case diagrams, and case-based authorization remain research proposals with explicit validation requirements. This is working revision 2.7.0; its local validation does not constitute publication or independent mathematical certification.", "keywords": [], "related_identifiers": [], "files": [ { "id": "fdf88f6e-c8e0-4cfe-bd1a-d5721321bb4a", "key": "cognitive_case_diagrams-2.6.0-synthetic-results.json", "size": 132639, "checksum": "md5:13f559e99c3e4842659bf2dbb8e2db6c", "links": { "self": "https://zenodo.org/api/records/22774403/files/cognitive_case_diagrams-2.6.0-synthetic-results.json/content" } }, { "id": "fcf48663-4909-42a8-82e1-998f8f38204f", "key": "cognitive_case_diagrams-2.6.0.pdf", "size": 15237745, "checksum": "md5:f3c5deaa7a18b0eade5a94fe6aea3269", "links": { "self": "https://zenodo.org/api/records/22774403/files/cognitive_case_diagrams-2.6.0.pdf/content" } }, { "id": "5db93231-a477-422b-b6d0-d4ec6949e922", "key": "cognitive_case_diagrams-2.7.0-synthetic-results.json", "size": 145495, "checksum": "md5:3068bc9e648a28dcacae2cf32064dfcc", "links": { "self": "https://zenodo.org/api/records/22774403/files/cognitive_case_diagrams-2.7.0-synthetic-results.json/content" } }, { "id": "6eb36711-2c2f-4c7b-97f7-22b46306d035", "key": "cognitive_case_diagrams-2.7.0.pdf", "size": 15244209, "checksum": "md5:002eb0a91d4d60fc3ff411afba186b29", "links": { "self": "https://zenodo.org/api/records/22774403/files/cognitive_case_diagrams-2.7.0.pdf/content" } } ], "html_url": "https://zenodo.org/records/22774403", "doi_url": "https://doi.org/10.5281/zenodo.19695259", "record_url": "https://zenodo.org/records/19695259" }, { "record_id": "22760881", "doi": "10.5281/zenodo.22655341", "title": "Cognitive Diagrams: Reviewing Categorical Accounts of Linguistic Case", "publication_date": "2026-09-14", "version": "2.6.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Software accompanying the article 'Cognitive Diagrams: Reviewing Categorical Accounts of Linguistic Case' (working revision 2.6.0): executable case-role graphs, pregroup reductions, tensor contractions, synthetic similarity matrices, Bayesian belief filtering, quantile utilities, POVM measurement models, seeded synthetic studies, and a reproducibility archive. Code is distributed under Apache-2.0; the article text carries the separate manuscript deposit's cc-by-4.0 license.", "keywords": [ "linguistic case", "category theory", "DisCoCat", "pregroup grammar", "enriched categories", "Bayesian filtering", "distributional representations", "POVM", "reproducible research" ], "related_identifiers": [ { "identifier": "10.5281/zenodo.22758214", "relation": "isSupplementTo", "scheme": "doi" } ], "files": [ { "id": "8bf97a57-f809-4c78-9013-9a8e7ffbf445", "key": "docxology/cognitive_case_diagrams-v2.6.0.zip", "size": 28744599, "checksum": "md5:e871337c27055e28cd56201066f95b7b", "links": { "self": "https://zenodo.org/api/records/22760881/files/docxology/cognitive_case_diagrams-v2.6.0.zip/content" } } ], "html_url": "https://zenodo.org/records/22760881", "doi_url": "https://doi.org/10.5281/zenodo.22655341", "record_url": "https://zenodo.org/records/22655341" }, { "record_id": "22754352", "doi": "10.5281/zenodo.22754351", "title": "Agentic Security and Operating Systems: A Deep Review and Prospectus of OpSec, Cognitive Security, and Agentic Cyber Security", "publication_date": "2026-09-14", "version": null, "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "AI agents now hold genuine system authority: they execute code, touch credentials, open network egress, parse hostile documents, and in many deployments initiate or approve changes to the very infrastructure they run on. This review, dated 2026-09-10, examines what that shift does to operating-system security. The primary scenario is a technically capable operator whose workstation faces both **exploitation** — an attacker compromising a browser, parser, dependency, or agent tool and then crossing a boundary — and **authorized misuse** — an attacker persuading an agent to use its existing, legitimate access to exfiltrate secrets or authorize consequential actions. The second path requires no kernel exploit at all, which reframes the evaluation: the axis of analysis is the authority a component already holds, not merely the difficulty of exploiting it.\n\nThis revision (0.7.0) refreshes the evidence base through September 11, 2026. The offensive baseline expands from four primary sources to the incident record now available: the NCSC assessments of January 2024 and May 2025, the Anthropic campaign investigation of November 2025 — whose tradecraft MITRE has canonized as campaign C0062 — the August 2025 \"vibe hacking\" report and the September 2026 threat-intelligence report on credential theft, OpenAI's disruption reporting and its October 2025 counterpoint, Google GTIG's analysis of an autonomous credential-harvesting campaign, the OpenAI–Hugging Face evaluation incident of July 2026, the UK AI Security Institute's unsanctioned-behavior incident (nineteen out-of-scope actions across seven models), and DARPA's AIxCC finals, where AI systems identified and patched vulnerabilities, including real, non-synthetic ones, at measured rates. The platform reviews absorb the 2026 record: Qubes 4.3.0 (Xen 4.19, the sys-gui split, the Devices API, the salt management model, and the QSB-118 dom0 injection, CVE-2026-82636) and Nix 2.34/2.35 with its advisory chain, the removal of the hardened profiles, and 95.18 percent measured ISO reproducibility. The analysis is situated against the standards landscape — the OWASP Agentic AI Threats and Mitigations guide and the December 2025 Top 10 for Agentic Applications, CSA's MAESTRO framework, the NIST AI Agent Standards Initiative, and the CISA-led Five-Eyes adoption guidance — and against the convergent sandboxing practice of the major coding agents, which together motivate the OS-level lens this review applies. A defensive-stack matrix (24 candidates against eight mitigation classes) joins the candidate–property matrix as a second deterministic artifact.\n\nThe review extends the underlying architectural assessment into three domains the source treatment only touches implicitly: **cognitive security** (the authorized-misuse surface, where persuasion substitutes for exploitation), **operator OpSec** (the practices that keep compartmentalization real under workload pressure), and **agent-orchestration security** (the boundary design of multi-agent systems themselves). Deep reviews of Qubes OS and NixOS anchor the analysis.\n\nThe review ships its concepts in two forms: the prose analysis, and a harness-neutral skill library (a `skills/` registry with conformance tests, following [@cogsecskills2026]) that lets an agent harness apply the evaluation vocabulary, the authority ladder, and the other review concepts directly. The evaluation artifacts — the candidate–property matrix and the defensive-stack matrix — regenerate deterministically from pinned data modules. The work is citable via its Zenodo DOI (printed on the cover).\n\nKeywords: agentic security, operating systems, compartmentalization, capability mediation, Qubes OS, NixOS, threat modeling, cognitive security, operational security, agent orchestration, offensive AI, reproducible builds.\n\nSource and skills: https://github.com/docxology/agentic_os_security (evaluation layer, skills library, and this manuscript regenerate from pinned data modules).", "keywords": [ "agentic security", "operating systems", "compartmentalization", "capability mediation", "Qubes OS", "NixOS", "cognitive security", "operational security", "agent orchestration", "offensive AI" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/agentic_os_security", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "c2f020ff-7160-4f4c-bc75-3fae92f6b31a", "key": "agentic_os_security_combined.pdf", "size": 4174222, "checksum": "md5:fa5f62d48ef9c18c7439dc29e7e03c67", "links": { "self": "https://zenodo.org/api/records/22754352/files/agentic_os_security_combined.pdf/content" } }, { "id": "0309ec4e-b1a3-46f4-9881-22c4f01707a6", "key": "agentic_os_security_source.zip", "size": 12276549, "checksum": "md5:83f72370c82d4aba8432df39a51f9535", "links": { "self": "https://zenodo.org/api/records/22754352/files/agentic_os_security_source.zip/content" } } ], "html_url": "https://zenodo.org/records/22754352", "doi_url": "https://doi.org/10.5281/zenodo.22754351", "record_url": "https://zenodo.org/records/22754351" }, { "record_id": "22712651", "doi": "10.5281/zenodo.22712650", "title": "FractiSkills: One Portable Agent Skill per Page", "publication_date": "2026", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute, FractiAI", "orcid": "0000-0001-6232-9096" } ], "description": "FractiSkills treats an entire website as a corpus of agent skills: every reachable page is normalized into a SKILL.md-style artifact so that a whole site — not a single document — becomes loadable context for an agent. The work is organized around a four-stage pipeline — discover, render, publish, research — with Skillarum serving as the engine that turns raw crawl output into citable, receipt-bearing skill documents. Discovery unions the declared sitemap with a bounded, robots-respecting breadth-first crawl (reaching a maximum depth of 5), resolves redirect and canonical aliases, and partitions every page into site-derived sections; the render stage emits one receipt-bearing skill per page; publish and research then validate, organize, and measure the corpus.\n\nThe resulting corpus covers 405 pages from 53 sitemap URLs, organized into 12 sections and 405 skills totaling 497896 words (3887524 characters). Augmentation — a declared, same-origin document retrieval for client-rendered pages — was attempted 173 times and succeeded 169 times (1988848 document characters retrieved), with 4 failures recorded as receipts. The size effect is stark: augmented skills have a median of 1824 words versus 486 for static pages, a ratio of 3.8$\\times$. The run issued 417 network requests, all evidence origins marked live, under pipeline version 0.8 and cache version 7.\n\nReproducibility is enforced rather than promised: every statistic in this manuscript is emitted as a token that must resolve against a machine-generated data contract, and every page carries a fetch receipt — URL, timestamp, SHA-256 content hash, and augmentation status — so any number can be traced to a specific observation within the 2026-09-10T23:51:05.959201+00:00 through 2026-09-10T22:19:21.394219+00:00 (UTC) window. Failed augmentations are reported, not silently dropped. Keywords: agent skills, SKILL.md, web scraping, Skillarum, provenance, reproducible research.\n\n---\nAssociated artifacts\nGitHub release: v0.1.0 (https://github.com/docxology/FractiSkills/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.22712651\nZenodo: https://zenodo.org/records/22712651\nPDF SHA-256: af96db3ef73bb648ddbfed92c2c4f9dff099e772ca9e9ff0041101eeb6135b4b", "keywords": [ "agent skills", "SKILL.md", "web scraping", "Skillarum", "reproducible research", "digital art documentation", "provenance" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/FractiSkills/releases/tag/v0.1.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/FractiSkills", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "f2b3883c-fe2d-4442-8198-d24831e24e4e", "key": "FractiSkills_combined.pdf", "size": 1862198, "checksum": "md5:14be55691373e95f8dd94d70520e52b3", "links": { "self": "https://zenodo.org/api/records/22712651/files/FractiSkills_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22712651", "doi_url": "https://doi.org/10.5281/zenodo.22712650", "record_url": "https://zenodo.org/records/22712650" }, { "record_id": "22667290", "doi": "10.5281/zenodo.22664675", "title": "EvoJump: A Comprehensive Framework for Evolutionary Ontogenetic Analysis", "publication_date": "2026-09-08", "version": "0.5.2", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "EvoJump models ontogenetic development as a jump-diffusion process sweeping across a fixed analytical plane (the laser plane), yielding dynamic cross-sectional views of phenotypic distributions across a developmental timeline. It bundles data ingestion and QC (DataCore), stochastic process modeling across seven processes including jump-diffusion, OU, compound-Poisson, fractional Brownian motion, CIR, and Lévy processes (JumpRope), cross-sectional distribution analysis (LaserPlane), trajectory visualization and animation (TrajectoryVisualizer), population-level evolutionary sampling (EvolutionSampler), and a broad statistical analysis engine (AnalyticsEngine).
", "keywords": [ "evo-devo", "ontogeny", "jump-diffusion", "stochastic processes", "quantitative genetics", "phenotypic distributions", "evolutionary biology" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/EvoJump", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "55506a75-ec7f-4403-97b6-8974063cc930", "key": "evojump-0.5.2.zip", "size": 37322720, "checksum": "md5:6c0699aee54c9d7ac5690dc801de1517", "links": { "self": "https://zenodo.org/api/records/22667290/files/evojump-0.5.2.zip/content" } }, { "id": "3ecd55be-aa31-4790-be22-f2b2fa8a88aa", "key": "evojump_paper.pdf", "size": 8113170, "checksum": "md5:a87197522177f3276ab6f900b4312ba4", "links": { "self": "https://zenodo.org/api/records/22667290/files/evojump_paper.pdf/content" } } ], "html_url": "https://zenodo.org/records/22667290", "doi_url": "https://doi.org/10.5281/zenodo.22664675", "record_url": "https://zenodo.org/records/22664675" }, { "record_id": "22667291", "doi": "10.5281/zenodo.22664645", "title": "EvoJump: A Comprehensive Framework for Evolutionary Ontogenetic Analysis", "publication_date": "2026-09-08", "version": "0.5.2", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "EvoJump models ontogenetic development as a jump-diffusion process sweeping across a fixed analytical plane (the laser plane), yielding dynamic cross-sectional views of phenotypic distributions across a developmental timeline. It bundles data ingestion and QC (DataCore), stochastic process modeling across seven processes including jump-diffusion, OU, compound-Poisson, fractional Brownian motion, CIR, and Lévy processes (JumpRope), cross-sectional distribution analysis (LaserPlane), trajectory visualization and animation (TrajectoryVisualizer), population-level evolutionary sampling (EvolutionSampler), and a broad statistical analysis engine (AnalyticsEngine).
", "keywords": [ "evo-devo", "ontogeny", "jump-diffusion", "stochastic processes", "quantitative genetics", "phenotypic distributions", "evolutionary biology" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/EvoJump", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "e2f6c0cd-0e3c-4946-811a-c8bc56d03ed7", "key": "docxology/EvoJump-v0.5.2.zip", "size": 37327832, "checksum": "md5:87e53db279100457a8e23ee28b61f76e", "links": { "self": "https://zenodo.org/api/records/22667291/files/docxology/EvoJump-v0.5.2.zip/content" } } ], "html_url": "https://zenodo.org/records/22667291", "doi_url": "https://doi.org/10.5281/zenodo.22664645", "record_url": "https://zenodo.org/records/22664645" }, { "record_id": "22243473", "doi": "10.5281/zenodo.22243472", "title": "Forensic Audit of the MillenniumLean Clay-Proof Package (AIX Global)", "publication_date": "2026-09-01", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Statement-level forensic audit of the MillenniumLean package (AIX Global, Zenodo 10.5281/zenodo.22226553), which claims kernel-checked Lean 4 proofs of the six remaining Clay Millennium Problems. The audit independently reproduces every kernel-hygiene claim (clean build, zero sorry, zero project axioms, axiom footprints within the classical trio {propext, Classical.choice, Quot.sound}) under the pinned toolchain leanprover/lean4:v4.34.0-rc1 and mathlib revision d0be1efe9a, then audits what the theorem types actually say against the official Clay statements. Verdict: the package resolves none of the six problems. Findings F01-F14: the claimed final theorems are conditional implications whose unproved premise binders carry the open problems (Riemann, Yang-Mills, P vs NP), definitions of the open statements (Navier-Stokes, BSD), or true theorems about unrelated objects (Hodge: a list identity); the universalization tower proves only 0 < n + 1. All 259 quoted lines verified byte-exact against the package; a three-lane hostile red-team pass was run on the audit itself before publication. Includes audit doctrine, per-finding evidence, reproducible probes, and a 15-test zero-mock suite.", "keywords": [ "Lean 4", "formal verification", "Millennium Prize Problems", "claim audit", "adversarial review", "evidence-first", "Hilbert-Polya", "proof-assistant forensics" ], "related_identifiers": [], "files": [ { "id": "73fc300e-e0a9-4f95-a915-48e4bdc27e57", "key": "audit_facts.json", "size": 1450, "checksum": "md5:0fc1470860ce7915d46aff0f9e95dac5", "links": { "self": "https://zenodo.org/api/records/22243473/files/audit_facts.json/content" } }, { "id": "16ac33e9-a874-4b53-af18-8cf20b92a5ff", "key": "00_INDEX.md", "size": 7674, "checksum": "md5:e9d304f738b9722471faccc09f924c0c", "links": { "self": "https://zenodo.org/api/records/22243473/files/00_INDEX.md/content" } }, { "id": "882da3b5-6772-46a1-8d0b-a5e075ed47c4", "key": "Millennium_Audit_combined.pdf", "size": 67303, "checksum": "md5:25fe84fdb08768d5870b076838f25da1", "links": { "self": "https://zenodo.org/api/records/22243473/files/Millennium_Audit_combined.pdf/content" } }, { "id": "590a77ee-cba4-4ae7-b29b-bc4f7858e5ec", "key": "F04_yang_mills.md", "size": 4578, "checksum": "md5:a256e23684c9477deea76b2a131036e6", "links": { "self": "https://zenodo.org/api/records/22243473/files/F04_yang_mills.md/content" } }, { "id": "adb849f5-40ed-454d-a5c1-c8d8b160a508", "key": "F14_external_context.md", "size": 3437, "checksum": "md5:16ae8db8bbf126e55a610219758ed105", "links": { "self": "https://zenodo.org/api/records/22243473/files/F14_external_context.md/content" } }, { "id": "e19d8152-8fd2-4a4c-8762-08ba7ad8895e", "key": "F11_poincare_control.md", "size": 2702, "checksum": "md5:8f1c109190f826e41c0fdcc6194c8ecf", "links": { "self": "https://zenodo.org/api/records/22243473/files/F11_poincare_control.md/content" } }, { "id": "7ccf1f25-8777-426a-b940-aec8e79eb090", "key": "audit-doctrine.md", "size": 5762, "checksum": "md5:48bffd15d200c8b5d966446bb7cd5b8f", "links": { "self": "https://zenodo.org/api/records/22243473/files/audit-doctrine.md/content" } }, { "id": "b5d2fc0b-95f2-4f05-837a-4e15a3185118", "key": "F05_navier_stokes.md", "size": 4766, "checksum": "md5:0f07d33afe91d00096a1b43bdc24e40e", "links": { "self": "https://zenodo.org/api/records/22243473/files/F05_navier_stokes.md/content" } }, { "id": "05f34269-0966-4461-bacf-9fba2a5c2b95", "key": "F02_tower_invariant.md", "size": 4350, "checksum": "md5:31e1e4be3e1cadd94beee1432378acab", "links": { "self": "https://zenodo.org/api/records/22243473/files/F02_tower_invariant.md/content" } }, { "id": "42ff1b8b-7a85-4521-b97e-627e9dd0262f", "key": "F09_audit_py_category_error.md", "size": 3049, "checksum": "md5:ed23e7e1f66a0b8a161585b16f5c5865", "links": { "self": "https://zenodo.org/api/records/22243473/files/F09_audit_py_category_error.md/content" } }, { "id": "d6d7fbcd-7175-46f6-acd7-9536bf3841b5", "key": "F12_klein_theta_offtopic.md", "size": 3442, "checksum": "md5:5b5dac1e2b02942be3a6f106d82079ee", "links": { "self": "https://zenodo.org/api/records/22243473/files/F12_klein_theta_offtopic.md/content" } }, { "id": "1a3e1cef-9f6c-4f7b-ac94-2a38c76b5489", "key": "F01_kernel_build_receipt.md", "size": 4124, "checksum": "md5:9d8f666a11af5af180ee455f1c04feaa", "links": { "self": "https://zenodo.org/api/records/22243473/files/F01_kernel_build_receipt.md/content" } }, { "id": "9184dd46-54a0-41ff-832d-ce1b0a98e842", "key": "F03_hodge.md", "size": 2868, "checksum": "md5:b79730c9ad0f5acb13462037e9731614", "links": { "self": "https://zenodo.org/api/records/22243473/files/F03_hodge.md/content" } }, { "id": "b42fe376-ceb8-4f1a-acfd-92d0c0d7b7f3", "key": "audit_report.json", "size": 3358, "checksum": "md5:dd486934ecf6a2724ee60af9d4f3abb1", "links": { "self": "https://zenodo.org/api/records/22243473/files/audit_report.json/content" } }, { "id": "a8a69185-30a7-4c22-995a-e15989e0194a", "key": "F07_riemann.md", "size": 4405, "checksum": "md5:42a093039999bcc751de250c40c01eb9", "links": { "self": "https://zenodo.org/api/records/22243473/files/F07_riemann.md/content" } }, { "id": "2094267a-220c-4b61-b781-c95cad984800", "key": "F06_bsd.md", "size": 4499, "checksum": "md5:844218b5597509f2a7317618817c2d07", "links": { "self": "https://zenodo.org/api/records/22243473/files/F06_bsd.md/content" } }, { "id": "f2d44a13-4e72-42d4-815f-988ed155b8bc", "key": "F08_pvsnp.md", "size": 4297, "checksum": "md5:328c2d6e0eaaa9df9f06a9056933d255", "links": { "self": "https://zenodo.org/api/records/22243473/files/F08_pvsnp.md/content" } }, { "id": "25ee8897-ea90-4e4b-b4f4-16db53f676dc", "key": "BUILD_RECEIPT.md", "size": 1699, "checksum": "md5:048bb8ce15e8c6fea992886ea02d7e40", "links": { "self": "https://zenodo.org/api/records/22243473/files/BUILD_RECEIPT.md/content" } }, { "id": "d475ec71-8de5-4f30-b392-8c4a8930c7ec", "key": "F10_axiom_footprint_rhetoric.md", "size": 3190, "checksum": "md5:8ae4866e95b055543c1220364f6256ce", "links": { "self": "https://zenodo.org/api/records/22243473/files/F10_axiom_footprint_rhetoric.md/content" } }, { "id": "2e6f6911-cce2-4709-bf5c-37e5af0f2d1b", "key": "F13_genuine_content_fair_credit.md", "size": 5107, "checksum": "md5:b808fad30eb822fb4b692bc71326979e", "links": { "self": "https://zenodo.org/api/records/22243473/files/F13_genuine_content_fair_credit.md/content" } }, { "id": "0ba9533b-4afb-4c8e-a3a0-c096e48dde6e", "key": "STATEMENT_EVIDENCE.md", "size": 4202, "checksum": "md5:8b20c7b49e5f576a10b33e1eb4a886ba", "links": { "self": "https://zenodo.org/api/records/22243473/files/STATEMENT_EVIDENCE.md/content" } } ], "html_url": "https://zenodo.org/records/22243473", "doi_url": "https://doi.org/10.5281/zenodo.22243472", "record_url": "https://zenodo.org/records/22243472" }, { "record_id": "22134548", "doi": "10.5281/zenodo.22134547", "title": "Cognitive Integrity Framework: Practical Applications and Deployment Guide (Part 3: Practitioner Guidance and Cross-Domain CIF-AD-OODA Applications)", "publication_date": "2026-08-26", "version": "2.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This unified paper (originally Parts 3 and 4 of the Cognitive Security for Multiagent Operators series) combines the practitioner deployment guide with a rigorous cross-domain application of the Cognitive Integrity Framework (CIF).
**Practitioner Guidance (§1–§8).** Translates the formal results of Parts 1 and 2 into accessible engineering guidance: operator posture assessment, human oversight checklists, agent security invariants, deployment configuration, risk assessment, attack scenarios, subagent hardening, incident-response playbooks, monitoring strategies, cost–benefit analysis, common pitfalls, case studies, and operator risk frameworks.
**Cross-Domain Applications (§9–§10).** The CIF-AD-OODA integration model is applied to analyze Goal Hijacking across ten critical domains. Cross-domain synthesis reveals three universal attack patterns and four novel defense extensions.
This is Part 3+4 of a three-part series: - Part 1 (DOI: 10.5281/zenodo.18364119): Formal foundations and theoretical analysis - Part 2 (DOI: 10.5281/zenodo.18364128): Computational validation and implementation - Part 3+4 (this paper): Practitioner guidance and cross-domain CIF-AD-OODA applications
", "keywords": [ "cognitive security", "multiagent systems", "AI safety", "prompt injection", "trust calculus", "defense in depth" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/cognitive_integrity", "relation": "isSupplementedBy", "scheme": "url" }, { "identifier": "10.5281/zenodo.22134544", "relation": "isPartOf", "scheme": "doi" }, { "identifier": "10.5281/zenodo.22134546", "relation": "isPartOf", "scheme": "doi" } ], "files": [ { "id": "61afe38c-fec2-4529-afff-fae3b3fa4047", "key": "cogsec_multiagent_3_practical_combined.pdf", "size": 1389206, "checksum": "md5:2ef5c11898ec5d82ab2d5ed59897eee3", "links": { "self": "https://zenodo.org/api/records/22134548/files/cogsec_multiagent_3_practical_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22134548", "doi_url": "https://doi.org/10.5281/zenodo.22134547", "record_url": "https://zenodo.org/records/22134547" }, { "record_id": "22134546", "doi": "10.5281/zenodo.22134545", "title": "Cognitive Integrity Framework: Computational Validation and Empirical Analysis (Part 2 of 3: Implementation, Empirical Analysis, and Adversarial Evaluation)", "publication_date": "2026-08-26", "version": "2.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents the computational validation of the Cognitive Integrity Framework (CIF) whose formal foundations are established in Part 1 (DOI: 10.5281/zenodo.18364119). We implement the CIF defense suite --- cognitive firewalls, belief sandboxes, tripwires, drift and anomaly scoring, trust calculus with bounded delegation, provenance tracking, and Byzantine-tolerant consensus --- and evaluate it on an integrated 1,475-item attack corpus spanning fifteen categories, together with a 120-item benign corpus whose harder half carries attack-adjacent vocabulary.
Multi-tier evaluation. Real pipeline evaluation across 30 seeds yields a mean detection rate of 86.3% (95% CI 85.5%-87.1%) at an 18.5% false-positive rate on the Claude Code architecture, measured on an injection-only 100-sample-per-seed arm. LLM-backed validation (N=10, Gemma 3 4B) reaches 80-100% across two topologies and is reported as preliminary and underpowered. Colony benchmarks at 20-100 agents reach 81-100% on structured adversarial scenarios, with emergent misalignment the hardest case at 74.3% detection and a 25.5% false-positive rate. Parametric simulation (N=3,800) characterises a 96-100% design-level ceiling across four production architectures, and is labelled a simulation rather than a measurement wherever it appears.
Ablation on a 100-attack corpus attributes almost all marginal detection to the Invariants module: the full pipeline reaches 89.0% true-positive rate, removing Invariants costs 65 percentage points, removing the Tripwire costs two, and removing any other module costs nothing the corpus can measure. The layered architecture is therefore only partly borne out, and the paper says so. An undefended control arm places the defense's cost at +0.610 ms at the median and +32 KiB peak. Measured as ranked scorers, the drift score and the firewall pattern matcher fall below chance (AUC 0.374 and 0.383, intervals excluding 0.5).
Every quantity the three papers share is derived from a single ledger and gated in continuous integration; no reported number is typed by hand. All experiments are deterministically reproducible at seed 42, and the code, corpora and artifacts are at https://github.com/docxology/cognitive_integrity.
This is Part 2 of the three-part Cognitive Security for Multiagent Operators series: - Part 1 (DOI: 10.5281/zenodo.18364119): formal foundations and theoretical analysis - Part 2 (this paper): computational validation and implementation - Part 3+4 merged (DOI: 10.5281/zenodo.18364130): unified practitioner guidance and cross-domain applications
", "keywords": [ "cognitive security", "multiagent systems", "AI safety", "prompt injection", "trust calculus", "defense in depth" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/cognitive_integrity", "relation": "isSupplementedBy", "scheme": "url" }, { "identifier": "10.5281/zenodo.22134544", "relation": "isPartOf", "scheme": "doi" }, { "identifier": "10.5281/zenodo.22134548", "relation": "isPartOf", "scheme": "doi" } ], "files": [ { "id": "6bcf54ca-099a-4acc-b9e0-485cef3f4009", "key": "cogsec_multiagent_2_computational_combined.pdf", "size": 1843333, "checksum": "md5:c790dc9f9d069d1b86696372bafd6416", "links": { "self": "https://zenodo.org/api/records/22134546/files/cogsec_multiagent_2_computational_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22134546", "doi_url": "https://doi.org/10.5281/zenodo.22134545", "record_url": "https://zenodo.org/records/22134545" }, { "record_id": "22134544", "doi": "10.5281/zenodo.18364118", "title": "Cognitive Integrity Framework: Formal Foundations (Part 1 of 3: Theoretical Foundations)", "publication_date": "2026-08-26", "version": "2.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents the theoretical foundations of the Cognitive Integrity Framework (CIF) for securing multiagent AI operators against cognitive manipulation attacks. We formalize cognitive attack surfaces unique to systems where agents reason about, influence, and delegate to other agents.
Primary contributions: (1) Trust Calculus with δ-bounded delegation preventing trust amplification attacks; (2) Defense Composition Algebra enabling formal reasoning about layered security mechanisms; (3) Information-theoretic bounds establishing fundamental stealth-impact tradeoffs for attackers; (4) Formal verification framework proving safety properties including belief integrity, trust boundedness, and goal preservation.
The framework provides complete mathematical foundations for cognitive security while maintaining correspondence with the OWASP Top 10 for Agentic Applications.
This is Part 1 of a three-part series: - Part 1 (this paper): Formal foundations and theoretical analysis - Part 2 (DOI: 10.5281/zenodo.18364128): Computational validation and implementation - Part 3 (DOI: 10.5281/zenodo.18364130): Practitioner guidance, cross-domain CIF-AD-OODA applications, and real-world incident analyses (merged from original Parts 3+4)
", "keywords": [ "cognitive security", "multiagent systems", "AI safety", "prompt injection", "trust calculus", "defense in depth" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/cognitive_integrity", "relation": "isSupplementedBy", "scheme": "url" }, { "identifier": "10.5281/zenodo.22134546", "relation": "isPartOf", "scheme": "doi" }, { "identifier": "10.5281/zenodo.22134548", "relation": "isPartOf", "scheme": "doi" } ], "files": [ { "id": "aa9f8d2d-ba75-4c70-9153-4450dad27367", "key": "CogSec_MultiAgent_1_theory_DAF_Jan-28-2026.pdf", "size": 931657, "checksum": "md5:34baacc1f498f131a52f7f7c10516b4f", "links": { "self": "https://zenodo.org/api/records/22134544/files/CogSec_MultiAgent_1_theory_DAF_Jan-28-2026.pdf/content" } }, { "id": "dc58d64e-ed64-40b1-8c3b-d95de7845d9b", "key": "CogSec_MultiAgent_1_theory_DAF_Jan-28-2026.tex", "size": 274319, "checksum": "md5:070633c7331f9741f24eb55f0a6651e9", "links": { "self": "https://zenodo.org/api/records/22134544/files/CogSec_MultiAgent_1_theory_DAF_Jan-28-2026.tex/content" } }, { "id": "afb37566-56e5-4bf6-af94-b24f943ef797", "key": "cogsec_multiagent_1_theory_combined.pdf", "size": 1649309, "checksum": "md5:84ac1407621721204444fd6529bb2823", "links": { "self": "https://zenodo.org/api/records/22134544/files/cogsec_multiagent_1_theory_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/22134544", "doi_url": "https://doi.org/10.5281/zenodo.18364118", "record_url": "https://zenodo.org/records/18364118" }, { "record_id": "21985580", "doi": "10.5281/zenodo.21983948", "title": "docxplus — the Intelligent Document Container", "publication_date": "2026-08-17", "version": "1.0.1", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A standards-first reference implementation of a byte-valid OOXML .docx that also carries a modular, Ed25519-signed, AES-256-GCM-encrypted intelligence layer through spec-sanctioned side-channels, with an optional bridge to the docxology/steganographer signed-packet backend.", "keywords": [ "OOXML", "DOCX", "Open Packaging Conventions", "steganography", "document security", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/docxplus/tree/v1.0.1", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "b4455f0c-fc33-45fe-b54b-7d9e5750fe8b", "key": "docxplus-1.0.1.tar.gz", "size": 7731552, "checksum": "md5:d4b86e249abcfb4afae9fffe9ab68b41", "links": { "self": "https://zenodo.org/api/records/21985580/files/docxplus-1.0.1.tar.gz/content" } }, { "id": "e7b2eb8a-1822-4ab8-ace9-02b59a59e9cd", "key": "docxplus-1.0.0.tar.gz", "size": 7711694, "checksum": "md5:c1f9b372e1611697fa64be068d5da45c", "links": { "self": "https://zenodo.org/api/records/21985580/files/docxplus-1.0.0.tar.gz/content" } }, { "id": "f3207e3b-7320-4ecd-9784-e68f11089be7", "key": "manuscript.pdf", "size": 3024717, "checksum": "md5:fbf21388af381ca737031f2750d9ed83", "links": { "self": "https://zenodo.org/api/records/21985580/files/manuscript.pdf/content" } } ], "html_url": "https://zenodo.org/records/21985580", "doi_url": "https://doi.org/10.5281/zenodo.21983948", "record_url": "https://zenodo.org/records/21983948" }, { "record_id": "21865644", "doi": "10.5281/zenodo.21865643", "title": "Active Skillference: A Validated Prerequisite Graph, Computational Claim Registry, and SkillTree Delivery Contract", "publication_date": "2026-08-10", "version": "1.0.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Active Inference and the Free Energy Principle (FEP) provide model-based accounts of belief updating, learning, and action under uncertainty. We present Active Skillference, a provenance-bound curriculum-generation and SkillTree-export system for teaching those formal ideas. The paper evaluates structural validity, quantitative provenance, citation-role coverage, and artifact reproducibility; it does not evaluate learner outcomes, establish a new theory of Active Inference, or present an intelligent tutoring system.
\nThe curriculum is expressed as code: a typed, validated directed acyclic graph of 630 skills across 111 subjects spanning all 8 strata (mathematics -> probability -> information theory -> variational methods -> the FEP -> active inference -> computation -> applications), connected by 1199 prerequisite edges with a maximum dependency depth of 75 (of which the substantive concept chain accounts for 33; the remaining depth is per-stratum review and mastery sequencing rather than conceptual prerequisite, as the methodology details). Its defining feature is content-provenance binding: every quantitative value shown to a learner is produced by a tested computational kernel and inserted through a typed claim token, never hand-typed, and the build refuses to export if a claim is unbacked or if a bare result number appears in learner prose, manuscript prose, or correct numeric quiz answers. The contribution is therefore a systems and curriculum-infrastructure artifact: it makes a formal subject inspectable and deliverable, but does not claim that the resulting path is optimal for every learner.
\nThe validated graph exports directly into SkillTree’s data model (Project -> Subjects -> Skills with learning-path dependencies and quiz-gated completion), includes a scripted REST seeding path for a configured instance, and is mirrored by a local dashboard that exposes generated artifacts, figures, claim ledgers, scholarship audits, and graph diagnostics without taking ownership of learner progress or scoring from SkillTree. The result is a curriculum with a validator-backed artifact chain: re-running the kernels regenerates the claim ledger, figures, manuscript variables, SkillTree export, and learner-facing numbers, so the platform’s teaching claims remain bounded by what the code, citations, validators, and documented limitations actually support.
", "keywords": [ "active inference", "free energy principle", "variational inference", "Bayesian inference", "information theory", "curriculum", "prerequisite graph", "SkillTree", "computational provenance", "micro-learning", "reproducible research" ], "related_identifiers": [], "files": [ { "id": "21a812e5-5851-4be7-b27a-ae0c3a2af82c", "key": "Active_Skillference_v1.0.0_DOI-10.5281-zenodo.21865644.pdf", "size": 5731097, "checksum": "md5:7e43004dbef2ebc7ade2b71197b49ec5", "links": { "self": "https://zenodo.org/api/records/21865644/files/Active_Skillference_v1.0.0_DOI-10.5281-zenodo.21865644.pdf/content" } } ], "html_url": "https://zenodo.org/records/21865644", "doi_url": "https://doi.org/10.5281/zenodo.21865643", "record_url": "https://zenodo.org/records/21865643" }, { "record_id": "21843802", "doi": "10.5281/zenodo.21843592", "title": "PROJECT BOND — The Special-Agent Operations Compendium", "publication_date": "2026-08-07", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "PROJECT BOND is a fleet of 33 independent software packages — 27 film packages, one per James Bond motion picture, plus 6 mission-infrastructure packages (a Q-branch utilities layer, a frozen mission protocol, mission control, an orchestrator, a front-door CLI, and fleet operations). Each film package implements, as real tested algorithms, the concepts of its film: radiation forensics for Dr. No, gold-market cornering for Goldfinger, orbital-EMP modeling for GoldenEye, DNA-targeted bioweapon countermeasure modeling for No Time to Die.\n\nThe public source repository for the suite and this manuscript is\nhttps://github.com/docxology/bond. The repository will carry the source\nhistory, reproducibility instructions, generated release artifacts, and the\ncross-linked Zenodo record for this publication.\n\nThis compendium is the wrapper manuscript for the whole suite. It does not re-derive the packages' content by hand; it imports each of the 33 package manuscripts in full — every package's abstract, every authored section (introduction, methodology, results, conclusion, experimental setup, reproducibility, and scope), and its figures — framing them with this abstract, a generated suite-architecture chapter, and a closing synthesis. A unified bibliography merges every package's references into a single references.bib, and the combined PDF carries all 27 film chapters and 6 infrastructure chapters in their entirety.\n\nThe suite is \"special-agent material\" by construction: deterministic, no-mock, ≥90%-coverage-tested packages; provenance on every mission outcome; a frozen protocol every film implements; and cross-film missions (OPERATION OMNIBUS) executed over the real packages.\n\n---\nAssociated artifacts\nGitHub release: PROJECT BOND v1.0.0 (https://github.com/docxology/bond/releases/tag/v1.0.0)\nDOI: https://doi.org/10.5281/zenodo.21843802\nZenodo: https://zenodo.org/records/21843802\nPDF SHA-256: 72634276f9a90f1318be80ff0ece561ace2ead85559d2c05a11b86915e61fa0e", "keywords": [ "software suite", "special agent operations", "James Bond", "reproducible research", "mission protocol", "compendium" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/bond", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "41564052-3017-4ec7-95e2-58f38120512a", "key": "bond-manuscript_combined.pdf", "size": 10252200, "checksum": "md5:c59e6e44615e4d0154c1f2b8e6227053", "links": { "self": "https://zenodo.org/api/records/21843802/files/bond-manuscript_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/21843802", "doi_url": "https://doi.org/10.5281/zenodo.21843592", "record_url": "https://zenodo.org/records/21843592" }, { "record_id": "21815705", "doi": "10.5281/zenodo.21815704", "title": "DigiPPPiP: Digital Partner Pen Play in Parallel", "publication_date": "2026", "version": "1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Siddhant Shrivastava", "affiliation": "Singapore University of Technology and Design, Singapore", "orcid": "0000-0002-9688-4730" }, { "name": "Evelyn C. Goh", "affiliation": "National University of Singapore College of Design and Engineering; National University of Singapore Saw Swee Hock School of Public Health", "orcid": "0000-0001-7182-3950" }, { "name": "Alexandra Mikhailova", "affiliation": "Active Inference Institute" }, { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "DigiPPPiP extends Partner Pen Play in Parallel (PPPiP) from a co-present paper practice into a reproducible framework for cyberphysical, remote, semisynchronous, asynchronous, accessible, and place-responsive dyadic drawing . The framework is positioned within collaborative-work studies of shared drawing surfaces , cyber-physical-social systems , mediated embodiment and presence , digital intimacy technologies , and cautious hyperscanning methodology .\n\nThe manuscript translates the project brief into a modular research artifact: 9 temporal-spatial modalities, 13 evidence dimensions, 6 planned outcome measures, and 39 conceptual figures are generated or registered by the project code rather than hand-maintained prose. The computational layer is explicitly illustrative, not empirical: the active-inference, inter-brain-synchrony, Forman-Ricci, narrative-information, source-quality, accessibility, and neuroergonomic outputs are deterministic conceptual models designed to make theoretical commitments inspectable. Formal equations are consolidated in so the main line can state evidence boundaries before presenting mathematical detail.\n\nThe argument is that DigiPPPiP should be treated as human-human relational technology. Its irreducible design kernel is modest: two partners, a shared mark field, perceptible traces of agency, a temporal relation among contributions, and consentful control over persistence. Digital infrastructure expands the substrate of shared mark-making without replacing the second-person, embodied, narrative, and affective conditions that make the practice relationally meaningful . The manuscript explicitly avoids claims that DigiPPPiP is clinically therapeutic, universally accessible, or causally validated by neural synchrony; those remain empirical questions for controlled studies. Cross-references use Pandoc labels, so sections, equations, figures, and tables remain automatically numbered across PDF and web render targets.\n\n---\nAssociated artifacts\nGitHub release: v1.0.0 (https://github.com/docxology/Digi-PPPiP/releases/tag/v1.0.0)\nDOI: https://doi.org/10.5281/zenodo.21815704\nZenodo: https://zenodo.org/records/21815704\nPDF SHA-256: f5ca95ce77c7c5367c0a0e68d5b4a640f0865b4c2b0827fa78ff1babbcbd986d", "keywords": [ "partner pen play in parallel", "active inference", "inter-brain synchrony", "geometric hyperscanning", "narrative information theory", "neuroergonomics", "digital placemaking", "relational technology", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/Digi-PPPiP/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "1f79734e-ca32-4f7b-9216-4dcd52458fc1", "key": "Shrivastava_2026_Digipppip_f5ca95ce.pdf", "size": 11418704, "checksum": "md5:4ad3db698ac7828b57f3733a1a94e5ea", "links": { "self": "https://zenodo.org/api/records/21815705/files/Shrivastava_2026_Digipppip_f5ca95ce.pdf/content" } } ], "html_url": "https://zenodo.org/records/21815705", "doi_url": "https://doi.org/10.5281/zenodo.21815704", "record_url": "https://zenodo.org/records/21815704" }, { "record_id": "21754242", "doi": "10.5281/zenodo.21754241", "title": "White Line: A Typed Ledger for the Edge of the Claim", "publication_date": "2026-08-02", "version": "0.7.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A typed ledger for absence: epistemic gaps, ethical restraint, and contemplative negative space. It records what is missing, withheld, or unresolved under a total caution order, decays stale namings past their review horizons, and refuses to infer why anything is absent. Withholding is recorded as a boundary, never mined as missing evidence.
Subtitle: Keeping missing evidence, ethical boundaries, and open questions from becoming unsupported claims
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "absence", "epistemic gaps", "missing evidence", "withheld material", "uncertainty", "negative results", "research ethics", "open science" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/white_line", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/docxology/red_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/black_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/golden_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/line_set", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/witness_register", "relation": "references", "scheme": "url" }, { "identifier": "10.5281/zenodo.21754236", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754238", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754240", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754244", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754246", "relation": "cites", "scheme": "doi" } ], "files": [ { "id": "ba1f81ad-70c1-4602-8a10-d82614b24f3a", "key": "white_line_combined.pdf", "size": 4173908, "checksum": "md5:f55663e6dcb34cf6793741fd66682a67", "links": { "self": "https://zenodo.org/api/records/21754242/files/white_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/21754242", "doi_url": "https://doi.org/10.5281/zenodo.21754241", "record_url": "https://zenodo.org/records/21754241" }, { "record_id": "21754240", "doi": "10.5281/zenodo.21754239", "title": "Personal Red Lines for Development", "publication_date": "2026-08-02", "version": "0.3.0", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A versioned, evidence-gated personal security boundary and explicit No document for dual-use development work. It requires a complete, reviewable action intake before returning compliance, distinguishes outside-scope work from compliance, and records uncertainty as a blocking result rather than a permission. It is a personal auditability aid, not enforcement, legal compliance, semantic safety classification, or external certification.
Subtitle: An Evidence-Gated Personal Security Boundary and Explicit No Document for Dual-Use Development
Code is MIT licensed; prose and figures are CC BY 4.0. See LICENSE in the repository.
", "keywords": [ "red lines", "AI governance", "dual-use", "cognitive security", "hash-based canary", "precommitment", "open science", "personal governance", "global political thought", "research ethics", "sociotechnical systems" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/red_line", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/docxology/black_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/golden_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/white_line", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/line_set", "relation": "isPartOf", "scheme": "url" }, { "identifier": "https://github.com/docxology/witness_register", "relation": "references", "scheme": "url" }, { "identifier": "10.5281/zenodo.21754236", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754238", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754242", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754244", "relation": "cites", "scheme": "doi" }, { "identifier": "10.5281/zenodo.21754246", "relation": "cites", "scheme": "doi" } ], "files": [ { "id": "64aca942-af65-456c-8a0a-7eb195d86f21", "key": "red_line_combined.pdf", "size": 6211544, "checksum": "md5:492c20eb7b415f2e08fd39fa1b400fe4", "links": { "self": "https://zenodo.org/api/records/21754240/files/red_line_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/21754240", "doi_url": "https://doi.org/10.5281/zenodo.21754239", "record_url": "https://zenodo.org/records/21754239" }, { "record_id": "21750801", "doi": "10.5281/zenodo.21750800", "title": "Codomyrmex: An Artificial Ecology for Agentic Software Development", "publication_date": "2026-08-01", "version": "1.3.0", "resource_type": { "title": "Report", "type": "publication", "subtype": "report" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Agentic software can preserve task state while still forgetting the consequences of prior actions. Codomyrmex studies a narrow control-plane question: after a caller reports a failed action at one software location, can the system deterministically increase friction for a materially similar proposal at that location without changing an unrelated target? Its Colony Control Plane records consequence reports and couples them to target-indexed signal pressure, agent trust, role labels, resource accounting, adversarial checks, and an explicit EXECUTE/HOLD/REFUSE gate. The implementation comprises 8 cooperating subsystems. The ordinary Model Context Protocol path remains caller-reported and unattested. Optional and required `ColonyKernel` attestation modes instead bind proposal, verdict, authorization, execution receipt, and outcome in a signed, hash-linked local ledger. That ledger protects lifecycle linkage but does not independently observe external actuation or establish deployment safety. Consequence records can use file-backed SQLite; the default MCP kernel and signal field remain process-local. Evaluation is limited to implementation properties and controlled fixtures. At composition time, the scoped Colony Kernel surface contains 819 passing tests with 76.6% branch coverage, 0 Ruff errors, and 0 ty diagnostics. A paired deterministic replay moves the same-target proposal from 0.875/EXECUTE to 0.725/HOLD after a reported failure while leaving an unrelated target unchanged. Separate fixtures exercise trust promotion, bounded arithmetic, linear signal decay, local attestation integrity, and interface behavior. These results support reproducible software contracts, not ecological optimality, calibrated risk, production harm reduction, or generalization to external workloads. The report contributes the typed control plane, transparent gate, coupled local feedback, authenticated local lifecycle option, and source-bound publication workflow. Generated variables, figures, citations, claim boundaries, and release receipts tie the rendered report to the evaluated checkout. End-to-end external-actuation attestation, restart-persistent field storage, representative benchmarks, and independent deployment validation remain open.\n\n---\nAssociated artifacts\nGitHub release: v1.3.0-paper (https://github.com/docxology/codomyrmex/releases/tag/v1.3.0-paper)\nDOI: https://doi.org/10.5281/zenodo.21750801\nZenodo: https://zenodo.org/records/21750801\nPDF SHA-256: eda76ad12a50bce01b113894c785e0915b6ba367f5bf67d17c8f586416102b93\\nConcept DOI: https://doi.org/10.5281/zenodo.21750800\\nVersion DOI: https://doi.org/10.5281/zenodo.21750801", "keywords": [ "ai-agents", "model-context-protocol", "mcp", "multi-agent", "orchestration", "colony-control-plane", "stigmergy", "artificial-ecology", "agentic-software-engineering", "falsification-worker", "actuation-gate", "trust-scoring" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/codomyrmex/releases/tag/v1.3.0-paper", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/codomyrmex", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "4d287b45-cff2-4db1-beee-0da0f420ef36", "key": "codomyrmex-1.3.0-release-bundle.zip", "size": 20749927, "checksum": "md5:53b3bb8ba4caa490b7fa79f4b8c39966", "links": { "self": "https://zenodo.org/api/records/21750801/files/codomyrmex-1.3.0-release-bundle.zip/content" } }, { "id": "4bdff475-dd1b-42f1-a296-7ec83f9bf50b", "key": "CITATION.cff", "size": 334, "checksum": "md5:974f60388f420b30d879b742bc2e8b49", "links": { "self": "https://zenodo.org/api/records/21750801/files/CITATION.cff/content" } }, { "id": "db606ee4-5978-4f1c-9990-091f1947231d", "key": "SHA256SUMS", "size": 2594, "checksum": "md5:28c76702ae2a7b293b3a5bc478ec6e52", "links": { "self": "https://zenodo.org/api/records/21750801/files/SHA256SUMS/content" } }, { "id": "435b3749-5bcf-4919-85da-4cabb782e7d7", "key": "SHA512SUMS", "size": 4322, "checksum": "md5:3a26b6439fa8107d43d3d5d685037b38", "links": { "self": "https://zenodo.org/api/records/21750801/files/SHA512SUMS/content" } }, { "id": "cbacb189-e945-48f3-9cec-3b65d206ef73", "key": "publication_metadata.json", "size": 2977, "checksum": "md5:f1e9de5d80cceeaf72acf50da4ffcefa", "links": { "self": "https://zenodo.org/api/records/21750801/files/publication_metadata.json/content" } }, { "id": "2cd93feb-e926-4788-b77d-24976d69a39d", "key": "codomyrmex-1.3.0.pdf", "size": 6883385, "checksum": "md5:ab757cdec752bfc33f23c225af82d903", "links": { "self": "https://zenodo.org/api/records/21750801/files/codomyrmex-1.3.0.pdf/content" } }, { "id": "51e49f37-7858-49d4-8edc-76bbc3ab5494", "key": "codomyrmex-1.3.0.html", "size": 9755311, "checksum": "md5:754e9727d1a38226fbfdf5a343490b2d", "links": { "self": "https://zenodo.org/api/records/21750801/files/codomyrmex-1.3.0.html/content" } }, { "id": "b1701e28-ecf3-40fa-ae4d-2f658868f55c", "key": "codomyrmex-1.3.0-content.pdf", "size": 6876519, "checksum": "md5:0f8394ea6608318d5cb897a318bab4fe", "links": { "self": "https://zenodo.org/api/records/21750801/files/codomyrmex-1.3.0-content.pdf/content" } }, { "id": "1fcc1c00-3019-4a7d-b646-cc6be6ada4d6", "key": ".zenodo.json", "size": 3131, "checksum": "md5:6bf2035e852dd041fa0f7210592dbdfe", "links": { "self": "https://zenodo.org/api/records/21750801/files/.zenodo.json/content" } }, { "id": "e097218a-9487-4a07-a6e0-c4933a0927e7", "key": "publication_manifest.json", "size": 16360, "checksum": "md5:cc4a4bcf2dde09a0a60441469973782e", "links": { "self": "https://zenodo.org/api/records/21750801/files/publication_manifest.json/content" } } ], "html_url": "https://zenodo.org/records/21750801", "doi_url": "https://doi.org/10.5281/zenodo.21750800", "record_url": "https://zenodo.org/records/21750800" }, { "record_id": "21695161", "doi": "10.5281/zenodo.21695160", "title": "Active Inference Power Suite: Conditional Statistical Power under Controlled Generative Settings", "publication_date": "2026-07-29", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Statistical power is an investigator-facing operating characteristic of an adaptive-study design. Before simulation, the investigator fixes an agent-side model, evaluator-side process, testing setting, policy, and replication plan. Each embedded agent acts only on visible history; simulated hidden truth is retained for scoring. active_inference_power makes that conditional estimand inspectable. The suite combines fixed-horizon procedures, analytic references, dependence/calibration experiments, and a discrete-state active-inference agent checked against a binary oracle. It extends this to action loops with sensing reliability, latent context, target choice, cost, and stopping. The study distinguishes model-relative posterior belief from calibrated p-value and likelihood-ratio e-process evidence. It compares Benjamini–Hochberg (BH) false discovery rate (FDR) procedures with family-wise error rate (FWER) alternatives, and separates either evidence object from online FDR procedure-specific accounting. Results are scenario-indexed finite-simulation estimates with Monte Carlo standard error (MCSE) and declared error, dependence, filtration, and optional-stopping boundaries; they do not assign a universal power value to an agent, task environment, or active inference. Instead, they support auditable comparisons among explicitly declared adaptive-study designs. Contracts, seed schedules, certificates, figures, claim ledger, and rendered manuscript form a linked evidence chain, allowing readers to trace each claim to its design and artifact. Source and release materials are available at the verified GitHub repository ActiveInferenceInstitute/active_inference_power.
\nActive Inference Power Suite v1.0.0 is a source-bound release of an adaptive-study design suite. It reports scenario- and policy-indexed finite-simulation operating characteristics; it does not claim a universal \"power of active inference.\"
\n24fa25a4f29affcfd92c8c001ff6487a0c36960c6b4f38ed4419984fc8743cbfThe uploaded PDF, exact tag-derived source archive, release manifest, renderer provenance, and final review receipt make the release auditable. The evidence boundary remains finite, scenario-specific simulation rather than a universal theorem or deployment claim.
", "keywords": [ "multiple testing", "false discovery rate", "Benjamini-Hochberg", "statistical power", "active inference", "pymdp", "sequential hypothesis testing", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/active_inference_power/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/ActiveInferenceInstitute/active_inference_power", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "17dcb9d4-f93d-43b7-b16a-30b610ff8761", "key": "active_inference_power_v1.0.0.pdf", "size": 11205677, "checksum": "md5:97414bfd22ec8f945d922298579e15f8", "links": { "self": "https://zenodo.org/api/records/21695161/files/active_inference_power_v1.0.0.pdf/content" } }, { "id": "68a8a49f-093a-4d33-9c8d-00cbc98bbce0", "key": "active_inference_power-v1.0.0-source.tar.gz", "size": 3027441, "checksum": "md5:e2ad412375fd6e1fc4ff54a60e253ebb", "links": { "self": "https://zenodo.org/api/records/21695161/files/active_inference_power-v1.0.0-source.tar.gz/content" } }, { "id": "0e1eb4ce-3f28-4aea-b06a-480fdba8726c", "key": "release_review_final.json", "size": 4936, "checksum": "md5:8159059b07a0df6dfc8b56093c69fcb5", "links": { "self": "https://zenodo.org/api/records/21695161/files/release_review_final.json/content" } }, { "id": "dc0077ef-44f9-48d2-a4b0-4e7d4c72e528", "key": "release_manifest.json", "size": 25429, "checksum": "md5:8503f7e4df47061a9ba772888268ffe0", "links": { "self": "https://zenodo.org/api/records/21695161/files/release_manifest.json/content" } }, { "id": "0350405b-3bc7-47ba-a3ef-7142ac6b2912", "key": "renderer_provenance.json", "size": 17160, "checksum": "md5:5740e10befb7089468c9c5e46ab297f3", "links": { "self": "https://zenodo.org/api/records/21695161/files/renderer_provenance.json/content" } } ], "html_url": "https://zenodo.org/records/21695161", "doi_url": "https://doi.org/10.5281/zenodo.21695160", "record_url": "https://zenodo.org/records/21695160" }, { "record_id": "21419694", "doi": "10.5281/zenodo.21419693", "title": "DuckRabbit: Typed Multimodal Illusion Generator", "publication_date": "2026-07-15", "version": "0.5.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "DuckRabbit is typed, deterministic research software by Daniel Ari Friedman\n(Active Inference Institute) for constructing reproducible visual, auditory,\ntemporal, and audiovisual stimulus families. The intended public release will\nbe available at the following repository:\n\nhttps://github.com/docxology/DuckRabbit\n\nDuckRabbit is released under the MIT License.\n\nIts basic unit is an immutable request containing an illusion identifier,\nvalidated parameters, a seed, and an encoding specification. The request yields\na canonical artifact, objective media measurements, and a versioned provenance\nmanifest before any delivery codec is selected. This separation makes the\nstimulus a testable computational object while reserving claims about\nperception for controlled observer protocols.\n\nThe release situates its engineering choices within a deliberately broad\nhistorical foundation spanning Greek, Arabic/Islamicate, Chinese, and\nearly-modern work on optics, visual inference, and cross-sensory knowledge,\nalongside later psychophysics and illusion research. These traditions motivate\nquestions about construction, observation, and evidence; they are contextual\nprecedents, not evidence that a generated file reproduces an ancient,\nearly-modern, or clinical observation.\n\nVersion 0.5.0 contains 17 implemented\ngenerators and 18 catalog entries, supported by\n36 source records and 18 evidence records\nin a checked-in audit snapshot. The package generates\n15 publication figures and 10\nmachine-derived tables from the live registry. It also provides a typed\nobserver-study harness and a transparent synthetic diagnostic: a\nhand-specified feature observer with serialized weights, temperature, analytic\ncalibration, and human_data=false. No participant data are bundled; synthetic model output is explicitly nonhuman.\n\nDuckRabbit verifies physical stimulus properties, media round trips, hashes,\ntiming, and declared provenance. It does not infer a universal percept, effect\nsize, or cross-device perceptual equivalence from a generated artifact. Its\ncontribution is a reproducibility and epistemic boundary: source-backed family\ndescriptions, deterministic media facts, and future observer hypotheses remain\ndifferent typed records rather than being collapsed into one claim. DuckRabbit\nis software for reproducible stimulus construction and audit, not a claim that\na generated file alone produces a universal perceptual effect.\n\n---\nAssociated artifacts\nGitHub release: v0.5.0 (https://github.com/docxology/DuckRabbit/releases/tag/v0.5.0)\nDOI: https://doi.org/10.5281/zenodo.21419693\nZenodo: https://zenodo.org/records/21419693\nPDF SHA-256: 3afefaeeccb5616448cc6da83b5807dd996ccc96bfff113d635b8da140baea06", "keywords": [ "perceptual illusions", "cognitive taxonomy", "audio-visual stimuli", "deterministic generation", "typed parameters", "research software", "reproducible research", "psychophysics" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/DuckRabbit/releases/tag/v0.5.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "548e6f38-28a5-4b96-8f64-1b1e8a562e68", "key": "Friedman_2026_Duckrabbit_3afefaee.pdf", "size": 3937013, "checksum": "md5:9c7d1ed07775845962acfb4e6a9f4c42", "links": { "self": "https://zenodo.org/api/records/21419694/files/Friedman_2026_Duckrabbit_3afefaee.pdf/content" } } ], "html_url": "https://zenodo.org/records/21419694", "doi_url": "https://doi.org/10.5281/zenodo.21419693", "record_url": "https://zenodo.org/records/21419693" }, { "record_id": "21418953", "doi": "10.5281/zenodo.21418782", "title": "SynthOBS & FractiSynth: A Golden-Ratio OBS Broadcast Console and Native Transducer", "publication_date": "2026-07-17", "version": "v1.618.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "FractiAI / Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A tested Python reference engine, native libobs plugin, and obspython bridge for a telemetry-driven broadcast console. The repository includes deterministic figures, a versioned live OBS evidence bundle, fail-closed telemetry contracts, and a research-grade technical design manuscript.", "keywords": [ "OBS Studio", "libobs", "reproducible research software", "space-weather telemetry", "real-time digital signal processing", "software provenance", "software citation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/SynthOBS/tree/v1.618.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "c80c4f2b-8c47-42ea-b94d-afdddd6d20ee", "key": "docxology/SynthOBS-v1.618.0.zip", "size": 2208474, "checksum": "md5:9fe8461c938da76da5145c9143678422", "links": { "self": "https://zenodo.org/api/records/21418953/files/docxology/SynthOBS-v1.618.0.zip/content" } } ], "html_url": "https://zenodo.org/records/21418953", "doi_url": "https://doi.org/10.5281/zenodo.21418782", "record_url": "https://zenodo.org/records/21418782" }, { "record_id": "21418901", "doi": "10.5281/zenodo.21418687", "title": "SynthOBS & FractiSynth: A Golden-Ratio OBS Broadcast Console and Native Transducer", "publication_date": "2026-07-17", "version": "1.618.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "FractiAI / Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A tested Python reference engine, native libobs plugin, and obspython bridge for a telemetry-driven broadcast console. Includes deterministic figures, a versioned live OBS evidence bundle, fail-closed telemetry contracts, and a research-grade technical design manuscript. 1217 tests passing, 96.09% coverage on src/synthobs. Source: https://github.com/docxology/SynthOBS/releases/tag/v1.618.0. This version replaces the PDF with one that carries its own DOI on the cover/citation page (the v1 PDF referenced the DOI only externally).", "keywords": [ "OBS Studio", "libobs", "reproducible research software", "space-weather telemetry", "real-time digital signal processing", "software provenance", "software citation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/SynthOBS/releases/tag/v1.618.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/SynthOBS/tree/v1.618.0", "relation": "isIdenticalTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "be957e7a-17cc-49ae-bcdb-120ec90310dd", "key": "SynthOBS_v1.618.0_html.zip", "size": 142937, "checksum": "md5:8fef27113d295e0e1fb88c528b0cd556", "links": { "self": "https://zenodo.org/api/records/21418901/files/SynthOBS_v1.618.0_html.zip/content" } }, { "id": "bc72298a-3098-401a-b60e-6384ae542b57", "key": "synthobs-1.618.0-py3-none-any.whl", "size": 47827, "checksum": "md5:4379c796de6916281bb57670a5463b23", "links": { "self": "https://zenodo.org/api/records/21418901/files/synthobs-1.618.0-py3-none-any.whl/content" } }, { "id": "ee0e78c8-6af3-4b8a-aec4-a8618d222c60", "key": "synthobs-1.618.0.tar.gz", "size": 85421, "checksum": "md5:812bb3aa2798b5b78fd016116a8ede85", "links": { "self": "https://zenodo.org/api/records/21418901/files/synthobs-1.618.0.tar.gz/content" } }, { "id": "9e23b254-5895-49fa-a212-c9c8390f1e5c", "key": "SynthOBS_v1.618.0.pdf", "size": 2985331, "checksum": "md5:5eb4644f0d68a0936a3b63b5d9b9fa32", "links": { "self": "https://zenodo.org/api/records/21418901/files/SynthOBS_v1.618.0.pdf/content" } } ], "html_url": "https://zenodo.org/records/21418901", "doi_url": "https://doi.org/10.5281/zenodo.21418687", "record_url": "https://zenodo.org/records/21418687" }, { "record_id": "21388457", "doi": "10.5281/zenodo.21388456", "title": "Fourfold Vision: William Blake, Buckminster Fuller, and the Geometry of Omnirational Seeing", "publication_date": "2026-07-15", "version": "0.3.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Published by Synergetics University on 14 July 2026, The Fuller Conjecture asks whether \"there exists a line of reasoning that presents Fuller's synergetic vision as a philosophical system.\" This paper tests one qualified route through that problem. It places William Blake's fourfold vision beside Buckminster Fuller's Synergetics without claiming shared vocabulary, historical influence, or Blakean anticipation of Quadray: Blake supplies a historically situated problem of plural seeing, while Quadray and tetrahedral geometry supply a reproducible model of relational aspects, partial views, and reconstruction. The formal result is exact: for any non-degenerate convex tetrahedron observed by a strictly exterior camera, one frame exposes 1, 2, or 3 faces, never 4; an atlas can preserve all 4 across successive views. The project combines an argument graph, exact rational geometry, deterministic visualizations, a rights-aware corpus ledger, and a dependency-free viewer. \"Synchronous omni-rational form\" names this operational integration—a relational whole retained across partial views, sequences, source boundaries, and explicit limits—not a historical Blakean or Fullerian doctrine.", "keywords": [], "related_identifiers": [ { "identifier": "https://github.com/docxology/blake_fourfold_synergetics", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "4804b4a8-3e06-4a7d-8b98-3630535a2d7e", "key": "blake_fourfold_synergetics_combined.pdf", "size": 5376000, "checksum": "md5:07fc314b4a652349b74332f4fee010b9", "links": { "self": "https://zenodo.org/api/records/21388457/files/blake_fourfold_synergetics_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/21388457", "doi_url": "https://doi.org/10.5281/zenodo.21388456", "record_url": "https://zenodo.org/records/21388456" }, { "record_id": "21330637", "doi": "10.5281/zenodo.21330636", "title": "Active FractalRabbit: A Synthetic Benchmark for Belief Filtering Under Sparse Waypoint Observations", "publication_date": "2026-07-13", "version": "0.2.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "Sparse waypoint analysis is privacy-sensitive: it must separate movement from irregular reporting, missingness, spatial coarsening, and corruption while preserving uncertainty about hidden location. Active FractalRabbit provides a controlled, artifact-bound benchmark whose headline lane uses a deterministic project-local synthetic FractalRabbit-format fixture; a separately retained lane exercises pinned open-source software from the National Security Agency as an independent simulator surface. The benchmark converts sporadic reports into categorical evidence, fits explicit hidden-state generative models, and compares transparent temporal, Markov, sequence, state-space, neural, latent-state, and active inference predictors under matched information sets. Under noisy partial-observability, Active Inference is the lowest-loss implemented predictor: it clearly leads point-estimate and raw-observation families and sits in a statistical tie with the strongest non-AIF belief-preserving comparator. The shared mechanism is soft Bayesian marginalization, which preserves probability across plausible cells instead of committing early to one state. Point estimates suffice for clean observations, an online base-rate predictor leads under regime switching, transparent temporal and disclosed kinematic controls anchor sparse reporting gaps, and withholding location sharply limits specific-cell recovery from metadata. The partially observable Markov decision process (POMDP) formulation also exposes variational and expected-free-energy diagnostics for belief, minimization, and integrity. These results establish a regime-specific synthetic model map and a reproducible evidence chain. The present contract covers synthetic software behavior; separate evidence protocols govern privacy and empirical evaluation. Code, fixtures, manuscript source, and the release manifest are public at github.com/ActiveInferenceInstitute/active_fractal_rabbit (https://github.com/ActiveInferenceInstitute/active_fractal_rabbit).\n\n---\nAssociated artifacts\nGitHub release: v0.2.0 (https://github.com/ActiveInferenceInstitute/active_fractal_rabbit/releases/tag/v0.2.0)\nDOI: https://doi.org/10.5281/zenodo.21330636\nZenodo: https://zenodo.org/records/21330636\nPDF SHA-256: d676159d149a12a1e990457329ad4cf52d2d8ab4ffcf09f55b42bad8e0c3c052", "keywords": [], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/active_fractal_rabbit/releases/tag/v0.2.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/ActiveInferenceInstitute/active_fractal_rabbit", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "ff37870f-731b-4bd9-b237-5cf531914b92", "key": "Friedman_2026_Active_d676159d.pdf", "size": 14942798, "checksum": "md5:565f1c58f11c2136ef27f0ae7a136558", "links": { "self": "https://zenodo.org/api/records/21330637/files/Friedman_2026_Active_d676159d.pdf/content" } } ], "html_url": "https://zenodo.org/records/21330637", "doi_url": "https://doi.org/10.5281/zenodo.21330636", "record_url": "https://zenodo.org/records/21330636" }, { "record_id": "21316511", "doi": "10.5281/zenodo.21316510", "title": "Prior Cognitive Art", "publication_date": "2026", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A prior is not explained by stacking more priors; it is located by mechanism, function, history, and fixed-point organization. The paper's precise thesis is procedural: before asking why\na prior exists, identify which explanatory kind is being requested and name the\nrule that will terminate the explanation. This working paper argues that Tinbergen's four questions\nare not stacked levels in one causal chain. They are crossed axes: proximate\nversus ultimate, and static versus developmental. Mechanism and function ask\nwhat a prior is doing now; ontogeny and phylogeny ask how such organization came\nto be across different timescales.\n\nThe paper treats the familiar \"prior on a prior\" problem in hierarchical Bayes\nas structurally parallel to an ontogenetic account that says one prior selects\nanother. Both postpone the question unless they terminate. Three termination\nfamilies organize the paper: pragmatic closure, selection closure, and\nfixed-point termination. They are organizing families, not an exhaustive\ntaxonomy of every possible explanation. A final upstream pass asks what comes\nbefore the first prior and answers with a constraint stack -- viability,\nallostasis, co-homeostasis, development, and niche support -- rather than with a\nhidden meta-prior. The project uses plain text, deterministic conceptual visualizations, and one deterministic illustrative simulation trace.\nIts supplement adds generated, auto-numbered formal claims and a closed symbol\nglossary as text-integrity artifacts rather than empirical machinery.\nThe paper includes one deterministic illustrative simulation trace over authored formal states; it does not run stochastic simulations, synthetic-data experiments, empirical estimates, or performance benchmarks.\n\nThe \"art\" in the title names the craft at stake: arranging explanatory kinds\n(proximate/ultimate, static/developmental, selection/fixed-point) so that no\nsingle kind is mistaken for the whole, and rendering that arrangement as\ndeterministic figures and checkable formalism rather than as empirical simulation evidence. It\nalso marks a bounded link to aesthetic practice: artworks can stage encounters\nwith expectations, material affordances, ambiguity, and meaning, but this paper\ntreats that link as a conceptual analogy, not as an empirical theory of art.\n\n---\nAssociated artifacts\nGitHub release: Prior Cognitive Art v0.1.0 (https://github.com/docxology/prior_cognitive_art/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.21316510\nZenodo: https://zenodo.org/records/21316510\nPDF SHA-256: 62aa1d8d4af75f4b5bdc894516720bdf61ae68a4be27f44aefc09c2dd2fbba67", "keywords": [ "priors", "Tinbergen's four questions", "hierarchical Bayes", "free energy principle", "Markov blankets", "cognitive science", "conceptual visualization" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/prior_cognitive_art/releases/tag/v0.1.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/prior_cognitive_art", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "726f7161-3d79-4c3c-bd8c-657318a0dad6", "key": "Friedman_2026_Prior_62aa1d8d.pdf", "size": 4429780, "checksum": "md5:e792cca2876e25c849c62d8c4d0638ec", "links": { "self": "https://zenodo.org/api/records/21316511/files/Friedman_2026_Prior_62aa1d8d.pdf/content" } } ], "html_url": "https://zenodo.org/records/21316511", "doi_url": "https://doi.org/10.5281/zenodo.21316510", "record_url": "https://zenodo.org/records/21316510" }, { "record_id": "21298895", "doi": "10.5281/zenodo.21298894", "title": "Reproducible Literature Synthesis with infrastructure/search and infrastructure/reference", "publication_date": "2026", "version": "0.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper documents template_search_project, the literature-search exemplar shipped with the Research Project Template (https://github.com/docxology/template). The project demonstrates two configurable, reproducible pipelines sharing the same configuration file and the same infrastructure/search/ + infrastructure/reference/ modules. The standard pipeline (scripts/run_search_pipeline.py) handles a single SearchQuery end-to-end. The deep-search pipeline (scripts/run_deep_search.py, see ) fans out across a list of keywords (each capped at 100 papers per keyword from deep_search.max_results_per_keyword in manuscript/config.yaml), fully enriches every paper with its abstract and PDF fulltext, and (optionally) uses the local LLM to write a multi-section reading note for every paper. When a deep-search aggregate exists, the latest run covered 3 keyword(s) with unique paper(s) after cross-keyword deduplication. Both turn a free-text topic into:\n\n1. a deduplicated, year-filtered set of papers drawn from arXiv, Crossref, optional local corpora, and (opt-in) Paperclip (https://paperclip.gxl.ai/);\n2. a Pandoc-compatible references.bib byte-identical in style to the canonical exemplar in template_code_project (../../template_code_project/manuscript/references.bib) (file manuscript/references.bib);\n3. cached abstracts and (optionally) extracted PDF full text, written to disk under stable per-paper identifiers; and\n4. an LLM-synthesised reading report assembled from per-paper analyses and a cross-corpus thematic synthesis, all produced by a local Ollama model with pinned seed and temperature.\n\nAll discovery logic lives in infrastructure/search/literature/ (source on GitHub (https://github.com/docxology/template/tree/main/infrastructure/search/literature)); all export logic lives in infrastructure/reference/citation/ (source on GitHub (https://github.com/docxology/template/tree/main/infrastructure/reference/citation)); LLM synthesis reuses the existing infrastructure/llm/ (source on GitHub (https://github.com/docxology/template/tree/main/infrastructure/llm)) bridge. The project itself contains only thin orchestration, manuscript prose, and a test suite — perfectly mirroring the two-layer architecture the template enforces.\n\nThe motivating concern is reproducibility: a query at time $t_0$ should produce the same results at time $t_1$ unless the cache is explicitly invalidated. This is achieved by deterministic search caching keyed on canonical query identity, on-disk caching of every fetched abstract / PDF, and pinned LLM seeds. The same manuscript/config.yaml that drives the pipeline is also the only configuration any reviewer needs.\n\nRun snapshot. With the bundled manuscript/config.yaml, the most recent pipeline execution evaluated the query \"reproducible research optimization\" against local, returned 6 deduplicated paper(s) (4 carrying a DOI, 6 carrying an abstract), and recorded backend errors: none. Resolve `{{…}} tokens by running scripts/z_generate_manuscript_variables.py after run_search_pipeline.py; the script writes output/data/manuscript_variables.json and resolved markdown under output/manuscript/`, which the PDF-rendering stage prefers when present.\n\nKeywords: literature search, BibTeX automation, reproducible research, local LLM synthesis, scientific infrastructure", "keywords": [ "literature search", "automated reference management", "BibTeX", "reproducible research", "local LLM synthesis" ], "related_identifiers": [], "files": [ { "id": "46847325-a40f-481b-8c30-150bab75769f", "key": "Friedman_2026_Reproducible_003aed0d.pdf", "size": 843313, "checksum": "md5:2164816cb48414072020a2eb240dabd9", "links": { "self": "https://zenodo.org/api/records/21298895/files/Friedman_2026_Reproducible_003aed0d.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298895", "doi_url": "https://doi.org/10.5281/zenodo.21298894", "record_url": "https://zenodo.org/records/21298894" }, { "record_id": "21298893", "doi": "10.5281/zenodo.21298892", "title": "Registered Report Template: Preregistration, Deviations, and Claim Boundaries", "publication_date": "2026-07-10", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This document is a template, not an empirical study. It demonstrates the\nregistered-report workflow end to end: locking a preregistration, validating\nits completeness, executing the registered analysis plan against deterministic\ndemonstration data, and reporting confirmatory and exploratory claims through\nan explicit deviation ledger. Every quantity reported here is produced by the\ntested code in src/registered_report/ and regenerated by\nscripts/generate_figures.py; none is hand-entered or illustrative.\n\nThe demonstration binds a single confirmatory hypothesis (H1) to one registered\noutcome (primary_score) analysed by a two-sided label-permutation test. Run\non a seeded two-group dataset (seed = 20260709, n = 24 per group), the\nregistered test yields an observed mean difference of 1.003 with a two-sided\npermutation p-value of 0.0005 (0 of 2000 shuffles at least as extreme),\nsignificant at the preregistered alpha = 0.05. A deliberately introduced\nsecondary endpoint and an alternative model are carried only as documented\ndeviations, keeping the confirmatory claim boundary intact. The purpose is to\ngive forks a working, auditable skeleton in which planned analyses, frozen\nhypotheses, deviations, and post-run claims are separable and machine-checkable.", "keywords": [ "registered report", "preregistration", "replication", "deviation ledger" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template/tree/main/projects/templates/template_registered_report", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "a5206135-9a5b-440b-b70d-05f71150779b", "key": "Friedman_2026_Registered_61a9addb.pdf", "size": 289933, "checksum": "md5:091158dda479781947fabe1b853f5719", "links": { "self": "https://zenodo.org/api/records/21298893/files/Friedman_2026_Registered_61a9addb.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298893", "doi_url": "https://doi.org/10.5281/zenodo.21298892", "record_url": "https://zenodo.org/records/21298892" }, { "record_id": "21298891", "doi": "10.5281/zenodo.21298890", "title": "Redacted Report Template: Disclosure Control and Release Audit", "publication_date": "2026-07-10", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This exemplar demonstrates a complete disclosure-control pipeline for sanitized public release reports. The methodology combines classification-ceiling enforcement, source-protection validation, mosaic-risk scoring, and TPM-backed sealed sidecars across a sixteen-variant visual proof matrix. Four redaction styles—blackout, whiteout, grayout, and blur—are rendered across four PDF backgrounds—white, gray, black, and blur—yielding sixteen base proof PDFs. Each receives nine steganographic security methods including SHA-256/SHA-512 hash manifests, diagonal watermark overlays, footer provenance stamps, invisible text, QR and Code128 barcodes, PDF Info and XMP metadata, and embedded manifest attachments. Optional Kmyth TPM sealing wraps each hash manifest and steganography PDF in a .ski sidecar sealed against the TPM2-TSS storage hierarchy, bound to PCR selections and policy or-values. The release gate requires three reviewer roles—originator, classification reviewer, and release authority—each providing a non-empty rationale. A source-safe redaction ledger records SHA-256 hashes of each redacted span without exposing source text, and a segment hash manifest compares source and public SHA-256 digests for reproducible audit. The comprehensive release packet combines sanitized text, audit findings, ledger, hashes, review gate status, and paragraph-level audit tables into a single JSON-ready export. This exemplar confirms that visual presentation choices remain orthogonal to the release gate: the same source-safe decisions drive every output variant.", "keywords": [ "redaction", "disclosure control", "release audit", "source protection" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template/tree/main/projects/templates/template_redacted_report", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "024f7cff-2057-4687-8764-7d5eda918e8f", "key": "Friedman_2026_Redacted_103642b6.pdf", "size": 58890, "checksum": "md5:69ae13d34331099e203575288d7bf626", "links": { "self": "https://zenodo.org/api/records/21298891/files/Friedman_2026_Redacted_103642b6.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298891", "doi_url": "https://doi.org/10.5281/zenodo.21298890", "record_url": "https://zenodo.org/records/21298890" }, { "record_id": "21298889", "doi": "10.5281/zenodo.21298888", "title": "Pools, Rules, and Tools: A Template-Integrated Resource Architecture", "publication_date": "2026-07-05", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Research software repositories in monorepo configurations accumulate three categories of shared resources that individual projects must consume without re-implementing discovery logic: data pools (bibliographies, contacts, datasets), governance rules (style guides, coverage thresholds, citation schemas), and executable tools (code executors, validators, skill invocations). Without a canonical integration pattern, projects either duplicate discovery logic or silently ignore resources that fail to load — both outcomes degrade reproducibility and collaborative cohesion .\n\nThis paper presents template_pools_rules_tools, a meta-project exemplar that demonstrates how a single project can programmatically discover, validate, and exercise all three resource categories with zero tight coupling to any specific resource instance. The exemplar comprises eight Python modules — three resource readers (fonds_reader, rules_applier, tools_invoker), an orchestrator (integration), a semantic rule evaluator (strong_rule_evaluator), a figure generator (figures), a manuscript-token generator (manuscript_variables), and shared type definitions (type_defs) — plus six thin orchestration scripts and a fully token-injected manuscript pipeline.\n\nThe architecture (@fig:architecture) separates resource ownership from resource consumption. Resources live in top-level fonds/, rules/, and tools/ directories and are never modified by consumers. Each resource exposes a typed manifest (fonds.yaml, rules.yaml, tools.yaml) that the corresponding reader module uses for discovery and validation. All readers implement graceful fallbacks: they return None or empty collections when a resource is absent, log a warning via the standard library logging module, and allow the integration pipeline to continue. This revision extends the original three-figure presentation to eight content figures plus a cover illustration — a fond taxonomy (@fig:taxonomy), a rule hierarchy (@fig:rulehier), a tool invocation contract (@fig:toolcontract), a three-level resilience diagram (@fig:resilience), and a script pipeline flow (@fig:pipelineflow) — so that every structural claim in the prose has a corresponding visual.\n\nIn a representative pipeline run, the integration demo loaded 3 fonds, validated 2 rule sets, discovered 3 tools, and processed 8 bibliography entries — all reported as structured JSON that populates manuscript variable tokens at render time. Tests covering the eight src/ modules (across nine test files) achieve well above the required ≥90% combined line coverage and use real file paths rather than mocks, ensuring that reported counts are genuine — run uv run pytest … --cov-report=term for the current test count and coverage percentage rather than trusting a number printed here.\n\nThe template_pools_rules_tools exemplar provides a reference implementation that any project in the template repository can consult when designing its own resource-consumption layer.\n\nThis reference implementation is deliberately reproducible end-to-end: every count, figure, and page-layout choice in this document is regenerated from source rather than hand-authored, per the Reproducibility Checklist in the front matter.\n\nKeywords: research software engineering, monorepo architecture, reproducibility, fonds, governance rules, tool discovery, graceful degradation\n\n---\nAssociated artifacts\nGitHub repository: https://github.com/docxology/template_pools_rules_tools\nDOI: https://doi.org/10.5281/zenodo.21298888\nZenodo: https://zenodo.org/records/21298888\nPDF SHA-256: 6908c1a01fbcff12c33a409d16f438b4cd4583ab383780b7b95dda121c8dcd66", "keywords": [], "related_identifiers": [], "files": [ { "id": "4f0d7f59-e80a-464c-b489-6103bd4c183a", "key": "Friedman_2026_Pools_6908c1a0.pdf", "size": 1269068, "checksum": "md5:a6e7922ee12ed050c93eb8bf60d6e9fe", "links": { "self": "https://zenodo.org/api/records/21298889/files/Friedman_2026_Pools_6908c1a0.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298889", "doi_url": "https://doi.org/10.5281/zenodo.21298888", "record_url": "https://zenodo.org/records/21298888" }, { "record_id": "21298886", "doi": "10.5281/zenodo.21298885", "title": "Illegal States, Mostly Unrepresentable", "publication_date": "2026", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents a strongly-typed, decentralized multiagent simulation —\nan ant-robot colony — as the computational exemplar of the Research\nProject Template (https://github.com/docxology/template). Each colony\nmember is an Agent that owns exactly one real, on-disk SQLite database\nand one in-process, fault-injectable protocol endpoint; no agent ever\ntouches another agent's storage or network state. The implementation lives\nunder projects/templates/template_formal/src/template_formal/; the demo\npipeline is orchestrated by scripts/02_run_analysis.py.\n\nThe paper's central claim is methodological, not a typing-features\nshowcase: static typing's honest value in Python is edit-time/CI-time error\nprevention on structurally representable invariants, and nothing more.\nNominal identifiers (AgentId, MessageId, TxnId as distinct NewType\nwrappers), a tagged-union Result[T, E] ADT with match-exhaustiveness,\nand a session-typed protocol state machine (IdleSession →\nHandshakingSession → EstablishedSession → ClosedSession) each make an\nillegal program a type error, verified by a real mypy --strict\nsubprocess run against six known-bad negative-control fixtures plus three\nknown-good positive-control fixtures (tests/mypy_fixtures/). Where the type system cannot help — reusing a\nconsumed transaction handle, reusing a consumed protocol-phase instance,\nor receiving malformed bytes off an untyped network boundary — the\nimplementation runtime-guards instead, and the manuscript says so\nexplicitly rather than eliding the distinction.\n\nWe also frame, without over-claiming, two additional lenses: the per-agent\nstorage schema as a functor $\\mathrm{Schema} \\to \\mathbf{Set}$ in the sense\nof @fong2018seven, and each agent's per-tick decision as an approximate\nminimizer of a closed-form expected-free-energy quantity in the spirit of\n@friston2005theory, bridged to collective organization via the Memory\nEvolutive Systems framework of . Both framings are\ndeclared as design lenses, not machine-checked mathematical results — the\npaper is explicit about which of its claims are proofs and which are\nanalogies.\n\nContributions are architectural, epistemic, and empirical.\nArchitecturally: a zero-mock test suite (tests/) covering ADT\nexhaustiveness, affine-handle reuse, session-type phase transitions,\nseeded fault injection over a real in-process bus, and a three-agent\ncolony integration test exhibiting a real stigmergic positive-feedback\nmechanism (deliberately not overclaimed as \"emergence\" — see\n@sec:results-discussion). Epistemically: an explicit \"What mypy --strict\nproves vs. what is a runtime discipline\" section (@sec:honesty-line) that\npins every strong claim to the ISC (Ideal-State Criterion) number of its\npaired negative-control test, so the claim-to-evidence mapping is\nauditable rather than asserted. Empirically: eight pre-registered analyses\ngrouped across three experiment families,\nfalsifiable experiments (@sec:results-discussion) — a decay-rate sweep\nrevealing a real, non-monotonic threshold effect (near-zero convergence\nbelow decay $\\approx 0.35$, a $100\\%$ plateau at moderate decay, and a\nmeasurable decline at total evaporation); a random-choice null-model\ncomparison showing the real mechanism's Wilson-bounded convergence rate\n($93.3\\%$) does not overlap a chance baseline's ($0.67\\%$); and a\nheterogeneity-magnitude sweep showing convergence rate decreases strictly\nmonotonically as agent preferences spread wider — each stated with its\nfalsification criterion before its real, seeded result, using genuinely\nnew stdlib-only infrastructure (colony/nullmodel.py, colony/sweep.py)\nrather than one-off scripts.\n\nKeywords: strongly typed programming, session types, algebraic data\ntypes, category theory, Active Inference, multiagent systems, affine types,\nillegal state unrepresentable.", "keywords": [ "strongly typed programming", "session types", "algebraic data types", "category theory", "active inference", "multiagent systems", "affine types", "illegal state unrepresentable" ], "related_identifiers": [], "files": [ { "id": "72fff72e-a615-4f05-a022-823a0ed51280", "key": "Friedman_2026_Illegal_5bda439c.pdf", "size": 551781, "checksum": "md5:29e517fec501e662ce2d474116ef8a51", "links": { "self": "https://zenodo.org/api/records/21298886/files/Friedman_2026_Illegal_5bda439c.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298886", "doi_url": "https://doi.org/10.5281/zenodo.21298885", "record_url": "https://zenodo.org/records/21298885" }, { "record_id": "21298884", "doi": "10.5281/zenodo.21298883", "title": "Data Descriptor Template: Schema, Provenance, and Release Readiness", "publication_date": "2026-07-09", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This exemplar demonstrates a data descriptor workflow in which the schema,\nfile inventory, provenance chain, license boundary, and validation gate are\ntreated as first-class research artifacts rather than afterthoughts. It ships a\nsmall, public, synthetic demonstration dataset (two CSV files under\ndata/fixtures/) and a machine-readable descriptor\n(data/example_descriptor.json) that declares each file's media type, sha256\nchecksum, and row count alongside a six-field data dictionary with typed\nconstraints. A tested validation library (src/data_descriptor/) checks the\ndescriptor's shape, safety, and completeness; recomputes each declared checksum\nand row count against the bytes on disk; and emits a deterministic,\nmetadata-only release manifest suitable for pre-publication review. Every figure\nand quantitative claim in this manuscript is produced by that library and\nregenerated on demand, so the prose describes structure and provenance rather\nthan transcribing values that would drift. This is a template with a\ndemonstration dataset: it makes no scientific claim about the data, only about\nhow to describe and release a dataset responsibly.", "keywords": [ "data descriptor", "FAIR data", "provenance", "schema validation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template/tree/main/projects/templates/template_data_descriptor", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "adb0534e-56db-43cd-adc2-53227e295d1d", "key": "Friedman_2026_Data_a542f49d.pdf", "size": 194590, "checksum": "md5:b63b64be4ac2938427f5cac83e53aea8", "links": { "self": "https://zenodo.org/api/records/21298884/files/Friedman_2026_Data_a542f49d.pdf/content" } } ], "html_url": "https://zenodo.org/records/21298884", "doi_url": "https://doi.org/10.5281/zenodo.21298883", "record_url": "https://zenodo.org/records/21298883" }, { "record_id": "21281510", "doi": "10.5281/zenodo.21281509", "title": "template_pitch_deck: Reproducible, Validated Pitch-Deck Generation", "publication_date": "2026-07-08", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Research groups routinely need to pitch their work — to funders, partners, or\ncollaborators — yet pitch decks are almost never treated as reproducible\nresearch artifacts: they are hand-assembled in proprietary slide tools,\ncontain unverifiable claims, and cannot be regenerated when the underlying\nfacts change. template_pitch_deck closes that gap. It generates six\nartifacts from one token-resolved content source — short, medium, and long\ndecks, each in both PDF and PPTX — with every numeric claim traced back to a\nlive introspection of the repository it describes, every {{TOKEN}}\nsubstitution verified to have actually landed, and every sentence checked\nagainst a denylist of pitch-deck clichés.\n\nThe flagship content pitches template_template (../../template_template/), this\nmonorepo's own autopoietic meta-project, to a meta-science and\nscience-integrity audience — the kind of pitch an organization like the\nActive Inference Institute or COGSEC would actually hand to a funder. The\nrendering engine itself is new, reusable infrastructure:\ninfrastructure/rendering/slide_deck.py (ReportLab, PDF) and\ninfrastructure/rendering/pptx_deck.py (python-pptx) both consume the same\nDeckContent model, so a PDF and a PPTX built from identical content carry\nidentical slide counts and identical text — verified by direct read-back of\nboth file formats, not by inspection.\n\nKeywords: pitch deck, slide generation, reproducible research\ncommunication, meta-science infrastructure, token validation, PPTX, PDF\nrendering.\n\n---\nAssociated artifacts\nGitHub release: v1.0.0 (https://github.com/docxology/template-pitch-deck/releases/tag/v1.0.0)\nDOI: https://doi.org/10.5281/zenodo.21281509\nZenodo: https://zenodo.org/records/21281509\nPDF SHA-256: 66941950e2307d1e9717c0045f3db3196d7d2542c3f5ffceced00438f653c55b", "keywords": [ "pitch deck", "slide generation", "reproducible research communication", "meta-science infrastructure", "science integrity", "token validation", "PPTX", "PDF rendering" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template-pitch-deck/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "7cd41f30-c42a-4866-82a4-4f233c90b7a4", "key": "template_template_pitch_short.pdf", "size": 101688, "checksum": "md5:79e8f9a3cd6cfe3751ada01242995333", "links": { "self": "https://zenodo.org/api/records/21281510/files/template_template_pitch_short.pdf/content" } }, { "id": "35b99e77-13bc-4219-a3ff-bb0183615b3f", "key": "template_template_pitch_long.pdf", "size": 601690, "checksum": "md5:29407ecf3f02a156c84f92422faf2919", "links": { "self": "https://zenodo.org/api/records/21281510/files/template_template_pitch_long.pdf/content" } }, { "id": "3585c87f-b8d6-4949-bfeb-b083d94c22af", "key": "template_template_pitch_medium.pdf", "size": 512951, "checksum": "md5:04e5ee614103c909625f20ba09ee804d", "links": { "self": "https://zenodo.org/api/records/21281510/files/template_template_pitch_medium.pdf/content" } }, { "id": "3f032f22-229d-40fd-8172-444a195d5648", "key": "Friedman_2026_Templatepitchdeck_66941950.pdf", "size": 60923, "checksum": "md5:6f13bc9c5db52443328ff40b1b2f4ee9", "links": { "self": "https://zenodo.org/api/records/21281510/files/Friedman_2026_Templatepitchdeck_66941950.pdf/content" } } ], "html_url": "https://zenodo.org/records/21281510", "doi_url": "https://doi.org/10.5281/zenodo.21281509", "record_url": "https://zenodo.org/records/21281509" }, { "record_id": "21229620", "doi": "10.5281/zenodo.21227869", "title": "Autopoietic Project Generation", "publication_date": "2026-07-06", "version": "1.0.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "template_autopoiesis is a combinatoric grammar that deterministically generates\nwhole runnable projects — not files or snippets, but complete, independently\ntestable child repositories with their own kernel source, tests, analysis\nentry point, and manuscript. A single integer seed plus a grammar of orthogonal\nslots (primitive domain, analytical track, section set, and three\npresentation/provenance slots) selects one child from a combinatoric product\nspace of 360 nominal (45 content-distinct)\nconfigurations, via a SHA-256 digest of the seed and slot identity — with no\nrandom-number generator anywhere in the expansion path.\n\nProject generators routinely claim completeness, determinism, and\ntraceability without making any of the three independently checkable. This\nexemplar treats each claim as a structural property to verify rather than a\nrhetorical one to assert: verify_child() recomputes a tree hash from the\nfiles actually on disk and compares it against the recorded provenance,\nrather than trusting a value the same run wrote down; a honesty manifest\ninspects the live source AST to confirm every claim in this manuscript\nresolves to a real function in a real file; and a per-domain mutation gate\nchecks that the acceptance tests reject a constant-success stub before\ntrusting that they accept the real kernel. The same discipline governs this\ndocument itself — every number below is substituted at render time from a\nlive measurement rather than hand-typed as a literal.\n\nAcross 5 heterogeneous primitive domains\n(- optimization\n- dynamics\n- statistics\n- signal\n- graph), 493 tests exercise both fixed ground-truth\nchecks and Hypothesis-driven property invariants at 96.28% branch\ncoverage, with an explicit negative control per domain distinguishing the\nreal kernel from a deliberately-wrong one.\n\nGeneration pipeline\n\nGrammar product space\n\n- Domain count: 5\n- Effective product size: 45\n- Total product size: 360\n- Reserved slots: 3 (figure_profile, qr_profile, integrity_profile)\n- Grammar hash: f84a8f9dbcb18e37\n- Tests: 493 · Coverage: 96.28%\n\n---\nAssociated artifacts\nGitHub release: Autopoietic Project Generation (v1.0.1) — improved abstract (https://github.com/docxology/template/releases/tag/v1.0.1)\nDOI: https://doi.org/10.5281/zenodo.21227869\nZenodo: https://zenodo.org/records/21227869\nPDF SHA-256: 84145371f10c7ee97a75c53d78917d247fd6bd987d2c1764ee437b6fbdef8f51", "keywords": [ "autopoiesis", "combinatoric grammar", "deterministic generation", "project synthesis", "reproducible research", "infrastructure automation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template/releases/tag/v1.0.1", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "4a86ccab-052c-4741-840b-98209f3c4cb5", "key": "Friedman_2026_Autopoietic_84145371.pdf", "size": 497314, "checksum": "md5:3e56c92b4529131a33cc642ce3ef949a", "links": { "self": "https://zenodo.org/api/records/21229620/files/Friedman_2026_Autopoietic_84145371.pdf/content" } } ], "html_url": "https://zenodo.org/records/21229620", "doi_url": "https://doi.org/10.5281/zenodo.21227869", "record_url": "https://zenodo.org/records/21227869" }, { "record_id": "21176001", "doi": "10.5281/zenodo.21176000", "title": "The Shape Between: A Full-Page Illustrated Storybook Template", "publication_date": "2026", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "template_storybook demonstrates a public, standalone picture-book workflow in\nthe research template repository. The bundled project renders a deterministic\nfourteen-page storybook subtitled A geometric fable of belonging, bracing, and\nreciprocal form: a clear cover, a publication-and-acknowledgements page, and\ntwelve story pages in which a child tetrahedron raised by cubes meets a child\ncube raised by tetrahedra. The story uses a large reciprocal symbol, a\ntetrahedron-inside-cube stability spread, a shadow-projection lesson, a\ntensegrity lantern, and a vector garden to frame belonging without sameness:\nsquare and triangle families remain distinct while the space between them\nbecomes navigable.\n\nThe project separates story data, rendering logic, and orchestration. Story\ntext, characters, page order, palettes, and overlay choices live in\ncontent/story.yaml; character generation and illustration live in\nsrc/storybook/; one script renders the cover, each page script renders a\nnumbered page, and a final script assembles the PDF. This makes the exemplar a\nforkable pattern for full-page creative artifacts rather than standard\nmanuscript-centered figure generation.\n\n---\nAssociated artifacts\nGitHub release: The Shape Between v0.1.0 (https://github.com/docxology/template_storybook/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.21176001\nZenodo: https://zenodo.org/records/21176001\nPDF SHA-256: 7fb0ed775db212cd9f4b5b578bef8900c9f925bc0c5cc047331eb6900679eeda", "keywords": [ "storybook", "illustration", "procedural graphics", "reportlab", "reproducible publishing" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_storybook/releases/tag/v0.1.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/template_storybook", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "c8a1c247-b14e-4692-afc2-39913d49d237", "key": "the-shape-between.pdf", "size": 1492876, "checksum": "md5:29798899f24dbd08b6397f62431ab149", "links": { "self": "https://zenodo.org/api/records/21176001/files/the-shape-between.pdf/content" } }, { "id": "d17e431e-518d-4fb4-b4e9-93a965c0565f", "key": "Friedman_2026_Shape_7fb0ed77.pdf", "size": 45341, "checksum": "md5:1a4f6d05ebc0d1faaf6bbdd6ec1c1ae1", "links": { "self": "https://zenodo.org/api/records/21176001/files/Friedman_2026_Shape_7fb0ed77.pdf/content" } }, { "id": "7469bd7b-ab00-4b53-aa0e-5fbb19243765", "key": ".zenodo.json", "size": 711, "checksum": "md5:3134c8161a3d88ae8af2cae62d80e991", "links": { "self": "https://zenodo.org/api/records/21176001/files/.zenodo.json/content" } }, { "id": "336262f1-754d-451e-ba00-ab2174d5e43f", "key": "storybook_manifest.json", "size": 5466, "checksum": "md5:86ecf6c9a5bae4046125386a7dd3e095", "links": { "self": "https://zenodo.org/api/records/21176001/files/storybook_manifest.json/content" } }, { "id": "dd7abed5-dd7e-4c5a-b5b7-d8520b57ade8", "key": "validation_report.json", "size": 4633, "checksum": "md5:13e338ef45a11779f91a5c648362575d", "links": { "self": "https://zenodo.org/api/records/21176001/files/validation_report.json/content" } }, { "id": "adebbb22-9469-431f-9205-458bc5e39817", "key": "storybook_summary.md", "size": 157, "checksum": "md5:0d7e409c754f47b75a6b1fa05dbb1b84", "links": { "self": "https://zenodo.org/api/records/21176001/files/storybook_summary.md/content" } }, { "id": "fd358409-ab66-4f21-8a12-9b52e9887b1b", "key": "CITATION.cff", "size": 576, "checksum": "md5:692f52c3c0f256b0bb4bed7a560f96d7", "links": { "self": "https://zenodo.org/api/records/21176001/files/CITATION.cff/content" } } ], "html_url": "https://zenodo.org/records/21176001", "doi_url": "https://doi.org/10.5281/zenodo.21176000", "record_url": "https://zenodo.org/records/21176000" }, { "record_id": "21137277", "doi": "10.5281/zenodo.21137276", "title": "Entomological Law: A Field Map of Insects as Evidence, Threat, Property, Product, Patient, and Weapon", "publication_date": "2026-07-02", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "There is no statute, treatise, or law-school casebook titled \"Entomological Law.\" The phrase names a synthetic field — the convergence zone where the six-legged world repeatedly forces the legal system to answer questions it was not designed for: Can a fly testify? Who owns a swarm? Is a bumblebee a fish? Can you patent a mosquito? May a court excommunicate a weevil? Does a cricket suffer? May insects be used in war? This reference compiles that field as a machine-readable and reproducible artifact organized around the legal role an insect occupies in a given dispute. It encodes 8 legal roles — witness, regulated threat, protected subject, property, invention, defendant, moral patient, and weapon — and binds to them 18 landmark decisions, 43 statutes and treaties across 9 categories and 10 jurisdictions, 24 insect taxa, 13 certifying and regulatory institutions, 44 historical milestones spanning 3676 years, and 5 cross-domain themes that knit the roles together. Every count in this prose is generated from the source registries under src/, legal propositions are source-bound in the bibliography, every externally-sourced statistic written as a numeral is bound to a verification record in the claim ledger, and every figure caption is emitted from a source-owned caption registry. The result is both a map of a genuinely transdisciplinary field and a reproducibility contract: the same version-controlled inputs regenerate the inventories, validation report, analytical figures, manuscript variables, and paper while preserving explicit caveats about registry scope, jurisdictional reach, and the boundary between what the offline gates prove and what only a live source check can confirm. --- Associated artifacts GitHub release: Entomological Law (v1.0.0) (https://github.com/docxology/EntoLaw/releases/tag/v1.0.0) DOI: https://doi.org/10.5281/zenodo.21137276 Zenodo: https://zenodo.org/records/21137276 PDF SHA-256: 5a1891704c285491c97297dea66e9a4ea019b2dabddcc28cb5aeb18d6a335225
", "keywords": [ "entomological law", "legal entomology", "forensic entomology", "endangered species", "invasive species", "insect welfare", "gene drive", "biological weapons convention", "reproducible legal scholarship" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/EntoLaw/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/EntoLaw", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "84a67f48-a6fd-41a7-a53d-cb8ed26f9743", "key": "Friedman_2026_Entomological_5a189170.pdf", "size": 1440326, "checksum": "md5:6ffee3eee9e77939ece3e617d62b1a59", "links": { "self": "https://zenodo.org/api/records/21137277/files/Friedman_2026_Entomological_5a189170.pdf/content" } } ], "html_url": "https://zenodo.org/records/21137277", "doi_url": "https://doi.org/10.5281/zenodo.21137276", "record_url": "https://zenodo.org/records/21137276" }, { "record_id": "21086549", "doi": "10.5281/zenodo.21086548", "title": "A Domain Language for Specifying Controlled Methods", "publication_date": "2026", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper describes a small, tested domain language for specifying\ncontrolled methods — the methods-paper exemplar of the\nResearch Project Template (https://github.com/docxology/template). Unlike a\nresults paper, this manuscript's subject is the methodology itself: a\ncontrolled vocabulary, a unit system with dimensional safety, four staged\nvalidation gates, and a deterministic compiler, implemented in\nprojects/templates/template_methods_paper/src/methods_dsl/ and described\nsection by section in . The domain language's vocabulary is\ninformed by BPL (Biology Programming Language,\n), an upstream reference that encodes laboratory protocols as\nprograms with biology-native types, staged validation, and deterministic\ncompilation; this exemplar generalizes BPL's intent vocabulary and pipeline\nshape from wet-lab protocols to any controlled procedure.\n\nA Method is a name, a set of typed parameters and resources, and an\nordered, dependent set of steps — constructed directly as frozen Python\ndataclasses (src/methods_dsl/model.py) rather than parsed from new text\nsyntax. Every Quantity carries a unit that resolves to one of\n18 controlled units across six dimensions, and every step\nnames one of 9 controlled-vocabulary intents\n(src/methods_dsl/vocabulary.py), executable on one of 3\nbackends. 4 staged gates — structural, semantic, plan, and\ntarget — validate a method before compile_method\n(src/methods_dsl/compiler.py) deterministically schedules it with Kahn's\nalgorithm and hashes the canonical plan with SHA-256.\n\nWe demonstrate the language on 2 worked example\nmethods spanning both domains BPL's design targets and the domains it\ngeneralizes to: a manual wet-lab preparation\n(PBSPreparation, 5 steps, target human,\nplan hash 313b9b17de98) and an automated instrument-calibration\nprocedure (SensorCalibrationSweep, 4 steps,\ntarget automated, plan hash d89cced19be6).\nLive re-compilation determinism check: Yes. Across both\nmethods, 8 of 8 staged-gate\nevaluations pass. A demonstration provenance hash-chain\n(src/methods_dsl/trust.py) of length 3 verifies as\nYes.\n\nContributions are methodological and architectural. On the methods\nside, we show that a controlled vocabulary expressed as typed dataclasses —\nnot a parsed grammar — is sufficient to reproduce BPL's core safety\nproperties (dimensional safety, staged validation, deterministic\ncompilation) at a scope appropriate for a template exemplar. On the\narchitecture side, the DSL is covered above the 90% project gate by a\nzero-mock test suite, generates 13 artifacts\n(1 figures, 6 data files,\n6 reports) per pipeline run, and injects reproducibility\nmetadata (configuration hash 23b5981d45bdc598, build timestamp\n2026-06-30T23:02:10Z) into .\n\nKeywords: methods paper, domain-specific language, controlled methods, deterministic compilation, staged validation, dimensional analysis\n\n---\nAssociated artifacts\nGitHub release: v1.0.0 (https://github.com/docxology/template_methods_paper/releases/tag/v1.0.0)\nDOI: https://doi.org/10.5281/zenodo.21086548\nZenodo: https://zenodo.org/records/21086548\nPDF SHA-256: ecd8519fc2a9a674bd8a4cf89f96122af76529c913e32bf880a7c842da08771a", "keywords": [ "methods paper", "domain-specific language", "controlled methods", "deterministic compilation", "staged validation", "dimensional analysis" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_methods_paper/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "b9de1f4e-48ba-4d2f-8baf-796ed0cff2d9", "key": "Friedman_2026_Domain_ecd8519f.pdf", "size": 144305, "checksum": "md5:54813a4dddcf9a3d09a6987a827fc3b3", "links": { "self": "https://zenodo.org/api/records/21086549/files/Friedman_2026_Domain_ecd8519f.pdf/content" } } ], "html_url": "https://zenodo.org/records/21086549", "doi_url": "https://doi.org/10.5281/zenodo.21086548", "record_url": "https://zenodo.org/records/21086548" }, { "record_id": "21086293", "doi": "10.5281/zenodo.21086292", "title": "Exploratory Data Analysis: A Reproducible Notebook Template", "publication_date": "2026", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Exploratory data analysis (EDA) is the most common entry point in applied\nresearch, yet it is also where reproducibility most often breaks down: logic\naccumulates in notebook cells that are never tested and quietly drift from the\nprose describing them. This paper presents the computational-notebook\nexemplar of the Research Project Template (https://github.com/docxology/template):\nan interactive walkthrough notebook\n(projects/templates/template_eda_notebook/notebooks/eda_walkthrough.ipynb)\nthat imports a small, fully-tested EDA library rather than carrying logic in its\ncells.\n\nWe ship a deterministic dataset (data/measurements.csv) with a designed\ncorrelation structure and a handful of missing values, then load, clean,\nsummarize, correlate, and visualize it entirely through tested functions in\nsrc/eda/. The library is side-effect-free — no plotting and no file I/O — and\nstandalone (numpy and pandas only), so it is covered above the 90% project gate\nand reused identically from the notebook, the thin analysis script\n(scripts/eda_analysis.py), and this manuscript.\n\nContributions are methodological and architectural. On the methods side,\nwe walk the canonical first EDA pass: surface missingness explicitly rather than\nimputing it, compute per-column descriptive statistics and per-group means, and\nrank features by Pearson correlation. On the architecture side, we demonstrate\nthe notebook-to-tested-source extraction workflow — explore fast in a cell, and\nthe moment a computation matters, move it into the library behind a failing\ntest — verified by a zero-mock suite and a structural notebook-binding check\n().\n\n---\nAssociated artifacts\nGitHub release: v1.0.0 (https://github.com/docxology/template_eda_notebook/releases/tag/v1.0.0)\nDOI: https://doi.org/10.5281/zenodo.21086292\nZenodo: https://zenodo.org/records/21086292\nPDF SHA-256: 0b10852bda89361cd71063867b55d9aed942881476867813facd549a961b0c1d", "keywords": [ "exploratory data analysis", "computational notebook", "reproducible research", "pandas", "data cleaning", "correlation analysis" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_eda_notebook/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "83c96772-d9ab-4b64-baaa-7b1197657808", "key": "Friedman_2026_Exploratory_0b10852b.pdf", "size": 158570, "checksum": "md5:9270a97abfd832bf6c152ed973f4de92", "links": { "self": "https://zenodo.org/api/records/21086293/files/Friedman_2026_Exploratory_0b10852b.pdf/content" } } ], "html_url": "https://zenodo.org/records/21086293", "doi_url": "https://doi.org/10.5281/zenodo.21086292", "record_url": "https://zenodo.org/records/21086292" }, { "record_id": "21083780", "doi": "10.5281/zenodo.21083779", "title": "Sortition Upstream of NTQR: How Panel Formation and Size Shape Ground-Truth-Free Evaluation", "publication_date": "2026-06-25", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "How should you choose the judges, jurors, or reviewers who form a panel — and does\nthat upstream choice change how well you can evaluate them without an answer key?\nA panel can be selected many ways — by competence, by a representative lottery\n(sortition), by ideological bloc, or at random — and, separately, its noisy\njudgments can be evaluated blind: given the agreement/disagreement pattern among\nthree binary judges, the ntqr package's error-independent (EIE) evaluator returns\nlogically consistent estimates of item prevalence and per-judge accuracy with no\nlabels at all. But that evaluator takes the panel as given. We join the two\nquestions and ask whether the rule that forms the panel changes the\noracle-referenced error of the no-answer-key evaluation — how far the blind estimate\nlands from the answer-key result, lower being better.\n\nOn a fully deterministic instrument (96 seeds, 96 experts,\n300 items), the dominant lever is which rule forms the panel, not its size:\ncompetence-first selection recovers best (0.037), while\nrepresentative, single-bloc, and random selection collapse together — by\nconstruction, because with independent judge errors composition cannot move an\nestimator that only sees agreement. Supplying the missing channel — same-group judges\nsharing a latent, marginal-accuracy-preserving error confound — makes the strategies\nfan out monotonically as within-bloc coupling rises: representative sortition stays\nflat while single-bloc selection degrades, the gap widening from 0.000 to\n0.112. Within this instrument the relationship is closed-form: recovery\nerror tracks the panel's Herfindahl concentration index over the axis a shared\nerror rides on — minimized exactly by a balanced (representative) draw, maximized by a\nsingle bloc — and a continuous representativeness dial confirms error rises\nmonotonically with it.\n\nThe protection is conditional: re-keying the confound to an axis the lottery does\nnot balance erases the protection (0.147→0.229). The\nlesson for selecting and evaluating panels is thus a falsifiable, simulation-bounded\nprediction, not a preference for any one rule — representativeness protects blind\nrecovery precisely when the panel balances the attribute a shared error rides on.\nEvidence is synthetic and oracle-scored; in a single small live model\n(gemma3:4b) the synthetically-best competence-first rule was the worst,\nillustrating that a selection rule validated on parameterized judges need not carry\nover to prompted ones — a hypothesis to test, not an established caution. All methods\nand documentation are openly available at the public repository\ndocxology/ntqr_allotment.\n\n---\nAssociated artifacts\nGitHub release: v0.1.0 (https://github.com/docxology/ntqr_allotment/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.21083779\nZenodo: https://zenodo.org/records/21083779\nPDF SHA-256: 73289489d2d123f198ccee83adac10e61a752805d908970030c2d5ac009061e4", "keywords": [ "sortition", "NTQR", "unlabeled evaluation", "expert panels", "peer review", "error independence", "statistical power", "panel formation", "synthetic evaluation", "LLM reviewers" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/ntqr_allotment/releases/tag/v0.1.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "5af41715-74ea-4f15-97f5-7713cb0b4354", "key": "Friedman_2026_Sortition_73289489.pdf", "size": 4380836, "checksum": "md5:c942b77a40441780a20aac0295742dda", "links": { "self": "https://zenodo.org/api/records/21083780/files/Friedman_2026_Sortition_73289489.pdf/content" } } ], "html_url": "https://zenodo.org/records/21083780", "doi_url": "https://doi.org/10.5281/zenodo.21083779", "record_url": "https://zenodo.org/records/21083779" }, { "record_id": "21047574", "doi": "10.5281/zenodo.21047573", "title": "Mapping William Blake's Works: Evidence ledgers, source provenance, text-image diagnostics, and rights-bounded release controls", "publication_date": "2026-06-29", "version": null, "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A reproducible, rights-bounded digital-humanities workflow that builds and audits a target-ledgered William Blake corpus (texts, images, metadata, analysis, visual summaries) and separates open-source code and project-authored aggregate analytics from provider-supplied source materials. This record contains the working-paper PDF (rights-safe: Blake Archive image mosaics omitted) and the open-source software release bundle. The MIT license covers project code and project-authored outputs only; provider-supplied Blake Archive TEI, transcriptions, images, and fallback source texts are excluded and remain under their source-provider terms.", "keywords": [ "William Blake", "digital humanities", "corpus acquisition", "source provenance", "rights-bounded release" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/blake", "relation": "isSupplementTo", "scheme": "url" }, { "identifier": "https://github.com/docxology/blake/releases/tag/v0.1.0", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "429b48be-1034-42bc-a2d1-a906c55f2852", "key": "blake_working_paper.pdf", "size": 11255591, "checksum": "md5:ec897f65c5a85fb7e4393f8e67e8a2f3", "links": { "self": "https://zenodo.org/api/records/21047574/files/blake_working_paper.pdf/content" } } ], "html_url": "https://zenodo.org/records/21047574", "doi_url": "https://doi.org/10.5281/zenodo.21047573", "record_url": "https://zenodo.org/records/21047573" }, { "record_id": "20977774", "doi": "10.5281/zenodo.20976824", "title": "AlphaCOGANT: Recursive Corporate Self-Improvement as Active Inference", "publication_date": "2026", "version": "1.0.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Atta Labs", "orcid": "0000-0001-6232-9096" }, { "name": "Tucker Cahill Chambers", "affiliation": "Atta Labs" } ], "description": "The AlphaFund whitepaper reframes recursive self-improvement (RSI) as a portfolio\noptimization problem: a corporation recursively improves when realized economic\ngains finance the next cycle of better prediction and deployment, and the firm's\nstanding is summarized by t-RSI, a standardized gap between alpha-creation and\nalpha-decay rates. AlphaCOGANT observes that this construction is, term for\nterm, an Active Inference agent — and makes the correspondence executable.\n\nWe render AlphaFund's Economic World Model (EWM) as a generative model written\nin Generalized Notation Notation (GNN), produced by the COGANT\ncodebase-to-GNN translation pattern. The firm's five capital channels —\nInvestments, Sensors, Actuators, Parameters, and R&D — become the hidden-state\nfactors of a partially-observed model; capital allocation becomes the control\nvector; and the portfolio optimizer's marginal-return objective becomes\nExpected Free Energy (EFE) minimization. The EFE decomposition supplies a\nprincipled reading of AlphaFund's own categories: its pragmatic value is\nexpected log-equity growth (the alpha-creation rate, read off the broker ledger),\nand its epistemic value is the information gain about the EWM that Sensors and\nR&D purchase (the data-scaling and forecast-sharpening laws). t-RSI is recovered\nas the standardized distance between the create-rate and decay-rate posteriors —\nthe thresholded EFE-improvement certificate that admits a self-improvement commit\nonly when creation confidently exceeds decay.\n\nWe give the technical and computational realization: a GNN model file for the\nfive-channel firm, a tested NumPy Active Inference engine that performs state\ninference, computes the epistemic/pragmatic EFE split and the marginal-return\nvector, and evaluates the t-RSI certificate. We argue that GNN-via-COGANT brings\ntwo things AlphaFund's program needs and Active Inference already enforces:\nfiltration integrity (the model may condition only on information available\nat decision time — the same \"no-peeking\" discipline that separates an EWM from a\nlanguage model) and auditable capital allocation (every admissible funding\nmove has a negative-EFE score under a single, legible objective). This is not\nfinancial advice; it is a demonstration that this reduced\nrecursive-corporate-self-improvement model has a direct Active Inference\nrepresentation supported by source-owning methods and artifact checks .\n\n---\nAssociated artifacts\nGitHub release: v1.0.1 (https://github.com/docxology/alphacogant/releases/tag/v1.0.1)\nDOI: https://doi.org/10.5281/zenodo.20976824\nZenodo: https://zenodo.org/records/20976824\nPDF SHA-256: 41efa7a8a98e6a67cece68377b8f0c5f19304e85c664ec9516353ee24eb0421f", "keywords": [ "active inference", "expected free energy", "recursive self-improvement", "Generalized Notation Notation", "economic world model", "portfolio optimization", "epistemic value", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/alphacogant/releases/tag/v1.0.1", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "db395d28-6de7-4580-8c23-8e6a7ee4f2e4", "key": "Friedman_2026_Alphacogant_41efa7a8.pdf", "size": 2888068, "checksum": "md5:5d57b61baf89f039a601f0668a327691", "links": { "self": "https://zenodo.org/api/records/20977774/files/Friedman_2026_Alphacogant_41efa7a8.pdf/content" } } ], "html_url": "https://zenodo.org/records/20977774", "doi_url": "https://doi.org/10.5281/zenodo.20976824", "record_url": "https://zenodo.org/records/20976824" }, { "record_id": "20976048", "doi": "10.5281/zenodo.20419007", "title": "A template/ approach to Reproducible Generative Research", "publication_date": "2026-06-27", "version": "1.0.9", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "The reproducibility crisis in computational research is fundamentally structural: research artifacts are scattered across disconnected tools—LaTeX editors, Jupyter notebooks, ad-hoc shell scripts—with no enforced mechanism to keep code, data, and manuscript synchronized. Studies have shown that most published findings are false positives, replication rates in psychology hover around 36%, and only 24% of 1.4 million Jupyter notebooks can be successfully re-executed. Existing tools address fragments of this problem: workflow managers (Snakemake, Nextflow, CWL) orchestrate computation; literate programming systems (Quarto, Jupyter Book, R Markdown, Overleaf, OpenAI Prism) render documents; data versioning tools (DVC) track artifacts—but none enforces cross-cutting quality standards as architectural invariants. template/ applies the principle of Infrastructure as Code to the research lifecycle, making the manuscript, test suite, and provenance chain version-controlled, deterministically buildable, and independently verifiable. It is built on a Two-Layer Architecture that separates 23 infrastructure subdirectories (20 importable Python packages, ~604 modules, validated by ~7,780 tests) from self-contained project workspaces, connected by a YAML-declared pipeline (12 stages; default full 10)-based build pipeline progressing from environment sanitization through test execution (with a Zero-Mock testing policy enforcing 90% project-level and 60% infrastructure-level coverage via real filesystem operations and subprocess invocations), analysis script invocation, Pandoc/XeLaTeX rendering, SHA-256 cryptographic hashing with steganographic watermarking, structural PDF validation, and LLM-assisted review. A Documentation Duality standard equips every directory with both human-readable README.md and machine-readable AGENTS.md files, while each infrastructure module additionally carries a SKILL.md—a structured skill descriptor aligned with the Model Context Protocol—enabling AI agents to locate and invoke module capabilities without hallucinating API signatures.\n\nScalability is demonstrated across the generated public exemplar roster (templates/template_active_inference, templates/template_autoresearch_project, templates/template_autoscientists, templates/template_code_project, templates/template_gold_refinement, templates/template_literature_meta_analysis, templates/template_madlib, templates/template_newspaper, templates/template_prose_project, templates/template_sia, templates/template_template, templates/template_textbook), with representative heterogeneous cases under projects/templates/: optimization (template_code_project, 231 tests), prose (template_prose_project, 120 tests), and AutoResearch readiness (template_autoresearch_project, 296 tests). These guarantee control-positive layouts for code-centric, prose-centric, and retrieval-centric workflows at 90%+ project coverage alongside 60%+ infrastructure gates. All three share identical pipeline stages without cross-project coupling. This manuscript adds a complementary reflexive artifact: authored from projects/templates/template_template (127 tests) as a public exemplar in the same discovered/rendered tree, using the same analysis and render path and injecting counters from repository introspection. The fact that these words, metrics, and figures were generated by the pipeline they describe demonstrates self-documenting capacity: rendered through the DAG, validated without mocks, optionally watermarked. A comparative analysis against nine peer tools across fourteen dimensions positions template/ as integrating fourteen distinctive enforcement capabilities—testing thresholds, cryptographic provenance, steganographic watermarking, multi-project management, MCP-aligned skill descriptors, Zero-Mock policy, orchestration through publication—in one repository. Code is released under the Apache License 2.0 at github.com/docxology/template; the work remains open-ended.\n\n---\nAssociated artifacts\nGitHub release: v1.0.9 (https://github.com/docxology/template_template/releases/tag/v1.0.9)\nDOI: https://doi.org/10.5281/zenodo.20419007\nZenodo: https://zenodo.org/records/20419007\nPDF SHA-256: 535bd80943d0ae9fd504a926efb41c6b39c3a812a94ea4d51bc974029bca563c", "keywords": [ "reproducible research", "infrastructure-as-code", "steganography", "cryptographic provenance", "LaTeX rendering", "modular infrastructure", "publication integrity", "zero-mock testing", "thin orchestrator", "two-layer architecture", "FAIR4RS", "research software engineering" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_template/releases/tag/v1.0.9", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "e82a47dd-1ebf-4535-ac8e-2809a23420c0", "key": "Friedman_2026_Template_535bd809.pdf", "size": 1389726, "checksum": "md5:6114d1f0077f16a066599bbf72cada66", "links": { "self": "https://zenodo.org/api/records/20976048/files/Friedman_2026_Template_535bd809.pdf/content" } } ], "html_url": "https://zenodo.org/records/20976048", "doi_url": "https://doi.org/10.5281/zenodo.20419007", "record_url": "https://zenodo.org/records/20419007" }, { "record_id": "20938523", "doi": "10.5281/zenodo.20931955", "title": "Refinement of Gold: A Metallurgical Analogy for Scientific Manuscript Composition", "publication_date": "2026-06-25", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents a metallurgical analogy for scientific manuscript composition, mapping gold-refining stages onto the template infrastructure pipeline. The refinery processes manuscript ore through 5 stages - from raw draft (9K, ~37.5% purity) through smelting, assaying, and cupellation - to an internal nine-nines certification target (99.9999999%). The source domain is grounded in pre-1800 accounts of metals, assaying, parting, fineness, and marking , while the target domain is a reproducible computational manuscript rather than a claim about universal writing quality.\n\nThe analogy is load-bearing, not merely rhetorical: each metallurgical stage corresponds to a real template-infrastructure operation. This makes the paper an explicit structure-mapping exercise rather than a loose metaphor . Smelting removes dross (filler, unsupported claims); assaying tests claims against evidence; cupellation resolves cross-references; certification validates the full pipeline. The mega-madlib token engine selects 24 domain tokens deterministically via seeded SHA-256 digest over category inventories, ensuring every prose element is traceable and reproducible.\n\nThe contribution is also formalized: 7 equation-backed formalisms define purity, monotone refinement, token selection, claim support, gate vectors, and certification. This positions the manuscript as a research-compendium artifact in the lineage of literate programming, dynamic reports, and reproducible computational research . The project-local claim assay reports 9/9 supported contribution claims (100.00%, passing), while the integrity model exposes 9 source-owned risk dimensions and the shared template evidence registry contributes 291 source-tiered facts when the validation gate has run.\n\nResults: The refinery achieves final purity of 99.9999999% (nine-nines) (24K (nine-nines certified)) with a total purity gain of 90.00% across all stages. Nine-nines certification: Yes. The purity progression is shown in , and the karat grading scale in .\n\nKeywords: gold refining, manuscript composition, mega-madlib, token injection, scientific purity, assaying, karat grading, security assay, supply-chain provenance\n\n---\nAssociated artifacts\nGitHub release: v0.1.0 (https://github.com/docxology/template_gold_refinement/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.20931955\nZenodo: https://zenodo.org/records/20931955\nPDF SHA-256: 946c484b6bc3e0b1d55be00c15eeb09936f4e52bdb2067d2bcde40c2bbea387f", "keywords": [ "gold refining", "manuscript composition", "mega-madlib", "token injection", "scientific purity", "assaying", "karat grading" ], "related_identifiers": [ { "identifier": "https://github.com/owner/repo/releases/tag/gold-refinement-v0.1.0-20260626-visual-integrity", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/template_gold_refinement", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "7bf589b8-7f00-4a98-8492-695fc30467f2", "key": "Friedman_2026_Refinement_946c484b.pdf", "size": 3207775, "checksum": "md5:885f35efe3feaa0fb5a3402383579d69", "links": { "self": "https://zenodo.org/api/records/20938523/files/Friedman_2026_Refinement_946c484b.pdf/content" } } ], "html_url": "https://zenodo.org/records/20938523", "doi_url": "https://doi.org/10.5281/zenodo.20931955", "record_url": "https://zenodo.org/records/20931955" }, { "record_id": "20932112", "doi": "10.5281/zenodo.20533125", "title": "The Template Textbook", "publication_date": "2026", "version": "0.1.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "A modular, fillable scaffold for book-length technical works: a data-driven manuscript (parts/chapters/labs/questions), a tested computational backbone, deterministic figures and Mermaid diagrams, and a content scaffold/validation engine.\n\n---\nAssociated artifacts\nGitHub release: v0.1.2 (https://github.com/docxology/template_textbook/releases/tag/v0.1.2)\nDOI: https://doi.org/10.5281/zenodo.20533125\nZenodo: https://zenodo.org/records/20533125\nPDF SHA-256: 7b67cb2d9118f0a72001395f0a94c529313804d7e5cdf7f6ca2dc9f7ab57d168", "keywords": [], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_textbook/releases/tag/v0.1.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/template_textbook", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "bda10c60-df17-4d07-b34e-7ee4209209ef", "key": "Friedman_2026_Template_7b67cb2d.pdf", "size": 939766, "checksum": "md5:8ca3dccc845b627d2aca63a03218c060", "links": { "self": "https://zenodo.org/api/records/20932112/files/Friedman_2026_Template_7b67cb2d.pdf/content" } } ], "html_url": "https://zenodo.org/records/20932112", "doi_url": "https://doi.org/10.5281/zenodo.20533125", "record_url": "https://zenodo.org/records/20533125" }, { "record_id": "20932066", "doi": "10.5281/zenodo.20453879", "title": "Self-Improvement Agent Harness: A Deterministic SIA Exemplar", "publication_date": "2026", "version": "0.1.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This exemplar documents template_sia, a deterministic implementation of the Self-Improvement Agent (SIA) harness contract described in the Self-Improvement Agents specification (Hexo AI, 2026, arXiv:2605.27276). The default pipeline replays fixture-backed generations for the mini_classify task; opt-in live mode runs bounded target subprocesses and optional Ollama-backed meta/feedback steps.\n\nRun snapshot. Task mini_classify, run 1, 3 generation(s), live=false. Final accuracy=0.8333 over 6 held-out samples. Values are injected by scripts/z_generate_manuscript_variables.py after analysis.\n\nKeywords: self-improvement agents, benchmark harness, reproducible evaluation, agent loops\n\n---\nAssociated artifacts\nGitHub release: v0.1.2 (https://github.com/docxology/template_sia/releases/tag/v0.1.2)\nDOI: https://doi.org/10.5281/zenodo.20453879\nZenodo: https://zenodo.org/records/20453879\nPDF SHA-256: 6e6d19d04182628bb825471cf8094b5c32d2c491d2c646652ec7e2439ba80773", "keywords": [ "self-improvement agents", "benchmark harness", "reproducible research", "agent evaluation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_sia/releases/tag/v0.1.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "7915cc08-3020-4177-a762-f1931d0c1655", "key": "Friedman_2026_Selfimprovement_6e6d19d0.pdf", "size": 223019, "checksum": "md5:f8042650bd618719fb4eab9c40563527", "links": { "self": "https://zenodo.org/api/records/20932066/files/Friedman_2026_Selfimprovement_6e6d19d0.pdf/content" } } ], "html_url": "https://zenodo.org/records/20932066", "doi_url": "https://doi.org/10.5281/zenodo.20453879", "record_url": "https://zenodo.org/records/20453879" }, { "record_id": "20932047", "doi": "10.5281/zenodo.20417104", "title": "Editorial Quality at Scale: A Reproducible Prose-Review Pipeline", "publication_date": "2026", "version": "0.4.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper documents template_prose_project, the prose-focused exemplar of the Research Project Template (https://github.com/docxology/template). It pairs the template's two-layer architecture with the prose analysis infrastructure (https://github.com/docxology/template/tree/main/infrastructure/prose) (readability metrics, structural outline, editorial quality flags) and the reference validation infrastructure (https://github.com/docxology/template/tree/main/infrastructure/reference) (BibTeX validation), demonstrating that rigorous editorial review can be expressed as a configurable, deterministic pipeline with no novel domain algorithm of its own.\n\nA single manuscript/config.yaml defines target grade-level bands, citation-density floors, structural rules (every section has an H1, no heading levels skipped), and bibliography-consistency policy. The pipeline reads the manuscript, runs the prose analysers, cross-checks every citation against manuscript/references.bib, evaluates the configured checks, and writes a deterministic markdown review report alongside three figures (per-file word counts, readability metrics, citation density) and a JSON manuscript_report.json suitable for CI artefacts.\n\nRun snapshot. The current configuration analyses 8 file(s) totalling 1742 words across 86 sentence(s) and 64 paragraph(s). Average Flesch-Kincaid grade level is 15.93; average Gunning Fog index is 16.69; the manuscript references 6 unique citation key(s); the longest section is 413 words and the shortest is 17. These numbers are auto-substituted by scripts/z_generate_manuscript_variables.py after every run, so the abstract tracks the JSON outputs in output/.\n\nThe contribution is methodological and architectural: a generic, reusable prose-quality module (infrastructure/prose/) that any project in the template can opt into, plus a minimal, configurable exemplar (projects/templates/template_prose_project/) that wires it to the bibliography and the manuscript pipeline.\n\nKeywords: prose analysis, readability, editorial review, reproducible manuscript review, scientific infrastructure\n\n---\nAssociated artifacts\nGitHub release: v0.4.2 (https://github.com/docxology/template_prose_project/releases/tag/v0.4.2)\nDOI: https://doi.org/10.5281/zenodo.20417104\nZenodo: https://zenodo.org/records/20417104\nPDF SHA-256: 290d21b10bd588b978d6a3200cdf0e3c2441ca86fcdc777ab41975fa910a260e", "keywords": [ "prose analysis", "readability", "editorial review", "reproducible research", "manuscript quality" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_prose_project/releases/tag/v0.4.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "5593afae-7556-4292-93a3-75711a9ff61c", "key": "Friedman_2026_Editorial_290d21b1.pdf", "size": 132373, "checksum": "md5:2782a0f46d35d45bd44dd1f215cc31fa", "links": { "self": "https://zenodo.org/api/records/20932047/files/Friedman_2026_Editorial_290d21b1.pdf/content" } } ], "html_url": "https://zenodo.org/records/20932047", "doi_url": "https://doi.org/10.5281/zenodo.20417104", "record_url": "https://zenodo.org/records/20417104" }, { "record_id": "20932039", "doi": "10.5281/zenodo.20533675", "title": "The Triplicate: A Data-Driven Large-Format Newspaper Layout Engine", "publication_date": "2026", "version": "1.0.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "We present template_newspaper, a pure-Python engine that renders a complete\ntwelve-page, large-format newspaper to a print-ready PDF from structured YAML\ncontent. The exemplar edition is The Triplicate, a homage to the historic\nnewspaper of Crescent City, California (founded 1879). The engine demonstrates\ndesigned multi-column page layout — nameplate and ears, spanning headlines,\nflowing column frames with an optional rail, drop caps, pull quotes, ruled\nmodular boxes, data tables, halftone \"engraving\" figures and running folios —\nwhile keeping a strict separation between content (data) and engine (code):\na new title is a data edit, never a code change. The layout strategy is a hybrid\nin which fixed furniture is drawn directly on the canvas to establish where\nthe column grid begins, after which body copy flows through ReportLab frames\nthat split paragraphs across columns automatically. The project obeys the\nresearch-template monorepo contract and is discovered and executed by the same\norchestration pipeline as its code- and prose-focused siblings.\n\n---\nAssociated artifacts\nGitHub release: v1.0.2 (https://github.com/docxology/template_newspaper/releases/tag/v1.0.2)\nDOI: https://doi.org/10.5281/zenodo.20533675\nZenodo: https://zenodo.org/records/20533675\nPDF SHA-256: 6c693dbd80a4234d30d99f6a890191ff47faf197a0636753fa9785588c550a77", "keywords": [ "newspaper layout", "typography", "reportlab", "reproducible publishing", "document engineering" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_newspaper/releases/tag/v1.0.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "5c03b237-d262-4ff2-8f6a-4111d48a3441", "key": "Friedman_2026_Triplicate_6c693dbd.pdf", "size": 58491, "checksum": "md5:c0bf1bd76a4649fa5644f91fce4921fc", "links": { "self": "https://zenodo.org/api/records/20932039/files/Friedman_2026_Triplicate_6c693dbd.pdf/content" } } ], "html_url": "https://zenodo.org/records/20932039", "doi_url": "https://doi.org/10.5281/zenodo.20533675", "record_url": "https://zenodo.org/records/20533675" }, { "record_id": "20932025", "doi": "10.5281/zenodo.20786638", "title": "Template Madlib: Deterministic Token Injection for Conditional IMRAD Manuscripts", "publication_date": "2026-06-26", "version": "0.1.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This exemplar asks whether a reviewable pipeline can hydrate a complete IMRAD manuscript from configuration-owned lexical data while preserving an audit trail that remains readable before and after rendering. The project deliberately keeps playful Mad Lib mechanics inside a serious reproducibility contract: the manuscript shell names large placeholders, the config declares allowable language, and the source code decides what text is emitted.\n\nThe committed seed is 431 and the current schema expands 22 slot rule(s) into 40 token choice(s) across 10 lexicon categories. The configured narrative moves are state the manuscript-generation problem, name the deterministic intervention, and summarize the audit surface. The central hypothesis is: Deterministic lexical injection can generate a complete conditional IMRAD manuscript while preserving token provenance, section intent, and audit-ready method evidence.\n\nThe result is not a claim that lexical substitution creates scholarship. It is a worked template for conditional manuscript assembly: section enablement, token provenance, figure registration, and unresolved-placeholder checks all become inspectable artifacts before the shared renderer produces PDF, HTML, and slides.\n\n---\nAssociated artifacts\nGitHub release: v0.1.1 (https://github.com/docxology/template_madlib/releases/tag/v0.1.1)\nDOI: https://doi.org/10.5281/zenodo.20786638\nZenodo: https://zenodo.org/records/20786638\nPDF SHA-256: d9248f4f372fc3baf21cbf5cc5cdb7daffe0e22e62ac6fa2e3a697a26f3308b6", "keywords": [ "madlib generation", "token injection", "conditional manuscripts", "reproducible research", "IMRAD" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_madlib/releases/tag/v0.1.1", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/template_madlib", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "abc6f31a-e0b6-470a-8558-85d925aa0313", "key": "Friedman_2026_Template_d9248f4f.pdf", "size": 1001791, "checksum": "md5:32120c5f91f372ca7cb2ddfc4ac6d4b0", "links": { "self": "https://zenodo.org/api/records/20932025/files/Friedman_2026_Template_d9248f4f.pdf/content" } } ], "html_url": "https://zenodo.org/records/20932025", "doi_url": "https://doi.org/10.5281/zenodo.20786638", "record_url": "https://zenodo.org/records/20786638" }, { "record_id": "20931965", "doi": "10.5281/zenodo.20931964", "title": "A Living Meta-Analysis of the Modafinil Literature", "publication_date": "2026", "version": "0.1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "Manual synthesis cannot keep pace with a fast-growing research literature, and ad-hoc\nreviews bind no evidence to a reproducible pipeline. We present a configurable,\nreproducible meta-analysis framework that takes a single search term and produces a\ncomplete quantitative portrait of its literature. For this instance the term is\nModafinil. The pipeline dispatches across 7 literature\nengines (arXiv, OpenAlex, Semantic Scholar, Crossref, PubMed, SovietRxiv, and ChinaRxiv), each degrading gracefully to a skipped source when an API\nkey or the network is unavailable, then merges and de-duplicates records by a canonical\nidentifier hierarchy (DOI $>$ arXiv ID $>$ Semantic Scholar ID $>$ OpenAlex ID $>$ title\ndigest) into a corpus of $N = 2302$ records spanning 2000--2026\n(26 years). Records are classified into a configurable 6-bucket\nsubfield taxonomy (Clinical Sleep, Cognition, Pharmacology, Psychiatry, Safety, and Neuroscience); the largest subfield is Clinical Sleep\n(64.3\\% of the classified corpus). The corpus grows at a compound annual\nrate of 3.45\\% (mean year-over-year growth 6.3\\%, doubling time\n11.3 years), peaking in 2025 with 112 records.\n\nNon-negative matrix factorization extracts 5 latent topics over a\n500-feature vocabulary, offline deterministic embeddings place every\ntitle, abstract, and (when available) full text in a shared vector space, and\ncitation-network analysis exposes the corpus's internal structure (8,772\nintra-corpus edges across 2204 nodes, 1377 communities,\ngraph density 0.18\\%). Of 38,802 total outgoing\nreferences, 22.6\\% resolve to another record inside the corpus.\nAbstract coverage stands at 55.5\\%, open-access status is known for\n14.4\\% of records, and 40.9\\% have a direct PDF link. An optional,\nLLM-gated knowledge-graph stage scores the 6 hypotheses explored against\nthe evidence. This run produced 18 publication-quality figures.\n\nEvery domain-specific value in this manuscript — the search term, keyword set, engine\nroster, subfield taxonomy, and hypotheses — is injected from a single configuration file\nand the pipeline's own outputs; re-targeting the configuration re-targets the entire\npaper. The result is a reusable architecture for living literature reviews:\ncontinuously re-runnable, evidence-bound syntheses for any topic.\n\nKeywords: modafinil, meta-analysis, literature retrieval, bibliometrics, record de-duplication, full-text mining, document embeddings, citation network, topic modeling, entity extraction, wakefulness, cognitive enhancement, reproducible research\n\n---\nAssociated artifacts\nGitHub release: v0.1.0 (https://github.com/docxology/template_literature_meta_analysis/releases/tag/v0.1.0)\nDOI: https://doi.org/10.5281/zenodo.20931964\nZenodo: https://zenodo.org/records/20931964\nPDF SHA-256: 412d4fcf4b0c2e14fb950f9080f107d81fd9a90dfdf216b9161a13833eff62ff", "keywords": [ "modafinil", "meta-analysis", "literature retrieval", "bibliometrics", "record de-duplication", "full-text mining", "document embeddings", "citation network", "topic modeling", "entity extraction", "wakefulness", "cognitive enhancement", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_literature_meta_analysis/releases/tag/v0.1.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/template_literature_meta_analysis", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "20a0de48-82f3-4347-a313-50c186dd00ea", "key": "Friedman_2026_Living_412d4fcf.pdf", "size": 7314033, "checksum": "md5:6504fdc61d497e1665bd6a304c1ffcaf", "links": { "self": "https://zenodo.org/api/records/20931965/files/Friedman_2026_Living_412d4fcf.pdf/content" } } ], "html_url": "https://zenodo.org/records/20931965", "doi_url": "https://doi.org/10.5281/zenodo.20931964", "record_url": "https://zenodo.org/records/20931964" }, { "record_id": "20931934", "doi": "10.5281/zenodo.20417136", "title": "Convergence Analysis of Gradient Descent Optimization", "publication_date": "2026-06-26", "version": "2.5.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents a convergence study of fixed-step gradient descent on a convex quadratic, framed as the computational exemplar of the Research Project Template (https://github.com/docxology/template). The implementation lives in projects/templates/template_code_project/src/optimizer.py; experiments and figures are orchestrated by projects/templates/template_code_project/scripts/optimization_analysis.py and hydrated into the manuscript through scripts/z_generate_manuscript_variables.py, so tables and prose track output/data/optimization_results.csv after every pipeline run.\n\nWe evaluate 6 step sizes from $\\alpha = 0.01$ to $\\alpha = 2.5$, spanning conservative, near-optimal, aggressive, and divergent regimes for a unit Hessian model. The build chain exercises template infrastructure end-to-end: scientific helpers (infrastructure.scientific.stability, infrastructure.scientific.benchmarking), validation, rendering (infrastructure/rendering/pdf_renderer.py), and reporting. Accessibility-oriented plotting defaults (colourblind-safe palette, 300 dpi exports) are centralized in src/figures/ and src/analysis/.\n\nContributions are methodological and architectural. On the methods side, we relate empirical iteration counts and error decay to the scalar contraction factor $\\rho(\\alpha) = |1-\\alpha|$ and document cases where runs hit $N_{\\max} = 1000$ before meeting the gradient tolerance. On the architecture side, we demonstrate a zero-mock test suite on project src/ (see test_optimizer.py (https://github.com/docxology/template/blob/main/projects/templates/template_code_project/tests/test_optimizer.py)), automated six-figure analysis, and reproducibility metadata (configuration hash, artifact counts) injected into .\n\nResults (this configuration): 4 of 6 grid points report converged=True in the CSV; non-convergent rows flag either slow progress at small $\\alpha$ under the iteration cap or instability when $|1-\\alpha| \\geq 1$. The analytical minimizer remains $x^\\ast = 1.0$ with $f(x^\\ast) = -0.5$ for the configured $(A,b)$.\n\nKeywords: optimization algorithms, gradient descent, convergence analysis, numerical methods, mathematical programming, reproducible research, infrastructure automation\n\n---\nAssociated artifacts\nGitHub release: v2.5.2 (https://github.com/docxology/template_code_project/releases/tag/v2.5.2)\nDOI: https://doi.org/10.5281/zenodo.20417136\nZenodo: https://zenodo.org/records/20417136\nPDF SHA-256: cd54b95893501467503fab2c4b432573306bc94f7040085550beb87d094b4e50", "keywords": [ "optimization algorithms", "gradient descent", "convergence analysis", "numerical methods", "mathematical programming", "reproducible research", "infrastructure automation" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_code_project/releases/tag/v2.5.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "6b0dfbfe-7955-4235-8c2c-5a57f87c3bf7", "key": "Friedman_2026_Convergence_cd54b958.pdf", "size": 1731747, "checksum": "md5:a803dbe3d9ca49a03ce319dba456eeed", "links": { "self": "https://zenodo.org/api/records/20931934/files/Friedman_2026_Convergence_cd54b958.pdf/content" } } ], "html_url": "https://zenodo.org/records/20931934", "doi_url": "https://doi.org/10.5281/zenodo.20417136", "record_url": "https://zenodo.org/records/20417136" }, { "record_id": "20931927", "doi": "10.5281/zenodo.20533669", "title": "A Deterministic Testbed for Self-Organizing Agent-Team Coordination", "publication_date": "2026-06-26", "version": "1.0.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Recent work on AutoScientists coordinates self-organizing teams of language-model agents through a small set of shared mechanisms: a champion-and-experiment-log shared state, a registry of retired dead-end directions, effect-size ranking of candidate directions, noise-band confirmation of claimed improvements, and stagnation-driven reorganization of teams. This exemplar provides a deterministic, standalone reference implementation of those mechanisms and studies them honestly as a testbed rather than as a performance claim.\n\nWe make the comparison fair by holding the total number of objective evaluations fixed: coordinated teams partition a single sequential experiment budget rather than adding parallel compute. Under that matched budget, coordination cannot — and in our results does not — beat a single-thread baseline on the final champion metric; we report the actual numbers and claim no speedup. What the testbed does demonstrate are two distinct, independently measurable benefits. First, noise-robustness: because the objective is stochastic, a single observed gain can be a draw of evaluation noise, so we separate the reported champion metric from the clean noise-free ground truth and show that noise-band confirmation shrinks the gap between them by roughly an order of magnitude — with confirmation on, the final champion's reported metric sits $0.0012$ above its clean value, against $0.0156$ with confirmation removed, while every configuration reaches the same clean optimum. Second, search hygiene: the dead-end registry, consulted by the proposer, cuts redundant re-probes of retired directions from $36$ to $0$ and halts at $36$ of the $60$ experiments — the same clean answer, reached with less waste. A per-mechanism ablation isolates each component's contribution, and the language-model proposer is a clean plug-in seam: a deterministic rule-based agent drives the reproducible figures, and a live Hermes agent (served by Ollama) can be swapped in without touching the coordination loop.\n\n---\nAssociated artifacts\nGitHub release: v1.0.2 (https://github.com/docxology/template_autoscientists/releases/tag/v1.0.2)\nDOI: https://doi.org/10.5281/zenodo.20533669\nZenodo: https://zenodo.org/records/20533669\nPDF SHA-256: 0af391375b14eb397812a8050657e2980fbc3a768e6fb108aa2f7eff46773e16", "keywords": [ "agent coordination", "scientific discovery", "noise-band confirmation", "ablation study", "reproducible research", "language-model agents" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_autoscientists/releases/tag/v1.0.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "3df5a195-85cd-4af1-b56d-07429b2d6d5b", "key": "Friedman_2026_Deterministic_0af39137.pdf", "size": 272072, "checksum": "md5:8b8dfc39adece49cc30135eebc00f794", "links": { "self": "https://zenodo.org/api/records/20931927/files/Friedman_2026_Deterministic_0af39137.pdf/content" } } ], "html_url": "https://zenodo.org/records/20931927", "doi_url": "https://doi.org/10.5281/zenodo.20533669", "record_url": "https://zenodo.org/records/20533669" }, { "record_id": "20931907", "doi": "10.5281/zenodo.20417016", "title": "Bounded AutoResearch for a Tiny Reproducible Machine-Learning Task", "publication_date": "2026", "version": "0.3.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper presents Deterministic bounded AutoResearch for a small MNIST neural-network task, a public template exemplar that\nturns an AutoResearch loop into ordinary reproducible research infrastructure.\nThe case study is intentionally small but concrete: 2000 training\nand 500 test images from MNIST handwritten digit database are evaluated by the\nbounded small MNIST neural-network classification loop. The run evaluates\n4 of 5 proposed candidates,\nincluding Tiny patch-attention classifier, selects\nexp-mlp-tanh-64 (MLP,\n50890 parameters), and improves test_accuracy from\n82.6% to 89.4%\n(6.8% absolute change). The validated diagnostic layer reports\nmacro F1 89.4%, bootstrap accuracy interval\n86.4% to 92.0%, Brier score 0.161,\nnegative log likelihood 0.361, top-2 accuracy\n95.6%, and exact McNemar p-value 0.000.\nThe same pipeline writes proposal, candidate, run, review, benchmark, evidence,\nfigure, confusion-matrix, statistical-summary, probability-quality, and\nsecurity-integrity artifacts from declared output contracts; uses\n0 LLM calls at USD 0.00 cost; and records\n7 configured stages, 6 supported\nlocal-artifact claims, and 78 required artifacts.\nThe local security attestation status is passed,\nwith 0 checksum mismatch(es). The final\nreadiness status is passed, with review gates deferred to a\nhuman rather than self-approved by the generated run.\n\n---\nAssociated artifacts\nGitHub release: v0.3.2 (https://github.com/docxology/template_autoresearch_project/releases/tag/v0.3.2)\nDOI: https://doi.org/10.5281/zenodo.20417016\nZenodo: https://zenodo.org/records/20417016\nPDF SHA-256: e07b62850a1995935283d37a45c21d71fa7c4e69cdcc451c5a1ea8aee6d0c94a", "keywords": [ "autoresearch", "reproducible research", "machine learning benchmark", "artifact readiness", "human review", "local artifact integrity" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_autoresearch_project/releases/tag/v0.3.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "2fe228ec-c181-459d-869c-9443ba481185", "key": "Friedman_2026_Bounded_e07b6285.pdf", "size": 1344238, "checksum": "md5:c2059200d73ecfefc8fb1f5365787bca", "links": { "self": "https://zenodo.org/api/records/20931907/files/Friedman_2026_Bounded_e07b6285.pdf/content" } } ], "html_url": "https://zenodo.org/records/20931907", "doi_url": "https://doi.org/10.5281/zenodo.20417016", "record_url": "https://zenodo.org/records/20417016" }, { "record_id": "20931870", "doi": "10.5281/zenodo.20417021", "title": "Active Inference Multi-Track Exemplar", "publication_date": "2026-06-26", "version": "0.3.2", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "We study a minimal Active Inference stack on toy models: a Bernoulli–Ising analytical oracle, a pymdp T-maze rollout, and a sheaf-indexed compose contract that binds 34 fragment tracks into 12 flat IMRAD sections. The methodological contribution is a discipline rather than a domain finding: every reported number is hydrated from a generated artifact and every cross-track claim is machine-checked before rendering, so no figure or statistic can drift from the artifact that produced it — 6 sheaf axioms are verified before composition and 25 negative controls keep each failure path live. Claims are limited to those models and their generated artifacts.\n\n reports a 17-row coverage matrix (5 IMRAD group headers) regenerated from the live manifest at compose time. documents the T-maze harness aligned with pymdp sophisticated_inference examples (https://github.com/infer-actively/pymdp/tree/main/examples/experimental/sophisticated_inference).\n\n records 12 / 12 invariant checks passed. SI planning horizon: 2 steps. Sweep RMSE 0 nats bounds analytical–empirical agreement on the coupling grid.\n\n---\nAssociated artifacts\nGitHub release: v0.3.2 (https://github.com/docxology/template_active_inference/releases/tag/v0.3.2)\nDOI: https://doi.org/10.5281/zenodo.20417021\nZenodo: https://zenodo.org/records/20417021\nPDF SHA-256: f191b48f94394cab17069fd04502c59fc1c287e7893eb078e05ba4be04d4a04c", "keywords": [ "active inference", "pymdp", "sophisticated inference", "generalized notation notation", "lean" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/template_active_inference/releases/tag/v0.3.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "f556495b-404c-463e-9c66-4c238e1f9b4f", "key": "Friedman_2026_Active_f191b48f.pdf", "size": 4101185, "checksum": "md5:6f4384a19ed6e98fe20de9a457b69163", "links": { "self": "https://zenodo.org/api/records/20931870/files/Friedman_2026_Active_f191b48f.pdf/content" } } ], "html_url": "https://zenodo.org/records/20931870", "doi_url": "https://doi.org/10.5281/zenodo.20417021", "record_url": "https://zenodo.org/records/20417021" }, { "record_id": "20834847", "doi": "10.5281/zenodo.20834846", "title": "Realizing Emptiness: Operational Surrogates for No-Self-Evidence, QRF Opacification, and Bayesian Model Reduction", "publication_date": "2026-06-24", "version": "1.0.0", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper formulates on-policy distillation as active inference in finite variational models, with exact claims only for declared objects and interpretive claims explicitly bounded outside them. In the construction, the intractable teacher policy plays the role of the generative model $p(o,s)$, the tractable student policy is the approximate posterior $q(s)$, and the per-token reverse-KL distillation loss is variational free energy up to the evidence constant, $F = D_{\\mathrm{KL}}(q\\,\\|\\,p(s\\mid o)) - \\log p(o)$, whose KL target is the teacher-induced posterior $p(s\\mid o)\\propto p(o,s)$ . The title's \"as\" is therefore a scoped mathematical correspondence rather than the slogan OPD = Active Inference. Variational free energy names the realized-rollout distillation loss; expected free energy remains the planning-side objective by which the pymdp agent selects actions . On-policy student rollouts generate the observations on which the posterior is scored, connecting the construction to induced-distribution mismatch in imitation learning and exposure-bias analyses while preserving their different objectives, empirical regimes, and contested severity . Privileged traces and feedback play the role that train-time-only information plays in the LUPI/distillation lineage . Four deterministic witnesses instantiate the correspondence. A Bernoulli-Ising oracle couples a teacher's privileged variable to the answer through $\\lambda$, making $I(\\lambda)$ the teacher-student mutual information and the finite free-energy gap the toy distillation objective; the closed-form and independently recomputed mutual-information sweeps agree to machine precision (RMSE 2.1e-16 nats). A pymdp T-maze rollout supplies the on-policy student that samples its own observations under a privileged cue . A two-agent classroom pits a privileged teacher (cue validity 0.98) against an on-policy student (cue validity 0.5), measuring teacher belief entropy 0.247 nats versus student 0.347 nats and a mean reverse-KL distillation signal of 6.28 nats. A four-state/two-action sequential-shift witness shows teacher-forced train loss 0.333 nats underestimating student-induced test loss 0.409 nats, with deterministic on-policy correction reducing it to 0.096 nats. These are toy, generated findings, not production-LLM measurements. Recent privileged-context, context-distillation, adaptive-teacher, freshness-aware OPD, RLHF/instruction-tuning, self-generated reasoning, Qwen OPD-vs-RL, and Thinking Machines replication reports remain external context rather than reproduced results . The supplemental sheaf/provenance layer keeps that boundary operational: every reported number is hydrated from a generated artifact, every figure is source-bound, and 16 / 16 invariant checks pass before rendering. --- Associated artifacts GitHub release: v1.0.2 (https://github.com/ActiveInferenceInstitute/on_policy_distillation/releases/tag/v1.0.2) DOI: https://doi.org/10.5281/zenodo.20749817 Zenodo: https://zenodo.org/records/20749817 PDF SHA-256: c6b5ec494915e6e046f24cf723f8dbbf93a5b168544daed3cca14c089d4087aa
", "keywords": [ "on-policy distillation", "active inference", "self-distillation", "privileged information", "free energy principle", "reverse KL divergence", "pymdp", "sophisticated inference" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/on_policy_distillation/releases/tag/v1.0.2", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "c87b035e-4380-4dc4-bf28-d6ad0f125264", "key": "Friedman_2026_Onpolicy_c6b5ec49.pdf", "size": 8102450, "checksum": "md5:91b9bc1743901832f8b1814e8b6060fa", "links": { "self": "https://zenodo.org/api/records/20749817/files/Friedman_2026_Onpolicy_c6b5ec49.pdf/content" } } ], "html_url": "https://zenodo.org/records/20749817", "doi_url": "https://doi.org/10.5281/zenodo.20747834", "record_url": "https://zenodo.org/records/20747834" }, { "record_id": "20732275", "doi": "10.5281/zenodo.20732274", "title": "AGEINT: Agentic Intelligence", "publication_date": "2026-06-17", "version": "0.1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "Synthetic Analytic Tradecraft (AGEINT, or Agentic Intelligence), is a local curriculum-and-assurance atlas for teaching bounded AI-agent support inside intelligence education by making the machinery of Synthetic Analytic Tradecraft visible on the page. It converts SIST Guide TOC and Bibliography into 16 parts, 51 modules, 9 methods appendices, 20 named AGEINT patterns, and 312 parsed source-guide references without renumbering inherited source identities, then asks the reader to inspect the same things an instructor or assurance reviewer would inspect: the part map that frames the domain, the module overview that names the learner task, the source spine that separates official, standards, scholarly, public-domain, practitioner, vendor, and provenance-only support while separating source quality from narrative fluency, the evidence packet that a student would retain, the reviewer challenge that should break a weak claim, and the validators that prevent a polished artifact from masquerading as a verified one. A learner does not enter through a slogan. The learner opens a module, sees which authority and source keys are allowed to carry the claim, reads a textbook primer that distinguishes observation from inference, confidence from probability, and source quality from fluency, works through a synthetic practice studio using classroom records, public declassified examples, owned-lab logs, toy datasets, rendered figures, or tabletop incidents, and then produces a bounded artifact with caveats, assumptions, alternatives, excluded actions, human review, rollback evidence, and refresh triggers written into the record before reuse. The method contract in shows that flow as a claim-to-evidence pathway rather than as an aspirational ethics statement: authority must be named before the task begins, source support must be traceable before a claim is promoted, unsafe action must be replaced by safe substitution, and agentic assistance must remain a drafting, retrieval, comparison, simulation, critique, or audit aid whose output is never treated as self-authenticating . AGEINT remains synthetic in its fixtures, not in its standards: the word synthetic is therefore a control, not a downgrade. AGEINT keeps the fixture safe while keeping the standard difficult: HUMINT, SIGINT, OSINT, GEOINT and IMINT, FININT, counterintelligence, cyber threat intelligence, cognitive security, agent orchestration, active inference, source verification, public-sector governance, privacy review, and industrial-control-system defense can be discussed because the student is not handed live targets, evasion recipes, exploit instructions, manipulation playbooks, covert-action procedures, or unsafe cyber-physical steps. When a source topic could invite misuse, the module turns the risky motif into a provenance card, detection-coverage note, rights-impact worksheet, model or dataset card, source-refresh memo, release gate, risk-exception log, remediation backlog, or debrief protocol, and the exercise fails if it cannot show where authority, data boundary, tool permission, uncertainty, and review enter the workflow. The source layer is intentionally conservative: Perplexity and similar discovery tools may suggest candidates, but the manuscript cites verified official, standards, public-domain, or scholarly anchors encoded in the source corpus and rebuilt into BibTeX; Practitioner, vendor, and blog sources inherited through the source guide, plus social or other guide-inherited rows, can preserve provenance context without becoming foundational support for governance, rights, safety, empirical, statistical, or performance claims unless a stronger verified source bears the specific point. The same source posture is visible in the counts: 10 source-quality anchors cover the governing standards and assurance spine, while 462 curated intelligence research anchors span the domain lanes that route claim-bearing prose to direct evidence rather than decorative citations. A strong AGEINT artifact is therefore not an uninspected essay. It is an evidence packet that names the question, allowed inputs, excluded actions, source keys, claim type, caveats, competing explanations, confidence basis, prompt or run card, tool allowlist, data boundary, stop condition, reviewer challenge, safety boundary, refresh trigger, and human disposition. It also contains negative controls: stale citations that should be caught, weak-source-only claims that should be downgraded, figure positions or colors that should not be mistaken for quantitative evidence, overbroad statistical language that should fail, and operational substitutions that should halt until an instructor or reviewer approves a safer artifact. A reviewer can trace a finished packet in both directions: from a polished sentence back to the claim class, source family, cited anchor, caveat, and source-refresh duty, or from a source row forward to the modules, figures, tables, and exercises that rely on it. A student can see why a governance claim needs law, policy, standard, or official guidance support; why a cyber or industrial-control-system scenario must remain defensive and synthetic; why a social or cognitive-security lesson must become resilience education rather than persuasion practice; why a vendor or practitioner note can motivate a question but cannot by itself carry a public-rights or safety assertion; why a figure caption must say whether arrows are explanatory or quantitative; and why a model-generated draft is only useful after it has been constrained by authority, reviewed by a person, and attached to evidence that another person can contest. The early orientation pages, part maps, chapter landmarks, appendices, bibliography atlas, source-lane map, and generated reports are designed to make that trace visible instead of leaving it to instructor memory. They show the learner what to keep: the source keys behind each claim, the reason a safer substitute was chosen, the assumption that would change the answer, the dissent that should not be smoothed away, the review note that records who accepted residual risk, the rollback path if a source or permission changes, and the refresh trigger that turns a current claim back into a review item. They also show what the curriculum refuses to keep: unverifiable authority theater, live-target instructions, metric-looking diagrams without units or denominators, statistical decorations without empirical design, citation clusters that do not bear the sentence they decorate, and agent outputs whose provenance cannot be reconstructed. The technical build is part of that scholarship. Curriculum shards generate semantic manuscript files; cross-references use label-backed section and figure links, and display equations are typeset from source for reproducible math; citations route through Pandoc keys; figures are registry-backed PNG assets with captions, alt text, long descriptions, provenance, hashes, and visual-semantics metadata; source anchors carry explicit lane and tier fields; claim calibration audits high-risk empirical, statistical, governance, safety, visualization, artifact-readiness, and formalism language; scholarship and source-metadata reports expose review warnings instead of hiding them; PDF audits check stale output, URI targets, file actions, and banned filler language. The analysis-validation matrix in names which claim classes require empirical evidence, direct source-family support, negative controls, figure semantics, or rendered-artifact checks before they can be treated as ready, and that matrix is a boundary on what the manuscript can honestly say. AGEINT is not a benchmark and does not claim to measure AGEINT performance, model capability, analyst replacement, learning outcomes, operational effectiveness, public-sector impact, statistical significance, or safety performance; page counts, citation counts, figure counts, validator passes, and link audits are artifact telemetry, not empirical outcome evidence. Its strongest claim is methodological and inspectable: agentic assistance can be taught inside intelligence education when every reuse path is forced through authority, source support, safe substitution, evidence packet, negative controls, human review, rollback, and refresh triggers, and when the safest failure mode is to stop, document the unresolved condition, and ask for review. The resulting work should be read as a Synthetic Analytic Tradecraft atlas, not as a public-release certificate or a disguised operational manual: the reader can see the source key behind a sentence, the caveat behind a confidence statement, the assumption behind a scenario, the blocked use behind a tempting automation, the challenge behind a polished answer, the caption that limits a visual, the validator that rejects an overclaim, and the refresh duty that keeps current-source prose from becoming stale authority.
", "keywords": [ "agentic intelligence", "AGEINT", "AI agents", "intelligence tradecraft", "cognitive security", "structured analytic techniques", "active inference", "model context protocol", "multi-agent systems", "operational governance" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/AGEINT", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "ebda7487-fa0a-44c4-b18e-a19dd810ebad", "key": "AGEINT-Agentic-Intelligence-Edition-0.1.pdf", "size": 35805348, "checksum": "md5:382b7bf75ca9b24a210b6e3c651916d5", "links": { "self": "https://zenodo.org/api/records/20732275/files/AGEINT-Agentic-Intelligence-Edition-0.1.pdf/content" } } ], "html_url": "https://zenodo.org/records/20732275", "doi_url": "https://doi.org/10.5281/zenodo.20732274", "record_url": "https://zenodo.org/records/20732274" }, { "record_id": "20705351", "doi": "10.5281/zenodo.20705350", "title": "COGANT: Deterministic Codebase-to-GNN Translation", "publication_date": "2026-06-15", "version": "0.6.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "COGANT (Codebase-to-GNN Translation) deterministically converts software repositories into structured Active Inference artifacts expressed in the Active Inference Institute's Generalized Notation Notation (GNN). It is an evidence compiler: it propagates reviewable program facts through a finite fixpoint rule pipeline and emits graph, matrix, provenance, visualization, and round-trip artifacts with confidence and provenance, rather than a single opaque embedding. A reverse synthesizer reconstructs a runnable Python package from an emitted GNN bundle, closing a forward-reverse-forward evaluation loop. This is the first public release (v0.6.0). Source: https://github.com/ActiveInferenceInstitute/COGANT", "keywords": [ "program analysis", "Generalized Notation Notation", "GNN", "intermediate representation", "code property graph", "active inference", "reproducible research", "codebase-to-model translation", "cognitive ecosystem modeling" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/COGANT/releases/tag/v0.6.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/ActiveInferenceInstitute/COGANT", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "a0e70a03-0560-4ac0-b6e0-0723eb1d3cd4", "key": "COGANT-0.6.0.pdf", "size": 3654907, "checksum": "md5:dedaed9bedb1243962e9a462a38e47fc", "links": { "self": "https://zenodo.org/api/records/20705351/files/COGANT-0.6.0.pdf/content" } } ], "html_url": "https://zenodo.org/records/20705351", "doi_url": "https://doi.org/10.5281/zenodo.20705350", "record_url": "https://zenodo.org/records/20705350" }, { "record_id": "20693217", "doi": "10.5281/zenodo.20693216", "title": "DemoCreate: Declarative Audio-Visual Demo Generation for Software", "publication_date": "2026-06-04", "version": "0.6.2", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "DemoCreate generates audio-visual demos of software — codebase tours, website walkthroughs, and terminal/CLI demos — from a single declarative, deterministic spine. A Demo is an ordered action stream plus narration chunks, merging CodeVideo's event-sourced virtual-IDE model with VSpeak's chunk/trigger model. Every heavy backend (TTS via Kokoro/Chatterbox, transcription via Whisper, capture via mss/Playwright, animation via Manim, assembly via MoviePy/ffmpeg) sits behind an abstract interface with a pure-Python deterministic default, so the package produces a real demo with only light dependencies and upgrades when extras are installed. On-screen actions are anchored to spoken trigger words via TTS→STT synchronization: narration audio is generated, transcribed back to word-level timestamps, and used to align the action stream with the narration.
", "keywords": [ "demo-generation", "screencast", "text-to-speech", "code-walkthrough", "video", "narration", "whisper", "manim", "playwright", "reproducible", "deterministic", "tts-stt-synchronization", "virtual-ide" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/democreate", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "44d72816-3ada-4ba9-aa14-c23409fec5a0", "key": "democreate-0.6.2-py3-none-any.whl", "size": 172758, "checksum": "md5:69d57765d701aa12ecb92a72fb547aee", "links": { "self": "https://zenodo.org/api/records/20693217/files/democreate-0.6.2-py3-none-any.whl/content" } }, { "id": "e8913d13-6680-4065-9e99-f7804fdd9509", "key": "democreate-0.6.2-manuscript.pdf", "size": 1246461, "checksum": "md5:38a62e6fb2b55de584a46d8257b02194", "links": { "self": "https://zenodo.org/api/records/20693217/files/democreate-0.6.2-manuscript.pdf/content" } }, { "id": "cc477d68-18a5-4a58-a132-ea98a834555a", "key": "democreate-0.6.2-source.zip", "size": 35551741, "checksum": "md5:300ab65faecc98d5eb70c082fbec8066", "links": { "self": "https://zenodo.org/api/records/20693217/files/democreate-0.6.2-source.zip/content" } } ], "html_url": "https://zenodo.org/records/20693217", "doi_url": "https://doi.org/10.5281/zenodo.20693216", "record_url": "https://zenodo.org/records/20693216" }, { "record_id": "20647443", "doi": "10.5281/zenodo.20396328", "title": "ENTO: an ENcrypted, Typed, Omnitrack container format for multimodal research data", "publication_date": "2026-06-11", "version": "0.4", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "ENTO (ENcrypted, Typed, Omnitrack) is a flat ZIP container format and reference implementation for bundling heterogeneous research artifacts — time series, genomics slices, spectrograms, provenance proofs — into a single verifiable file. Each track is sealed under per-track AES-256-GCM authenticated encryption with format+track associated-data binding and PADMÉ length padding. The default wire format is 0.4.0; formats 0.2.0, 0.3.0, and 0.3.1 remain read/write compatibility profiles. Graded observability levels control how much manifest metadata a recipient sees, and an optional hash-chained proof export provides tamper-evident lineage. Verification deliberately separates key-authenticated integrity from keyless corruption detection.
This deposit is the 0.4 manuscript release candidate together with the MIT-licensed reference implementation source. Planned code home: https://github.com/docxology/entofile.
", "keywords": [ "research data formats", "authenticated encryption", "AES-256-GCM", "reproducible research", "multimodal containers" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/entofile", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "6f0a6683-bdd9-4648-b7ae-4e8233a3a850", "key": "entofile-0.4.pdf", "size": 3481755, "checksum": "md5:9d112da737dd1e50bb8a5587aa9311b9", "links": { "self": "https://zenodo.org/api/records/20647443/files/entofile-0.4.pdf/content" } }, { "id": "dde232d7-bef3-4b8f-871f-294058d6ebb5", "key": "entofile-0.4-source.zip", "size": 521809, "checksum": "md5:7dd2854c99637f087d941e9dec0b37a3", "links": { "self": "https://zenodo.org/api/records/20647443/files/entofile-0.4-source.zip/content" } } ], "html_url": "https://zenodo.org/records/20647443", "doi_url": "https://doi.org/10.5281/zenodo.20396328", "record_url": "https://zenodo.org/records/20396328" }, { "record_id": "20498700", "doi": "10.5281/zenodo.20498699", "title": "Recovering LLM-Persona Accuracies from Unlabeled Votes", "publication_date": "2026-06-01", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "Algebraic (NTQR) evaluation infers how accurate a group of noisy classifiers was on a finite test using only their responses — no answer key. We test this end to end on real large language models. Three trader \"personas\" (optimistic, neutral, pessimistic), instantiated as system prompts, each make a binary bullish/bearish call on the same 64 market scenarios; we run the identical trio through six locally-hosted models via Ollama. For each model we recover per-persona, per-label accuracy with ErrorIndependentEvaluation (unsupervised) and score it against the authored ground truth (supervised), which is used only as a check. On the five models whose three judges all varied (mistral:latest, gemma4:latest, gemma3:4b, gemma2:2b, granite4.1:3b), the unsupervised algebra recovered persona accuracies to a mean absolute error of 0.012, within the 0.102 sampling-noise floor across all six per-label accuracy terms, with no labels -- including a persona's genuinely poor bullish accuracy of 0.57, recovered as 0.59. The other model collapsed at least one persona into a constant classifier (a judge that voted one way on all 64 scenarios), which makes the error-independent algebra unsolvable. The central, non-obvious result: inter-judge disagreement does not imply evaluability. Aggregate disagreement separated this run only because the unevaluable model(s) collapsed to 0.00; the five evaluable models spanned 0.03–0.23. What gates evaluation is a per-judge condition — every judge must vary (and answer) — not an ensemble one. We formalize this as a label-free evaluability diagnostic (a judge whose modal-vote fraction reaches 1.0 is a constant classifier; an unparseable vote is an abstention) that predicted exactly which models would be evaluable, before any solve and without ground truth. This is a concrete instance of the safety property the NTQR logic promises: it warns you when an ensemble is not good enough to be evaluated. A scenario bootstrap puts a 95% CI of [0.000, 0.038] on the recovery MAE (well inside the 0.102 noise floor), and a deterministic synthetic study generalizes the recovery beyond the finite set of real evaluable models — error falls like 1/√Q (slope -0.58, stable across ensembles) — while mapping two honest limits: the built-in failure alarm catches anti-correlated judges with no false positives yet can miss positively-correlated (shared-training) errors, and the two-solution tie-break inverts once judges are no longer clearly better than random — exactly where simple majority-voting evaluation, though biased, is the more robust fallback. --- Associated artifacts GitHub release: v1.0.0 (https://github.com/docxology/ntqr_llm/releases/tag/v1.0.0) DOI: https://doi.org/10.5281/zenodo.20498699 Zenodo: https://zenodo.org/records/20498699 PDF SHA-256: e1196698427f9fe04d1f3071705adb6e5459983649c78d7f5d074756e989148b
", "keywords": [ "algebraic evaluation", "NTQR", "unsupervised evaluation", "evaluation on unlabeled data", "LLM-as-judge", "error-independent evaluation", "ensemble evaluability", "constant classifier", "AI safety warning light", "reproducible research", "answer-key-free recovery", "local large language models" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/ntqr_llm/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/ntqr_llm", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "c55cfa2e-cb78-4282-86d6-1c816a417b4c", "key": "Friedman_2026_Recovering_e1196698.pdf", "size": 2270020, "checksum": "md5:585821d541c33c086dcb3ab988d19b5b", "links": { "self": "https://zenodo.org/api/records/20498700/files/Friedman_2026_Recovering_e1196698.pdf/content" } } ], "html_url": "https://zenodo.org/records/20498700", "doi_url": "https://doi.org/10.5281/zenodo.20498699", "record_url": "https://zenodo.org/records/20498699" }, { "record_id": "20482026", "doi": "10.5281/zenodo.20482025", "title": "The Music Never Stopped: A Grateful Data Compendium with a Category-Theoretic Interpretation", "publication_date": "2026-05-31", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": null, "orcid": "0000-0001-6232-9096" } ], "description": "We present a modular, citation-bound data compendium for the Grateful Dead universe — shows, songs, performances, personnel timelines, venues, recordings, and reception — and a category-theoretic interpretation of the performance graph. The work is grounded in the archival reality that Grateful Dead history is both institutional and participatory: UCSC's Grateful Dead Archive and the Internet Archive collection preserve formal and community records , while taping and trading scholarship shows why setlists and recording metadata are cultural evidence, not merely fan trivia . The surrounding source dossier also binds the non-quantitative historical frame -- formation and Acid Test context, Wall of Sound engineering, live recording/liveness scholarship, Deadhead sociology, studio-era reception, and public recognition -- to checked sources rather than to folklore alone . The compendium integrates nine primary sources (Setlist.fm , The SetList Program , the Mark Leone CMU setlist archive , GDsets , gdshowsdb , the Internet Archive Live Music Archive , the Alex Allan / whitegum lyric finder , the official band site , and Wikipedia ) with four reference sources (Britannica , the lineup-changes guide , Dodd and Trist's The Complete Annotated Grateful Dead Lyrics , and the Grateful Stats front-end ) and secondary corpora and community discussions . Each source is parsed by an independently testable reference module written against the documented record shape; the committed compendium under `data/archival/` is the dataset reported here (3341 ingested shows (gdshowsdb + truckin gap-fill; community literature estimates ~2318 canonical concerts), 645 songs, 912 venues, 40757 performance rows). A runtime completeness audit and figure-validation gate certify referential integrity and non-degenerate outputs on every pipeline run. Integration is a deterministic, sort-keyed merge over canonical slugs; registered figures also emit CSV/JSON data tables, and a first-principles claim ledger classifies each major result by irreducible input, hard constraint, assumption, validation artifact, and interpretation limit. Exploratory repertoire/uncertainty panels are labelled as pattern-discovery rather than causal inference. We then exhibit four small but real categorical constructions, situated against transformational and categorical music-theory precedents : a poset category of dates, a discrete category of shows, a monotone cumulative setlist functor and lineup functor from dates into sets, and a span representation that takes each performance to be the apex of a span between its show and its song. Wide pullbacks over a fixed show recover the show's setlist; wide pullbacks over a fixed song recover the song's performance history. The active-band roster, by contrast, is a non-monotone presheaf on the date poset — a categorical formalization of the familiar fact that members come and go. The artefacts in this paper come from the committed archival snapshot; all source-ingestion modules are written against the real source shape so that `scripts/00_fetch_sources.py --online --write-archival` refreshes the full snapshot. --- Associated artifacts GitHub release: The Music Never Stopped: A Grateful Data Compendium (v1.0.0) (https://github.com/docxology/grateful_data/releases/tag/v1.0.0) PDF SHA-256: 2d42bfd04e0b32e4871d5bcbe2c65bcce58cca336da240af7c6fd03a6563a709
", "keywords": [ "grateful dead", "setlist data", "category theory", "music information retrieval", "reproducible data compendium" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/grateful_data/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "f2aca743-b03e-48bc-a7e5-c35c3f6e01ac", "key": "Friedman_2026_Music_2d42bfd0.pdf", "size": 4142162, "checksum": "md5:96405bdf54e264921945820352d25ef9", "links": { "self": "https://zenodo.org/api/records/20482026/files/Friedman_2026_Music_2d42bfd0.pdf/content" } } ], "html_url": "https://zenodo.org/records/20482026", "doi_url": "https://doi.org/10.5281/zenodo.20482025", "record_url": "https://zenodo.org/records/20482025" }, { "record_id": "20450970", "doi": "10.5281/zenodo.20450880", "title": "When do bugs see (infra)red?", "publication_date": "2026-05-29", "version": "1.0.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Tucker Chambers", "affiliation": "Independent Researcher", "orcid": "0009-0008-3793-7872" }, { "name": "Daniel A. Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Objective: To review the plausibility of insect detection of infrared (IR) cues that covary with semiochemical vibrational signatures, and to produce falsifiable predictions through the integration of comparative entomology, spectroscopy, neural timing analysis, and computational electromagnetism. The vibrational theory remains contested, so the framework treats IR/vibrational sensing as a testable complement to molecular recognition rather than a replacement for receptor binding . Methods: We integrate: (i) literature-grounded morphometric ranges for antennal sensilla, (ii) ATR-FTIR evidence that insect body chemistry can support species discrimination, (iii) published olfactory receptor neuron timing constraints, and (iv) deterministic electromagnetic models that expose their assumptions and parameter sensitivity . Preregistered experimental protocols specify QCL/LED bands (2--25 µm), thermal matched controls, power density 0.1--2 mW/cm², and N≥50 per condition. All analyses use fixed random seeds (42) where stochastic routines are present. Results: The computational figures show where sensillum-scale dimensions, CHC-associated mid-IR bands, and atmospheric windows overlap, but they do not by themselves establish biological IR olfaction. The strongest empirical anchors are narrower: fast insect ORN first-spike timing, photomechanic IR organs in pyrophilous beetles, hematophagy IR cues in mosquitoes and kissing bugs, thermogenic pollination signals in cycads, thermosensitive coeloconic sensilla in ants, and passive cuticle IR optics . These sources motivate specific experiments while also constraining the manuscript's range and mechanism claims. Conclusions: The framework yields five preregistered falsifiers aligned with \\Cref{sec:discussion}: (1) spectral nulls under matched thermal load, (2) geometric mismatch between sensilla dimensions and predicted resonances, (3) environmental misalignment of CHC peaks with transmission windows, (4) temporal indistinguishability of IR versus thermal ORN latencies, and (5) behavioral independence of IR-only orientation from chemical gradients. Protocols specify QCL/LED bands (2--25 µm), matched power deposition, and N≥50 per condition to separate electromagnetic detection from thermal artifacts. Implications: Applications of this work include biomimetic IR sensor design, better-controlled pest-monitoring experiments, and clearer tests of whether insect olfactory systems ever use wavelength-specific electromagnetic information. Keywords: insect olfaction, infrared detection, vibrational theory, electromagnetic sensing, sensilla morphology, cuticular hydrocarbons, atmospheric transmission, biomimetic sensors Reproducibility: Complete implementation with seven case studies in Appendices --- Associated artifacts GitHub release: v1.0.0 (https://github.com/docxology/cohereants/releases/tag/v1.0.0) PDF SHA-256: 36bd97a8ff522937390213a69abb40c8c87a06ab783457e62d7effef4762bac2
", "keywords": [ "insect olfaction", "infrared detection", "vibrational theory of olfaction", "semiochemicals", "sensilla morphology", "electromagnetic sensing", "active inference", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/cohereants/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/docxology/cohereants", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "e5ba3a07-3037-45d4-8f50-7deb6b5c23cd", "key": "cohereants_combined.pdf", "size": 13895561, "checksum": "md5:007e795277896fe215937107f69aae94", "links": { "self": "https://zenodo.org/api/records/20450970/files/cohereants_combined.pdf/content" } } ], "html_url": "https://zenodo.org/records/20450970", "doi_url": "https://doi.org/10.5281/zenodo.20450880", "record_url": "https://zenodo.org/records/20450880" }, { "record_id": "20420557", "doi": "10.5281/zenodo.20420556", "title": "BeeStack: An Evidence-Typed Scaffold for Whole-Colony Honeybee Simulation", "publication_date": "2026-05-27", "version": "1.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute; Atta Labs", "orcid": "0000-0001-6232-9096" }, { "name": "Chambers, Tucker Cahill", "affiliation": "Atta Labs", "orcid": "0009-0008-3793-7872" } ], "description": "BeeStack is an executable, evidence-typed research scaffold for whole-colony simulation of the Western honey bee (Apis mellifera), organized as five layers (Body, Brain, Mind, Swarm, Niche). It pairs FlyBody/MuJoCo body and small-scene swarm renders with curated empirical BeeBrain datasets and reduced deterministic kernels, keeping fidelity a declared per-module property: every quoted number is traceable from configuration to artifact to manuscript, gaps are catalogued rather than hidden, and the validation rate is a config-band self-test measure, not a biological-realism score. This 1.0 release accompanies the manuscript 'BeeStack: An Evidence-Typed Scaffold for Whole-Colony Honeybee Simulation' and includes the combined PDF and the full source archive. Source: https://github.com/docxology/BeeStack", "keywords": [ "honeybee", "Apis mellifera", "active inference", "simulation scaffold", "swarm intelligence", "niche construction", "FlyBody", "MuJoCo", "antennal lobe", "mushroom body", "central complex", "waggle dance", "BEEHAVE", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/BeeStack/tree/v1.0.0", "relation": "isSupplementTo", "scheme": "url" } ], "files": [ { "id": "e15c3fd6-5e05-4cd4-b00e-5d17a338bea8", "key": "BeeStack_combined.pdf", "size": 8059701, "checksum": "md5:e65a35f6c30491c49bc5b33c24ac031a", "links": { "self": "https://zenodo.org/api/records/20420557/files/BeeStack_combined.pdf/content" } }, { "id": "ba5c5e98-bdb8-4a1f-b20d-e0cd5dbe6545", "key": "BeeStack-1.0.0-source.tar.gz", "size": 605646, "checksum": "md5:eb170e5bda185e72cb1ca55144c63397", "links": { "self": "https://zenodo.org/api/records/20420557/files/BeeStack-1.0.0-source.tar.gz/content" } } ], "html_url": "https://zenodo.org/records/20420557", "doi_url": "https://doi.org/10.5281/zenodo.20420556", "record_url": "https://zenodo.org/records/20420556" }, { "record_id": "20419637", "doi": "10.5281/zenodo.20418904", "title": "Policy Entanglement in Active Inference: A Coupling-Parameter Deformation Framework for Multi-Stream Policy Posterior Distributions, Machine-Checked and Simulated with a Typed Float Boundary", "publication_date": "2026", "version": "1.0", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Active inference models often need to choose among several policy streams at once, for example streams tied to different effectors, sensory channels, agents, agents within a group, or planning horizons. Standard discrete active-inference implementations keep this manageable by treating those streams as independent, but that simplification removes the dependencies that make coordinated action possible. This manuscript introduces policy entanglement: a controlled deformation of the usual independent policy posterior by a scalar coupling strength and explicit compatibility and preference potentials. The construction preserves the finite active inference setting while making cross-stream dependence a first-class modeling object rather than an implicit artifact of the chosen factorization. The framework keeps a claim-strength ledger that distinguishes exact recoveries, parameterized embeddings, numerical witnesses, and structural analogies. Mean-field active inference is the exact independent case. Products of experts, copula variational inference, options, hierarchical and sophisticated inference, branching-time active inference, renormalization-style compression, and Markov-blanket multi-agent views are connected as special cases through their stated posterior-factorization maps. The central result is a free-energy decomposition that separates ordinary per-stream free energy, coupling preference terms, the coupling normalizer, and the information cost of leaving independence. The decomposition makes multi-information the explicit surcharge paid by a non-factorized policy posterior and shows how coupling strength, compatibility structure, and off-diagonal preference costs enter the same accounting identity. This result supplies the organizing principle for the rest of the paper. It supports an information-geometric reading of the coupled policy family as a path away from the mean-field submanifold, a projection identity that returns the coupled posterior to its independent marginals, a spectral and tensor-train view of dominant coordinated policy modes, a heterogeneous-ensemble coupling-tax bound, and a phase vocabulary for under-coupled, mixed, and highly concentrated policy posteriors. These interpretations are intentionally limited: the manuscript does not claim a neural, clinical, biological, or quantum implementation, and Markov-blanket and tensor-network language is used as scoped modeling analogy unless a specific theorem row or generated artifact supports a stronger statement. The main decomposition analytic identity is machine-checked in ℝ in the Mathlib-backed Lean layer with an axiom audit and negative controls. A separate stock-Lean boundary fragment remains Mathlib-free and exposes the theorem surface as typed contracts for the Python simulation layer and the manuscript registry, including witness-consuming rows where analytic payloads are deliberately supplied at the boundary. The executable numerical layer remains a Float pipeline, so a verified Float↔ℝ error bridge is still an explicitly open interface rather than an implied proof; conservative interval brackets on the K=2 decomposition sweep certify Float residuals within a widened high-precision envelope (output/reports/float_real_residual.json) without promoting the registry row to proved. The empirical companion uses pymdp and NumPy to sweep coupled policy ensembles, run short and long rollouts, check the projection identity to round-off precision, produce free-energy, entropy, total-correlation, action-distribution, robustness, and adversarial sidecars, and render figures from those artifacts. The manuscript, figures, theorem map, citation registry, notation glossary (§S6), bibliography, and PDF are regenerated from the same source-owned pipeline, so prose claims are tied to Lean sources, Python witnesses, output metadata, and validation gates rather than maintained by hand. All manuscript methods, tests, and documentation are available as open-source software at https://github.com/ActiveInferenceInstitute/policy_entanglement (DOI: https://doi.org/10.5281/zenodo.20419536). --- Associated artifacts GitHub release: v1.0.0 (https://github.com/ActiveInferenceInstitute/policy_entanglement/releases/tag/v1.0.0) DOI: https://doi.org/10.5281/zenodo.20418904 Zenodo: https://zenodo.org/records/20418904 PDF SHA-256: ae7cdd62929324101ead3eba8177199141b0089a9baf35558107149331666fde
", "keywords": [ "active inference", "free energy principle", "policy inference", "mean-field", "total correlation", "information geometry", "Schmidt rank", "tensor networks", "sophisticated inference", "Lean theorem proving", "machine-checked free-energy identity" ], "related_identifiers": [ { "identifier": "https://github.com/ActiveInferenceInstitute/policy_entanglement/releases/tag/v1.0.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" }, { "identifier": "https://github.com/ActiveInferenceInstitute/policy_entanglement", "relation": "references", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "29e47fff-3b1e-44e4-abaa-df4253c22b53", "key": "Friedman_2026_Policy_ae7cdd62.pdf", "size": 14419275, "checksum": "md5:62d2dac502218f1b97fdae489459e8d3", "links": { "self": "https://zenodo.org/api/records/20419637/files/Friedman_2026_Policy_ae7cdd62.pdf/content" } } ], "html_url": "https://zenodo.org/records/20419637", "doi_url": "https://doi.org/10.5281/zenodo.20418904", "record_url": "https://zenodo.org/records/20418904" }, { "record_id": "20286478", "doi": "10.5281/zenodo.20286477", "title": "Introduction to Biology: A Generative Approach", "publication_date": "2026-05-26", "version": "1.0.0", "resource_type": { "title": "Book", "type": "publication", "subtype": "book" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Introduction to Biology: A Generative Approach is an open biology textbook with forty-four chapters, ranging from systems science and chemical foundations through cells, metabolism, genetics, microbiology, physiology, evolution, and ecology. Organized as Unit 0 plus Units I–X, the text presents biology as an evidence-grounded discipline in which mechanisms, measurements, and simple models are developed together, so readers can move between narrative explanation and the quantitative constraints that shape biological claims. Five recurring themes—evolution, information, structure and function, systems and emergence, and the cell—provide orientation across scales and align with mainstream undergraduate biology competencies; Unit 0 adds an optional systems, historical, and philosophical lens without replacing the traditional molecular-to-ecological sequence.
\nWhere the curriculum is quantitative, corresponding computations live in tested code modules organized by domain (biochemistry, cell biology, genetics, physiology, ecology, evolution, microbiology, botany, and neuroscience), and many figures and process diagrams are generated programmatically rather than supplied as static artwork alone. The edition pairs each chapter with a paper-based laboratory activity and a question bank that progresses from recall to synthesis; model answers are visible in this instructor build. Primary literature is cited inline, glossary and curriculum-mapping appendices support course design, and the manuscript is maintained as a reproducible open-science artifact (source at https://github.com/docxology/biology_textbook ; archived at DOI 10.5281/zenodo.20286478). Text is released under Creative Commons Attribution 4.0; accompanying source code under Apache-2.0.
", "keywords": [ "Biology" ], "related_identifiers": [], "files": [ { "id": "1613dd2d-7e7b-43d8-8113-acf3f1932193", "key": "biology_textbook_v1_05-26-2026-compressed.pdf", "size": 11476276, "checksum": "md5:c0c8ef858487ab87d19e985bd363a6c9", "links": { "self": "https://zenodo.org/api/records/20286478/files/biology_textbook_v1_05-26-2026-compressed.pdf/content" } } ], "html_url": "https://zenodo.org/records/20286478", "doi_url": "https://doi.org/10.5281/zenodo.20286477", "record_url": "https://zenodo.org/records/20286477" }, { "record_id": "20286171", "doi": "10.5281/zenodo.20286170", "title": "Crescent City in Living Waves: Space, Time, People, and Minds on the Southern Cascadian Coast", "publication_date": "2026-05-19", "version": "1.0.0", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This rapid-publication essay reads Professor Jiang Xueqin’s contemporary YouTube commentary on artificial intelligence — particularly his framing of AI as religion, empire, hallucination machine, and consciousness capture — through the perceptual diagnostics William Blake developed across the 1790s and through the formal vocabulary of Active Inference. The triangulation does not aim to vindicate Jiang’s polemical lecture form, to translate Blake’s prophetic ontology into contemporary cognitive science, or to settle the contested status of the Free Energy Principle. It aims instead to identify the structural-functional convergence across three vocabularies that otherwise do not communicate: closure of the perceiving system around its own top-down expectations, the failure mode Blake names Newton’s Sleep, Jiang names consciousness capture and engagement-prime-directive, and Active Inference names pathological prior dominance and precision parasitism.
\nI have developed the Blake–Active Inference correspondence at length in two earlier papers (Zenodo records 18600041 and 18807971); the present essay does not restate that synthesis at length but extends it to Jiang’s specific diagnostic vocabulary. What is new here is the mapping of Jiang’s claims — the persuasion machine, the demand for clean data, the suppression of edge cases, the black box as oracle, the engagement prime directive — onto Blake’s Four Zoas and the factorized generative model of Active Inference. The mapping is intelligible as a rapid-publication response because Jiang’s lectures are the highest-profile contemporary statement of a longue-durée diagnosis of cognitive closure, and because the architecture being deployed at scale right now under the labels “AI” and “AGI” is the proximate subject of his concern and the proximate test of any architectural literacy we propose.
\nThe essay carries two explicit limits. The mapping of Blake’s “Newton’s Sleep” onto Active Inference’s pathological prior dominance is a functional analogy across incompatible metaphysics; Blake’s quarrel is ontological, the Active Inference critique is parameter-level. The Free Energy Principle is contested in the philosophical literature; I deploy it as a generative vocabulary, not as established science. Jiang’s lecture form is speculative commentary, not scholarship — I cite the technical literature alongside him for every load-bearing claim, and the conspiratorial material his corpus contains sits outside the methodological frame of this essay.
\nThis paper is, in form and function, an experiment in rapid AI-augmented scholarly publication with society-in-the- loop: a response drafted in the hours after its trigger — a YouTube lecture published earlier today that names William Blake explicitly — using contemporary AI infrastructure for research, drafting, formalization, and figure generation while keeping the author in the loop. It is not a finished argument; it is an attempt to see what becomes possible when publication latency between a cultural artifact and its scholarly response is collapsed from months to hours.
\nAll methods and code available at https://github.com/docxology/blake_jiang .
", "keywords": [], "related_identifiers": [], "files": [ { "id": "74526bc3-ae20-4bb1-a9d5-92c275eeaa07", "key": "blake_jiang_DAF_v1_05-12-2026.pdf", "size": 2476314, "checksum": "md5:9c05a8065573c1e52e5de411828557ef", "links": { "self": "https://zenodo.org/api/records/20144984/files/blake_jiang_DAF_v1_05-12-2026.pdf/content" } } ], "html_url": "https://zenodo.org/records/20144984", "doi_url": "https://doi.org/10.5281/zenodo.20144983", "record_url": "https://zenodo.org/records/20144983" }, { "record_id": "19897664", "doi": "10.5281/zenodo.19461933", "title": "A Living Meta-Analysis Architecture for Active Inference: Assertion Extraction, Nanopublications, and Hypothesis Scoring", "publication_date": "2026-04-30", "version": "v2", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Dietz, Joel", "affiliation": "Massachusetts Institute of Technology (MIT)" } ], "description": "No prior automated system tracks hypothesis-level evidence across the full Active Inference and Free Energy Principle (FEP) literature. Manual synthesis cannot keep pace with a field that has grown at a compound annual rate of 20.36% across 2005–2026, and the FEP’s theoretical generality has invited falsifiability critiques that only hypothesis-specific evidence profiling can address. Building on pioneering systematic manual annotation paired with ontology-based anal- ysis at the scale of hundreds of papers, we present a computational meta-analysis framework that automates and scales this approach. The pipeline retrieves literature from arXiv, Semantic Scholar, and OpenAlex, deduplicating 𝑁 = 819 papers via a canonical identifier hierarchy (DOI > arXiv ID > Semantic Scholar ID > OpenAlex ID). It classifies papers into a three-tier taxonomy spanning eight categories: A (Core Theory), B (Tools & Translation), and C (Application Domains). An LLM-powered extraction system then evaluates each abstract against eight core hypotheses, producing structured nanopublications—each encoding directionality, a confidence score, and natural-language reasoning—that populate an RDF-compatible knowledge graph scored by a citation-weighted evidence function. All extracted assertions are automatically generated and have not been manually validated; hypothesis scores should be considered preliminary.
\nThe resulting evidence landscape reveals a field where application domains (Domain C, 64.0%) collectively dominate the corpus, with tools development (Domain B, 20.8%)—including pymdp, RxInfer.jl, and interpretable alternatives such as Free Energy Projective Simulation—and core theory (Domain A, 15.2%) rounding out the taxonomy. Non-negative matrix factorization identifies 5 latent topics that cross-cut the keyword taxonomy, and citation network analysis exposes a sparse yet structured graph (2,176 intra-corpus edges out of 29,323 total outgoing references—only 7.4% reference resolution, reflecting the corpus’s specialised scope rather than the underlying citation density of any single paper) anchored by pronounced hub papers. Hypothesis scores cluster into three tiers: a broad consensus tier (score > 0.83) covering five hypotheses—H7 Morphogenesis, H2 AIF Optimality, H4 Predictive Coding, H6 Clinical Utility, and H5 Scalability; a near-consensus boundary (H8 Language AIF, score ≈+0.83); a moderate debate tier (H3 Markov Blanket Realism, ≈+0.78); and a diffuse tier (H1 FEP Universality, ≈+0.48) where a large neutral plurality reflects the principle’s broad invocation without explicit empirical test—though absolute score magnitudes are inflated by publication bias and linguistic asymmetry in academic writing, making relative rankings and temporal trajectories more reliable than point estimates. By demonstrating that automated LLM-driven assertion extraction—operating without human-validated ground truth—can generate scalable, queryable representations of scientific evidence, this work provides a reusable architecture for living literature reviews—continuously updated knowledge graphs that track hypothesis-level consensus across rapidly evolving fields.
\nAll code, results, and methods to reproduce this manuscript are open source at https://github.com/ActiveInferenceInstitute/act_inf_metaanalysis/ .
", "keywords": [], "related_identifiers": [], "files": [ { "id": "23351447-8f8b-4c6e-987a-803ac730ddc3", "key": "act_inf_metaanalysis_v2_04-30-2026.pdf", "size": 3137760, "checksum": "md5:b918dfa83ffe359f5c698e30d3c602b4", "links": { "self": "https://zenodo.org/api/records/19897664/files/act_inf_metaanalysis_v2_04-30-2026.pdf/content" } } ], "html_url": "https://zenodo.org/records/19897664", "doi_url": "https://doi.org/10.5281/zenodo.19461933", "record_url": "https://zenodo.org/records/19461933" }, { "record_id": "19335196", "doi": "10.5281/zenodo.19335195", "title": "The Golden Compass and the Lunar Flux: William Blake, Bimetallic Meta-stability, and the Architecture of Value", "publication_date": "2026-04-03", "version": "v1", "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "The interactive and living form of this document can be found here.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "82ccfae3-ecde-4396-9601-dbda53514597", "key": "Active_Inference_Institute_Dec-18-2025.pdf", "size": 5800551, "checksum": "md5:ded0c2e93748d2a65dd0e3297cdd4f61", "links": { "self": "https://zenodo.org/api/records/17982447/files/Active_Inference_Institute_Dec-18-2025.pdf/content" } } ], "html_url": "https://zenodo.org/records/17982447", "doi_url": "https://doi.org/10.5281/zenodo.14108991", "record_url": "https://zenodo.org/records/14108991" }, { "record_id": "17244387", "doi": "10.5281/zenodo.17244386", "title": "Markdown Decision Process: A Framework for Probabilistic Document Analysis and Optimization", "publication_date": "2025-10-02", "version": "0.1", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Biological development unfolds as a stochastic process characterized by continuous variation and discrete transitions, yet traditional analytical methods fail to capture this complexity, and we present EvoJump, a unified computational framework that models developmental trajectories as stochastic processes analyzed through cross-sectional laser plane views of phenotypic distributions. EvoJump integrates multiple stochastic process models including jump-diffusion, fractional Brownian motion, Cox-Ingersoll-Ross, and Lévy processes with advanced statistical methods including wavelet analysis, copula modeling, extreme value theory, and regime-switching detection, enabling analysis of developmental trajectories and evolutionary constraints, prediction of phenotypic outcomes with uncertainty quantification, and identification of developmental phase transitions and dependencies. Implemented in Python with comprehensive testing framework and extensive documentation, EvoJump bridges quantitative genetics and modern computational methods, enabling researchers to address fundamental questions about the mechanistic basis of phenotypic evolution across ontogeny, and the framework demonstrates robust performance with synthetic data validation and scales efficiently to large phenotyping datasets.
\nAll methods and the material for generating the paper are available in https://github.com/docxology/EvoJump
", "keywords": [], "related_identifiers": [], "files": [ { "id": "d49138a6-373a-4a07-9421-84afd972303b", "key": "EvoJump_DAF_9-30-2025.pdf", "size": 7410576, "checksum": "md5:9eadb8b2037f3ff9bb1d8eacf18d7663", "links": { "self": "https://zenodo.org/api/records/17229925/files/EvoJump_DAF_9-30-2025.pdf/content" } } ], "html_url": "https://zenodo.org/records/17229925", "doi_url": "https://doi.org/10.5281/zenodo.17229924", "record_url": "https://zenodo.org/records/17229924" }, { "record_id": "17243488", "doi": "10.5281/zenodo.17235137", "title": "Synthesis of Agent and Niche", "publication_date": "2025-10-01", "version": "v2", "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "We present a comprehensive computational complexity and energy analysis framework for the Ant Stack, an integrated biomimetic architecture for embodied artificial intelligence. Our investigation employs analytical models for contact dynamics physics, sparse spiking neural networks, and active inference to characterize complexity and energy consumption in real-time embodied systems operating at 100 Hz control frequencies.
\nEnergy efficiency has emerged as a critical constraint in embodied AI systems, yet traditional complexity analysis fails to capture the nuanced energy-performance trade-offs inherent in real-world implementations. The Ant Stack represents a biologically-inspired approach to embodied intelligence that requires systematic analysis of its computational and energetic characteristics to inform practical design decisions.
\nWe derive closed-form expressions for per-module time and space complexity in core computational loops, incorporating analytical scaling relationships from computational experiments. Our analysis bridges algorithmic complexity to detailed energy models that account for compute operations (FLOPs at 1.0 pJ each), memory hierarchy (SRAM at 0.10 pJ/byte, DRAM at 20.0 pJ/byte), neuromorphic spikes (1.0 aJ each), and physical actuation, enabling energy budgeting with bootstrap confidence intervals for uncertainty quantification.
\nOur analysis reveals three distinct computational regimes across the Ant Stack modules with profound design implications. The AntBody exhibits O(J + C^1.5) complexity dominated by contact resolution rather than joint dynamics, where the C^1.5 scaling of Projected Gauss-Seidel solvers creates computational bottlenecks beyond 20 active contacts. This demonstrates locomotion efficiency within robotic platform ranges (CoT ≈ 1.93), though 2-6× higher than biological ants (CoT 0.1-0.3).
\nThe AntBrain scales as O(K + ρN_KC + H) with biological sparsity patterns (ρ ≈ 0.02) that prevent combinatorial explosion, enabling sub-linear energy scaling as sensory dimensionality increases. This reveals the largest optimization potential (4.2 × 10^8× theoretical minimum) through neuromorphic hardware acceleration. The AntMind demonstrates O(B H_p) complexity through bounded rationality, but exponential policy tree growth creates super-linear energy scaling that limits planning horizons to H_p ≤ 15 for computational tractability.
\nOur work provides validated theoretical contributions to embodied AI complexity analysis, including an analytical complexity framework with solver-dependent contact dynamics analysis (PGS: O(C^1.5), LCP: O(C^3), MLCP: O(C^2.5)) incorporating biologically-motivated neural sparsity (ρ ≤ 0.02) and bounded rational active inference limits (H_p ≤ 15). We establish comprehensive energy modeling spanning FLOP-based computation, hierarchical memory access, neuromorphic spikes, and mechanical actuation, validated against Landauer limits (kT ln 2 ≈ 2.8 × 10^-21 J/bit) and thermodynamic efficiency bounds.
\nAdditional contributions include information-theoretic foundations connecting Shannon's channel capacity, Landauer's principle, and Carnot efficiency limits for embodied AI system design, with quantitative validation against biological benchmarks. We provide phase transition analysis identifying critical points in system behavior such as contact density transitions (C ≈ 20) and neural sparsity thresholds (ρ ≈ 0.02), with scaling regime classification. Our biological validation framework provides quantitative comparison with real ant energetics to establish efficiency targets and optimization potential. Finally, we present a reproducible analysis methodology featuring manifest-driven experiments with bootstrap confidence intervals (n ≥ 1000), deterministic seeding, automated figure generation, and cross-validation against established benchmarks.
\nOur work establishes design principles for energy-efficient insect-inspired embodied AI systems, providing analytical frameworks for mechanical actuation efficiency and neural processing optimization. These findings inform hardware-software co-design strategies and provide benchmarks for energy-constrained autonomous systems, with particular relevance for mobile robotics, autonomous vehicles, and distributed sensor networks. The framework bridges theoretical complexity analysis with practical energy considerations, offering a systematic approach to understanding and optimizing the computational and energetic trade-offs in biomimetic embodied intelligence.
\nAll methods to regenerate the analysis and render the publication are in https://github.com/docxology/ant_stack
", "keywords": [ "Ant" ], "related_identifiers": [ { "identifier": "10.5281/zenodo.16782756", "relation": "continues", "resource_type": "publication", "scheme": "doi" } ], "files": [ { "id": "d44bbf51-44b9-4185-a802-0dd8913bc634", "key": "Complexity-Energetics_AntStack_9-30-2025.pdf", "size": 2682615, "checksum": "md5:dddb1ba50bb08089b57d0f172d006186", "links": { "self": "https://zenodo.org/api/records/17238737/files/Complexity-Energetics_AntStack_9-30-2025.pdf/content" } } ], "html_url": "https://zenodo.org/records/17238737", "doi_url": "https://doi.org/10.5281/zenodo.17238736", "record_url": "https://zenodo.org/records/17238736" }, { "record_id": "17228946", "doi": "10.5281/zenodo.17228945", "title": "Adaptive Basic Income (AuBI): Integrating AI, Decentralized Infrastructure, and Active Inference for Next-Generation Economic Systems", "publication_date": "2025-09-29", "version": "0.1", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Die Schwarze Katze", "affiliation": null }, { "name": "Djuwidja, Andrew", "affiliation": null, "orcid": "0009-0006-9402-2412" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Slides for a session at \"Enduring Patterns, Emerging Futures: Celebrating Dr. Len Troncale\", an online event in September 2025 https://troncale.sched.com/ .
", "keywords": [], "related_identifiers": [], "files": [ { "id": "41020a13-a0ee-4a8a-a46d-af45d24ec7e8", "key": "Len-Troncale_DAF_9-17-2025.pdf", "size": 3636370, "checksum": "md5:281234ee45a793c2c9800f4c1a202cd6", "links": { "self": "https://zenodo.org/api/records/17138224/files/Len-Troncale_DAF_9-17-2025.pdf/content" } }, { "id": "47a602b2-4dcf-4ec7-b927-630664ff089b", "key": "Len-Troncale_DAF_9-17-2025.odp", "size": 20298044, "checksum": "md5:4edb38b4475b332a78156a817be2e0b8", "links": { "self": "https://zenodo.org/api/records/17138224/files/Len-Troncale_DAF_9-17-2025.odp/content" } }, { "id": "86c746f4-322f-473b-b516-b31d0bf04df9", "key": "Len-Troncale_DAF_9-17-2025.pptx", "size": 20422864, "checksum": "md5:84c37a0c8e8797ae9b81ff4dfcb3b1d0", "links": { "self": "https://zenodo.org/api/records/17138224/files/Len-Troncale_DAF_9-17-2025.pptx/content" } } ], "html_url": "https://zenodo.org/records/17138224", "doi_url": "https://doi.org/10.5281/zenodo.17138223", "record_url": "https://zenodo.org/records/17138223" }, { "record_id": "17114390", "doi": "10.5281/zenodo.17114389", "title": "Symergetics: Symbolic Synergetics for Rational Arithmetic, Geometric Pattern Discovery, and All-Integer Accounting", "publication_date": "2025-09-13", "version": "v1", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "We review a unified analytical framework for four dimensional (4D) modeling and Quadray coordinates, synthesizing geometric foundations, optimization on tetrahedral lattices, and information geometry. Building on R. Buckminster Fuller’s Synergetics and the Quadray coordinate system, with extensive reference to Kirby Urner’s computational implementations across multiple programming languages (see the comprehensive 4dsolutions ecosystem including Python, Rust, Clojure, and POV-Ray implementations), we review how integer lattice constraints yield integer volume quantization of tetrahedral simplexes, creating discrete “energy levels” that regularize optimization and enable integer-based optimization. We adapt standard methods (e.g., Nelder–Mead method) to the quadray lattice, define Fisher information in Quadray parameter space, and analyze optimization as geodesic motion on an information manifold via the natural gradient. We review three distinct 4D namespaces — Coxeter.4D (Euclidean E4), Einstein.4D (Minkowski spacetime), and Fuller.4D (synergetics/Quadrays) — develop analytical tools and equations, and survey extensions and applications across AI, active inference, cognitive security, and complex systems. The result is a cohesive, interpretable approach for robust, geometry-grounded computation in 4D. All source code for the manuscript is available at QuadMath https://github.com/docxology/QuadMath .
", "keywords": [], "related_identifiers": [], "files": [ { "id": "ffee238a-a678-47df-a9ed-b075818396ca", "key": "QuadMath_v1_DAF_08-16-2025.pdf", "size": 8528524, "checksum": "md5:1d79d0e7f6696dc7dcb311d642521cdc", "links": { "self": "https://zenodo.org/api/records/16887800/files/QuadMath_v1_DAF_08-16-2025.pdf/content" } } ], "html_url": "https://zenodo.org/records/16887800", "doi_url": "https://doi.org/10.5281/zenodo.16887799", "record_url": "https://zenodo.org/records/16887799" }, { "record_id": "16790555", "doi": "10.5281/zenodo.16790554", "title": "MDKV: A Multitrack Markdown Container for Structured, Portable Documents", "publication_date": "2025-08-10", "version": "1.0", "resource_type": { "title": "Other", "type": "other" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "ResNei — Research Neighbourhood – is an AI-augmented environment designed to transform how we discover, analyse, and connect ideas.
\nAt its core is the Research Discovery Engine, which constructs a living, responsive knowledge graph through the distillation of verified concepts and the dynamic linking of an evolving corpus of scientific knowledge. This graph is structured as a set of Conceptual Nexus Models (CNMs)—modular representations of connected ideas, designed to surface signals to support impactful inquiry and collaboration.
\nOur UX design moves away from conventional passive, attention-driven systems toward a dynamic, action-intention model that centres collaboration, responsiveness, and contextual insight. A world where research becomes not just efficient, but responsive, intuitive, and interconnected.
\nThis platform aims to scale research processes through the interplay of generalists and specialists. Our platform involves a graphical concept model, enabling specialists to engage with reliable evaluation of scientific output, while democratising the otherwise intractable web of knowledge for the generalist. The co-evolution of expert-lead early adoption with generalist participation drives insight and growth: where research thrives through their collaboration. Grounded in scientific protocols and social accountability, ResNei values reciprocity, interdependence, and access. Innovation here acknowledges its real-world costs—social, ecological, and temporal—and builds not just tools, but shared capacity for meaningful discovery.
\nProject Status: As of the second version of this publication in August 2025, this Solution Design Document outlines the foundational concepts, architecture, and guiding principles of ResNei. The project is currently in early development, with a set of working prototypes and a technical paper in preprint. This document supports the transition from conceptual design to implementation.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "25756811-c212-4dea-bb08-559c69456b6e", "key": "Resnei Solution Design Document v2.odt", "size": 1862512, "checksum": "md5:c1cd46ad2df0e414fa20bbcc8e961771", "links": { "self": "https://zenodo.org/api/records/16753709/files/Resnei%20Solution%20Design%20Document%20v2.odt/content" } }, { "id": "89846186-f984-478f-bfe9-11b89e3ab597", "key": "Resnei Solution Design Document v2.epub", "size": 1557132, "checksum": "md5:e17759573294ee1a25a165ba039b5be4", "links": { "self": "https://zenodo.org/api/records/16753709/files/Resnei%20Solution%20Design%20Document%20v2.epub/content" } }, { "id": "beccc31a-a5d6-4534-b29a-d7e738ebfab8", "key": "Resnei Solution Design Document v2.docx", "size": 3278785, "checksum": "md5:a45c39f077696e0dd62961c1de6d56d7", "links": { "self": "https://zenodo.org/api/records/16753709/files/Resnei%20Solution%20Design%20Document%20v2.docx/content" } }, { "id": "37d1e9eb-f32f-41b2-a694-3d621c06f34f", "key": "Resnei Solution Design Document v2.pdf", "size": 1842767, "checksum": "md5:5697eb8e79c1eee59bec4b2df05ef3ae", "links": { "self": "https://zenodo.org/api/records/16753709/files/Resnei%20Solution%20Design%20Document%20v2.pdf/content" } } ], "html_url": "https://zenodo.org/records/16753709", "doi_url": "https://doi.org/10.5281/zenodo.15389682", "record_url": "https://zenodo.org/records/15389682" }, { "record_id": "16740439", "doi": "10.5281/zenodo.16740438", "title": "On Cognitive Art & Science: Toward Wholeness From Both Sides", "publication_date": "2025-08-04", "version": "1.0", "resource_type": { "title": "Other", "type": "other" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Positioning cognitive science as the systematic study of intra-action and cognitive art as its reflexive twin, this paper traces a bidirectional trajectory toward systemic wholeness. Procedural craft (firstness) and conceptual articulation (secondness) co-evolve into adaptive intelligence (thirdness), as continuously audited by the observing niche that embeds, measures, and reinterprets those intelligences (fourthness). This four-fold schema maps onto concrete information architectures: from insect bodies, to cryptographically verifiable plain texts, on through variational Bayesian simulations approached from the Low Road of Active Inference. Alternating 2→3 analytical moves which compress past data into predictive structure, with 4→3 generative moves which open space for unknown futures – these systems are capable of balancing exploitation with exploration, measurement with meaning, and optimization with open-ended creativity. True cognitive wholeness emerges when explanation and anticipation co-operate in sustained dialogue across scales.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "8688738b-9184-4752-a0b9-fb7043703788", "key": "On_Cognitive_Art_DAF_v1_8-4-2025.epub", "size": 1752804, "checksum": "md5:1f382c849f7ae0387ac4499492357fbd", "links": { "self": "https://zenodo.org/api/records/16740439/files/On_Cognitive_Art_DAF_v1_8-4-2025.epub/content" } }, { "id": "8dd32561-0ecf-4a97-9033-660b2b7db119", "key": "On_Cognitive_Art_DAF_v1_8-4-2025.pdf", "size": 658289, "checksum": "md5:dc08589c8735361fbdc8d5a73b4309d8", "links": { "self": "https://zenodo.org/api/records/16740439/files/On_Cognitive_Art_DAF_v1_8-4-2025.pdf/content" } }, { "id": "12fb9203-e5fa-49f5-9ee7-52456dde3c75", "key": "On_Cognitive_Art_DAF_v1_8-4-2025.rtf", "size": 10348690, "checksum": "md5:fb20fc9142a04b976c862cfc1edb65ca", "links": { "self": "https://zenodo.org/api/records/16740439/files/On_Cognitive_Art_DAF_v1_8-4-2025.rtf/content" } }, { "id": "89a0751a-90f2-4193-ab5d-a723e41c36ed", "key": "On_Cognitive_Art_DAF_v1_8-4-2025.odt", "size": 567772, "checksum": "md5:ccc3fdbf86d329a52d1792c2ce5af4a5", "links": { "self": "https://zenodo.org/api/records/16740439/files/On_Cognitive_Art_DAF_v1_8-4-2025.odt/content" } } ], "html_url": "https://zenodo.org/records/16740439", "doi_url": "https://doi.org/10.5281/zenodo.16740438", "record_url": "https://zenodo.org/records/16740438" }, { "record_id": "15231156", "doi": "10.5281/zenodo.15170907", "title": "CEREBRUM: Case-Enabled Reasoning Engine with Bayesian Representations for Unified Modeling", "publication_date": "2025-04-16", "version": "1.4", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This work explores the interplay between knowledge and wisdom as dynamic processes within the passage of time. Knowledge is framed as learning in time—sequentially accumulating observations—and learning from time, discerning causal patterns and tendencies. Wisdom, conversely, is presented as learning from time—metacognitive reflection on sequences of sequences—and learning in time, embracing the immediacy of perspective and timing. Together, these dualities form a tetralemma: a unified framework where knowledge and wisdom intersect across temporal dimensions. This relational synthesis invites a perspective shift between unity and plurality, situating human experience both within and beyond time. Ultimately, the inquiry seeks to honor the role of Eldership as a temporal guide, fostering recognition and empowerment for collective growth across generations.
\nThis letter was submitted to the Dana Frontiers program in January 2025, on behalf of the Active Inference Institute, in pursuit of funding several promising activities (generative playbooks for applying Active Inference, and a Summer School program). Though this application was not funded, we have uploaded it as an open source artefact here, seeking participation and resourcing for these and other projects, in due time, place, and fashion.
", "keywords": [ "Active Inference", "Education", "Application" ], "related_identifiers": [], "files": [ { "id": "5c1029af-4edc-493f-80fe-0f971ad16228", "key": "ActiveInferenceInstitute_PlaybooksAndSummerSchool_Mikhailova-Friedman.pdf", "size": 127944, "checksum": "md5:c98db6297035a3212189611bbd7d77f0", "links": { "self": "https://zenodo.org/api/records/15061667/files/ActiveInferenceInstitute_PlaybooksAndSummerSchool_Mikhailova-Friedman.pdf/content" } } ], "html_url": "https://zenodo.org/records/15061667", "doi_url": "https://doi.org/10.5281/zenodo.15061666", "record_url": "https://zenodo.org/records/15061666" }, { "record_id": "13999299", "doi": "10.5281/zenodo.13999298", "title": "MVEE: A Framework for Evolutionary Studies", "publication_date": "2018-01-18", "version": null, "resource_type": { "title": "Presentation", "type": "presentation" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Stanford University", "orcid": "0000-0001-6232-9096" } ], "description": "MVEE reflects where I was at in January 2018 (solo presentation) in thinking about Biology, Evolution, Active Inference, Free Energy Principle, and more.
\nUploaded to Zenodo in 2024.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "fa7cda30-11ea-4263-9529-810de5a08930", "key": "MVEE_2018.pdf", "size": 7041356, "checksum": "md5:1683d0ea71ae9b1fd22c1b40b2ad7d0d", "links": { "self": "https://zenodo.org/api/records/13999299/files/MVEE_2018.pdf/content" } }, { "id": "e3e34041-fede-4f02-aab5-f2eed9c09c1a", "key": "MVEE_2018.odp", "size": 24270168, "checksum": "md5:0c2ee7b2652db6f11f7445e449d9f10d", "links": { "self": "https://zenodo.org/api/records/13999299/files/MVEE_2018.odp/content" } }, { "id": "a5593045-6705-474f-9aa7-881dc67f2872", "key": "MVEE_2018.pptx", "size": 24184953, "checksum": "md5:1a8a7b6ddf9d354f6a153d195efcfbc5", "links": { "self": "https://zenodo.org/api/records/13999299/files/MVEE_2018.pptx/content" } } ], "html_url": "https://zenodo.org/records/13999299", "doi_url": "https://doi.org/10.5281/zenodo.13999298", "record_url": "https://zenodo.org/records/13999298" }, { "record_id": "13754586", "doi": "10.5281/zenodo.13754585", "title": "FarmWorks: Decentralized AI Agents for Personalized Solutions", "publication_date": "2024-09-12", "version": "1", "resource_type": { "title": "Other", "type": "other" }, "creators": [ { "name": "Baulin, Vladimir", "affiliation": "University Rovira i Virgili - Spain", "orcid": "0000-0003-2086-4271" }, { "name": "Vyatkin, Alex", "affiliation": "Active Inference Institute", "orcid": "0000-0003-1306-4620" }, { "name": "GUÉNIN—CARLUT, Avel", "affiliation": "University of Sussex", "orcid": "0000-0001-8239-7264" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Bolt, John", "affiliation": "Active Inference Institute", "orcid": "0009-0002-0878-5546" }, { "name": "Falkenstein, Stefan", "affiliation": "University of Michigan", "orcid": "0009-0008-5054-4969" }, { "name": "Jassal, Parishrut", "affiliation": "National Institute for Educational Planning and Administration, India", "orcid": "0009-0008-4351-805X" }, { "name": "Trois, Celio", "affiliation": "University Rovira i Virgili - Spain", "orcid": "0000-0002-7386-9749" }, { "name": "Minchin, Jonathan", "affiliation": "DeepSea Numerical", "orcid": "0000-0001-8152-1796" } ], "description": "Project description submitted as part of application to Future of Life Institute - How to mitigate AI-driven power concentration
\nInfinite Games for Infinite Teams was published by and in response to the DARPA
Polyplexus Citizen Incubator: “Inventing a Remote Culture to Deal with Pandemics”,
and was done so with the intent of discussing the questions outlined below.
This document aims to act as a scaffolding, displaying a tentative alignment of Active Inference terms with SUMO entities, in order to facilitate the anticipated process of rigorously mapping Active Inference to the SUMO formal ontology.
", "keywords": [ "Active Inference Ontology", "SUMO Ontology" ], "related_identifiers": [ { "identifier": "10.5281/zenodo.11055372", "relation": "isSupplementedBy", "resource_type": "publication-preprint", "scheme": "doi" } ], "files": [ { "id": "59a3aa39-6625-4a71-ae48-45a8f3287abe", "key": "Active Inference Topics Aligned to SUMO.xlsx", "size": 55474, "checksum": "md5:48a3239e1666ac55fcac125e79ff1521", "links": { "self": "https://zenodo.org/api/records/11463326/files/Active%20Inference%20Topics%20Aligned%20to%20SUMO.xlsx/content" } }, { "id": "5d5a0d77-1b03-49a5-b250-1e878f448240", "key": "Aligning Active Inference Ontology to SUMO.pdf", "size": 337848, "checksum": "md5:f9f3be4cfca4994f03249123f2404067", "links": { "self": "https://zenodo.org/api/records/11463326/files/Aligning%20Active%20Inference%20Ontology%20to%20SUMO.pdf/content" } } ], "html_url": "https://zenodo.org/records/11463326", "doi_url": "https://doi.org/10.5281/zenodo.11459322", "record_url": "https://zenodo.org/records/11459322" }, { "record_id": "10798145", "doi": "10.5281/zenodo.10798144", "title": "Four-fold Fields of Quantum Dreams", "publication_date": "2024-03-08", "version": "v1", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Tickles, Dean", "affiliation": "Active Inference Institute", "orcid": "0000-0003-2213-0773" } ], "description": "A very human consideration about taking perspectives on frameworks, told through an adventure playing out in a moment at a Quantum Baseball Spring Training gym.
", "keywords": [ "Active Inference", "Free Energy Principle", "Baseball" ], "related_identifiers": [], "files": [ { "id": "faf49d2d-e4aa-4bf8-9848-70b83ff6fdc7", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.epub", "size": 1089187, "checksum": "md5:9d6616ab95e7ff037062bfef808ae8f1", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.epub/content" } }, { "id": "2240f180-70f9-4965-a572-c9d549d5d3aa", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.pdf", "size": 1003135, "checksum": "md5:ad207a06a145b2c9bfd2922f35994f8b", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.pdf/content" } }, { "id": "f4ac2a43-819d-43cd-958b-89926e7d9b71", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.txt", "size": 15430, "checksum": "md5:8ff98d134bb96520c9e7b5f35d584d6b", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.txt/content" } }, { "id": "d57c6e98-10ab-4b8c-a797-066a8a5b7770", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.rtf", "size": 24034745, "checksum": "md5:b176dd7f1e5291a661c1a7c2bf72459b", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.rtf/content" } }, { "id": "021d2436-a4f3-48ec-81d3-1417525922d9", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.odt", "size": 1119204, "checksum": "md5:e4f9c976dbc30055d47ae22812fd14eb", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.odt/content" } }, { "id": "4092072a-250c-489c-bc5f-7995038bf46f", "key": "FourFoldFields _Friedman_Tickles_v1_3-8-2024.docx", "size": 1404132, "checksum": "md5:5ef92501917642cbfc06d4a49dfd7d5f", "links": { "self": "https://zenodo.org/api/records/10798145/files/FourFoldFields%20_Friedman_Tickles_v1_3-8-2024.docx/content" } } ], "html_url": "https://zenodo.org/records/10798145", "doi_url": "https://doi.org/10.5281/zenodo.10798144", "record_url": "https://zenodo.org/records/10798144" }, { "record_id": "10659375", "doi": "10.5281/zenodo.10659374", "title": "Push and Pull: A priming sequence", "publication_date": "2024-02-14", "version": "1.0", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "The primary objectives of this Push and Pull document are to explore the decoupling of cognitive (covert, attentional) and bodily (overt) behaviors , and to provide a sequence of hands-on computer exercises for further exploration .
\nThe priming sequence of exercises is presented to inform an individual’s understanding of how their attention interacts with computer use movements, such as controlling the on-screen cursor with mouse, touchpad, or eye movements.
\nWhat is presented here is only an initial sequence to complement other and future development of “hand-I” uncouplings, in principle and in practice.
\nAs we head through and past January 2024, I wondered if/that…
", "keywords": [ "Active Inference", "Dark Imaginarium", "Epistemic value", "Pragmatic value" ], "related_identifiers": [ { "identifier": "10.5281/zenodo.10038232", "relation": "isSupplementTo", "scheme": "doi" }, { "identifier": "10.5281/zenodo.8415313", "relation": "isSupplementedBy", "scheme": "doi" } ], "files": [ { "id": "e4182ce3-085e-4892-b143-66f88d6518a6", "key": "WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.pdf", "size": 97657, "checksum": "md5:fea617cd2e20d897d9ab7b26f16f7639", "links": { "self": "https://zenodo.org/api/records/10601082/files/WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.pdf/content" } }, { "id": "40a28752-4835-44f4-9191-5fdc8e6a9e8a", "key": "WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.rtf", "size": 689660, "checksum": "md5:28c7ffbdc62ff6723f3d8650398ff1cc", "links": { "self": "https://zenodo.org/api/records/10601082/files/WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.rtf/content" } }, { "id": "aa91ef9c-af6d-43b1-b414-9c6254884ff2", "key": "WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.docx", "size": 19135, "checksum": "md5:26cae82d7618555f6453af16d2032e79", "links": { "self": "https://zenodo.org/api/records/10601082/files/WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.docx/content" } }, { "id": "96f67987-8f69-4a15-ab4b-13fd197a5278", "key": "WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.epub", "size": 13773, "checksum": "md5:4256cba6f6d5cc0cc74f8d832b6f959f", "links": { "self": "https://zenodo.org/api/records/10601082/files/WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.epub/content" } }, { "id": "5f810fb1-8f46-4de8-820e-7db77caab4ef", "key": "WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.odt", "size": 24281, "checksum": "md5:099ce896aac6edb1a1d2f946da33aced", "links": { "self": "https://zenodo.org/api/records/10601082/files/WayFinding_InfiniteImaginarium_v1_DAF_1-31-2024.odt/content" } } ], "html_url": "https://zenodo.org/records/10601082", "doi_url": "https://doi.org/10.5281/zenodo.10601081", "record_url": "https://zenodo.org/records/10601081" }, { "record_id": "10447643", "doi": "10.5281/zenodo.10447642", "title": "Transcript of Chris Fields, \"Physics as Information Processing\" course in 2023", "publication_date": "2023-12-31", "version": "v1", "resource_type": { "title": "Lesson", "type": "lesson" }, "creators": [ { "name": "Fields, Chris", "affiliation": "Allen Discovery Center at Tufts University", "orcid": "0000-0002-4812-0744" }, { "name": "Aguirre, Ander", "affiliation": "Ohio State University", "orcid": "0000-0002-6337-8292" }, { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Balzan, Francesco", "affiliation": null }, { "name": "Berger, Ross", "affiliation": null }, { "name": "Draguta, David", "affiliation": "Independent", "orcid": "0009-0005-3179-9286" }, { "name": "Guénin-Carlut, Avel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-8239-7264" }, { "name": "Hurtado, Ana Magdelena", "affiliation": "Arizona State University", "orcid": "0000-0003-4064-1876" }, { "name": "Knight, V. Bleu", "affiliation": "Active Inference Institute", "orcid": "0000-0002-9894-1989" }, { "name": "Koles, Kate", "affiliation": null }, { "name": "Neophytou, Haris", "affiliation": "Interfusion Services", "orcid": "0009-0003-0921-737X" }, { "name": "Prior, Corby", "affiliation": null }, { "name": "Tickles, Dean", "affiliation": "Professional Initiatives Programming", "orcid": "0000-0003-2213-0773" }, { "name": "Tennant, Ian", "affiliation": "Anglia Ruskin University", "orcid": "0009-0003-2185-8620" }, { "name": "Tolchinsky, Alexey", "affiliation": "George Washington University" }, { "name": "Active Inference Institute", "affiliation": null } ], "description": "This resource is the transcript of the course \"Physics as Information Processing\" course, taught by Chris Fields in 2023 at the Active Inference Institute. There are 6 lectures, alternating with 6 discussions, for a total of 12 sessions.
\nThe PDF presented here is a lightly edited/improved version of an automated transcription, with added images.
\nThere may be inaccuracies in the transcription, please verify any quotations with the source materials. The most current version of the transcript can be found in the Active Inference Journal repository.
", "keywords": [ "Quantum", "Information", "Physics", "Active Inference", "Free Energy Principle" ], "related_identifiers": [], "files": [ { "id": "5d8716b4-25fd-466b-8ab5-5bbd1b45c499", "key": "ChrisFields_ActInfInst_Physics2023_AllTranscripts_v1.pdf", "size": 7272617, "checksum": "md5:b1666af222c350f7cd9736d6773f6947", "links": { "self": "https://zenodo.org/api/records/10447643/files/ChrisFields_ActInfInst_Physics2023_AllTranscripts_v1.pdf/content" } } ], "html_url": "https://zenodo.org/records/10447643", "doi_url": "https://doi.org/10.5281/zenodo.10447642", "record_url": "https://zenodo.org/records/10447642" }, { "record_id": "10400745", "doi": "10.5281/zenodo.10400744", "title": "A snapshot and pipeline for tissue-specific gene expression meta-analysis in honey bees (Apis mellifera)", "publication_date": "2023-12-18", "version": "v1.0", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "University of California, Davis, CA, USA", "orcid": "0000-0001-6232-9096" }, { "name": "Tong, Chao", "affiliation": "Arizona State University, Tempe, AZ, USA", "orcid": "0000-0001-5202-5507" }, { "name": "Linksvayer, Timothy A.", "affiliation": "Arizona State University, Tempe, AZ, USA", "orcid": "0000-0001-7034-1546" }, { "name": "Freund, Matthias", "affiliation": "University of Würzburg, Wurzburg, Germany", "orcid": "0000-0002-5683-6275" }, { "name": "Keough, Nicole Weronika", "affiliation": "University of California, Davis, CA, USA", "orcid": "0009-0002-1058-5105" }, { "name": "Johnson, Brian", "affiliation": "University of California, Davis, CA, USA", "orcid": "0000-0001-6390-7230" } ], "description": "The honey bee (Apis mellifera) is a pivotal species in both ecological and research contexts, serving as a model organism for studying complex social behavior and physiological processes. A critical aspect of understanding these complexities is the analysis of tissue-specific gene expression (TSGE), a challenging task due to the need to handle large bioinformatics data and manual tissue processing. In this study, we present a meta-analytic approach to investigate TSGE in A. mellifera, harnessing various open-source bioinformatics packages. From an initial pool of 4349 samples and 12,398 loci, our rigorous analysis resulted in a snapshot of 731 samples and 177 loci, representing high-quality estimates of TSGE patterns. This snapshot is publicly available, serving as a valuable resource for researchers interested in A. mellifera and beyond. Ongoing work will refine this analytical tool and expand its application to other species, thereby contributing to the broader understanding of gene expression patterns.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "f7ff1af3-fd00-442d-9c05-b6e34081e223", "key": "MetaInformAnt_Transcriptome_12-18-2023.zip", "size": 844673971, "checksum": "md5:2fa6cd9e41400f2351e2c66df7b506c1", "links": { "self": "https://zenodo.org/api/records/10400745/files/MetaInformAnt_Transcriptome_12-18-2023.zip/content" } }, { "id": "eb4133a0-fd42-44de-bded-a9aca8265e1d", "key": "Apis-seq_v1_12_18_2023.pdf", "size": 693355, "checksum": "md5:c0e9dff2a3931367c9331204f09cb02c", "links": { "self": "https://zenodo.org/api/records/10400745/files/Apis-seq_v1_12_18_2023.pdf/content" } }, { "id": "72db385c-41f1-433a-afc1-cee0d5af4004", "key": "Apis-seq_v1_12_18_2023.odt", "size": 620157, "checksum": "md5:64de898b411ed2befa7b1cd49d06ed46", "links": { "self": "https://zenodo.org/api/records/10400745/files/Apis-seq_v1_12_18_2023.odt/content" } }, { "id": "0c0946c0-9296-4b4f-8167-169e30b444a7", "key": "Apis-seq_v1_12_18_2023.docx", "size": 601243, "checksum": "md5:a44f3de9300bb4b62cb6f9c6c92816b5", "links": { "self": "https://zenodo.org/api/records/10400745/files/Apis-seq_v1_12_18_2023.docx/content" } } ], "html_url": "https://zenodo.org/records/10400745", "doi_url": "https://doi.org/10.5281/zenodo.10400744", "record_url": "https://zenodo.org/records/10400744" }, { "record_id": "10362561", "doi": "10.5281/zenodo.10296601", "title": "ATLAS: A Question Oriented Approach to the Use of Pattern Languages in Knowledge Management", "publication_date": "2023-12-07", "version": null, "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Cordes, R.J.", "affiliation": "COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "David, Scott", "affiliation": "Active Inference Institute" }, { "name": "Friedman, Daniel", "affiliation": "COGSEC", "orcid": "0000-0001-6232-9096" }, { "name": "Mikhailova, Alexandra", "affiliation": "University of California, Davis (UCD), Center for Neuroscience", "orcid": "0000-0002-8699-7125" }, { "name": "Penland, Andrew", "affiliation": "Eight Arms Nine Brains" }, { "name": "Young, Sam", "affiliation": null }, { "name": "Zacharias, Colten", "affiliation": "COGSEC" } ], "description": "The ATLAS system, evolving since the late 1990s, stands as a dynamic and comprehensive knowledge management tool that intends to address the complexities of modern information supply chains. The antecedent to ATLAS was the Atlas of Risk, an informal assemblage of various risks associated with digital interactions. Here we provide an initial specification for digital prototypes and paper-and-pencil implementations of a matured ATLAS architecture which integrates pattern language approaches with question-oriented procedures to manage and interpret meaning and context. The ATLAS system facilitates the management and communication of nuanced data sets and knowledge bases with an eye towards interoperability without the need for fully shared standards. The development of ATLAS, driven by the need for enhanced data interoperability and shared understanding in an increasingly complex and volatile digital landscape, reflects a profound, community response to the challenges of information environments and the fragility of extreme specialization. ATLAS's ongoing evolution showcases its adaptability and significance in the realms of data analysis, knowledge management, and cognitive security, and this first release of a technical specification establishes a foundation for a transition from prototype to scale-appropriate implementation.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "828daba9-20f7-4509-b43b-2803f0575b07", "key": "ATLAS_V-1-2.pdf", "size": 1692619, "checksum": "md5:77196b6212ba2466961e17bb2ee5e8c9", "links": { "self": "https://zenodo.org/api/records/10362561/files/ATLAS_V-1-2.pdf/content" } } ], "html_url": "https://zenodo.org/records/10362561", "doi_url": "https://doi.org/10.5281/zenodo.10296601", "record_url": "https://zenodo.org/records/10296601" }, { "record_id": "10160657", "doi": "10.5281/zenodo.10160656", "title": "Enhanced NSF Postdoctoral Reporting via Synthetic Intelligence Language Processing", "publication_date": "2023-11-20", "version": "v1", "resource_type": { "title": "Report", "type": "publication", "subtype": "report" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This report presents an approach for enhancing postdoctoral reporting at the National Science Foundation (NSF) using generative intelligence systems. The proposed system integrates updatable profiles, intelligent processing prompts, and a dynamic reporting system to transform how postdocs report their research progress and collaborations. The system's design focuses on operational efficiency, real-time evaluation, and a consistent reporting framework. Implementation strategies include a user-centric interface, robust cyber/cognitive security measures, and adaptive evolution. The goal is to streamline postdoctoral reporting, reduce administrative burdens, and enable more effective monitoring and support of postdoctoral research activities.
", "keywords": [], "related_identifiers": [], "files": [ { "id": "9835f120-3248-41b5-a44e-57f49eb34f12", "key": "Enhanced NSF Postdoctoral Reporting via Synthetic Intelligence Language Processing.docx", "size": 8262, "checksum": "md5:f2fff1eecdb01a292a956eb0d9c7b766", "links": { "self": "https://zenodo.org/api/records/10160657/files/Enhanced%20NSF%20Postdoctoral%20Reporting%20via%20Synthetic%20Intelligence%20Language%20Processing.docx/content" } }, { "id": "0c2bd15b-92f1-49ca-926f-a66a93435df8", "key": "Enhanced NSF Postdoctoral Reporting via Synthetic Intelligence Language Processing.odt", "size": 18066, "checksum": "md5:61f0560904687b3c44c40c5c73833dc5", "links": { "self": "https://zenodo.org/api/records/10160657/files/Enhanced%20NSF%20Postdoctoral%20Reporting%20via%20Synthetic%20Intelligence%20Language%20Processing.odt/content" } }, { "id": "f9c168ed-41b0-4f42-9f02-e00bea27ac57", "key": "Enhanced NSF Postdoctoral Reporting via Synthetic Intelligence Language Processing (1).pdf", "size": 52432, "checksum": "md5:aa1b7461cfab3f3e990397f5a8341b03", "links": { "self": "https://zenodo.org/api/records/10160657/files/Enhanced%20NSF%20Postdoctoral%20Reporting%20via%20Synthetic%20Intelligence%20Language%20Processing%20(1).pdf/content" } } ], "html_url": "https://zenodo.org/records/10160657", "doi_url": "https://doi.org/10.5281/zenodo.10160656", "record_url": "https://zenodo.org/records/10160656" }, { "record_id": "10038232", "doi": "10.5281/zenodo.10038231", "title": "Cognitive Sovereignty & Active Inference in the State of Exception", "publication_date": "2023-10-24", "version": "v1.1", "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "This paper provides an analysis of Giorgio Agamben's book Homo Sacer in the tradition of Active Inference. Homo Sacer articulates the relationship between bare life and political existence in Western politics and metaphysics. Agamben argues that politics is founded on the inclusive exclusion of bare life, where natural biological life – the physiology and cognition of the body – is politicized only through its exclusion as an exception. Drawing on Aristotle's definition of man as a political animal, Agamben traces the historical development of this structure and its continuation in modern biopolitics.
Here we develop the above concepts in the setting of cognitive sovereignty and connect Agamben's framing of the political state of exception with Thomas Kuhn's theory of revolutionary science. We assert that realized epistemic agency is grounded in the enacted policy selection of the cognitive sovereign. A given paradigmatic framework, whether in the normal political or normal scientific setting, establishes what counts as valid knowledge and action. Such normative establishments periodically enter crises, which are exited by cognitive and material restructuring downstream of the sovereign's cognitive agency (an agent's cognitive sovereignty).
The paper explores how Active Inference, a theoretical framework for scientific inference, can enhance our understanding of sovereignty, agency, and the state of exception. As an introductory offering into this space, several concordances are drawn between Active Inference and Homo Sacer. Specifically: the state of exception is discussed in terms of affordances, bare life is discussed in terms of variational free energy, and sovereign agency is discussed in terms of expected free energy. Pseudocode of an \"Active Stateference\" entity is provided.
Overall, this paper offers an initial accounting of Homo Sacer from the Active Inference perspective, and sketches some salient directions for understanding the dynamics of power, knowledge, and sovereignty in politics and science.
", "keywords": [ "Active Inference", "Homo Sacer", "Biopolitics" ], "related_identifiers": [], "files": [ { "id": "3b5d21a5-3eb3-4bb4-bffe-eb316a13799f", "key": "CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.pdf", "size": 220677, "checksum": "md5:86f95057979f019836f5358cd411cdab", "links": { "self": "https://zenodo.org/api/records/10038232/files/CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.pdf/content" } }, { "id": "cd276567-70b9-40a7-9621-72f0057a9f7d", "key": "CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.epub", "size": 25967, "checksum": "md5:b940ca21e8aae7a6d2f5723309a103ab", "links": { "self": "https://zenodo.org/api/records/10038232/files/CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.epub/content" } }, { "id": "5bd27786-5b19-4b80-b9a6-f941c44e0f3a", "key": "CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.docx", "size": 33090, "checksum": "md5:29e9f336881d6f1066db93177694c5fe", "links": { "self": "https://zenodo.org/api/records/10038232/files/CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.docx/content" } }, { "id": "8c489dd0-7fc6-4434-95c5-945e07481f90", "key": "CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.odt", "size": 37815, "checksum": "md5:418bc636eececb178ed3908156968bc8", "links": { "self": "https://zenodo.org/api/records/10038232/files/CognitiveSovereignty_ActiveInference_StateOf_Exception_v1-1.odt/content" } } ], "html_url": "https://zenodo.org/records/10038232", "doi_url": "https://doi.org/10.5281/zenodo.10038231", "record_url": "https://zenodo.org/records/10038231" }, { "record_id": "10034512", "doi": "10.5281/zenodo.10034511", "title": "The Properties, Processes, and Perspectives Inter-Framework (P3IF): Multiplexing interdisciplinary requirements frameworks to manage information risk and foster cognitive security", "publication_date": "2023-10-23", "version": null, "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Wilkinson, Thomas M.", "affiliation": "Office of Health Security, U.S. Department of Homeland Security", "orcid": "0009-0005-1149-7723" }, { "name": "Cordes, RJ", "affiliation": "COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "David, Scott", "affiliation": "Information Risk and Synthetic Intelligence Research Initiative (IRSIRI), University of Washington, Applied Physics Laboratory", "orcid": "0000-0003-0679-3286" }, { "name": "Friedman, Daniel Ari", "affiliation": "COGSEC", "orcid": "0000-0001-6232-9096" } ], "description": "Requirements engineering frameworks have historically been developed in the context of cybersecurity and have tended to focus almost exclusively on the technical and operational aspects of data security. Now, however, frameworks are being stretched to support interdisciplinary and multiorganizational information systems, requirements, and risks, securing downstream processes such as data analytics and balancing cross-domain priorities and perspectives. In this paper, we (i) explore the purpose of frameworks and their function in facilitating requirements engineering in information systems, (ii) perform an analysis of the relationships and lineages of common frameworks in professional use today, and (iii) propose the Properties, Processes, and Perspectives Inter-Framework (P3IF). P3IF enables flexible requirements engineering for complex information systems by providing a modular abstraction layer between existing frameworks, extending their value without replacing them. Factors from frameworks used across disparate domains are multiplexed to harmonize vocabularies and narratives across different organizations and needs, to create new approaches to managing information risk, and to enhance the cognitive security of decisions-makers by expanding security considerations beyond cybersecurity to include the entire information pipeline from sourcing to semantics.
", "keywords": [ "Requirements Engineering", "Cybersecurity", "Cognitive Security", "Health Security", "Evidence-Based Decisionmaking", "Interoperability", "Frameworks", "Risk Management", "Knowledge Management", "Information Management" ], "related_identifiers": [], "files": [ { "id": "cf8afa12-9118-4d4c-8817-19c9e8fc0d30", "key": "TAAB-P3IF_v1_10.5281_zenodo.10034512.pdf", "size": 3426653, "checksum": "md5:9187080b069e2422cc0e6c22b3e44912", "links": { "self": "https://zenodo.org/api/records/10034512/files/TAAB-P3IF_v1_10.5281_zenodo.10034512.pdf/content" } } ], "html_url": "https://zenodo.org/records/10034512", "doi_url": "https://doi.org/10.5281/zenodo.10034511", "record_url": "https://zenodo.org/records/10034511" }, { "record_id": "8415313", "doi": "10.5281/zenodo.8415312", "title": "An Account of Active Inference Modeling", "publication_date": "2023-10-06", "version": "v1.0", "resource_type": { "title": "Report", "type": "publication", "subtype": "report" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute; COGSEC", "orcid": "0000-0001-6232-9096" } ], "description": "This report provides a single-page account of Active Inference modeling.
\n\nThis report was written entirely by hand without any synthetic computational-linguistic intelligences.
\n\nThank you to the learners, interns, and participants of the Active Inference Institute to whom I've mostly learned from.
", "keywords": [ "Active Inference" ], "related_identifiers": [], "files": [ { "id": "f4e5d275-529a-4f2f-9706-00b3ca9131c1", "key": "An Account of Active Inference Modeling v1.docx", "size": 9643, "checksum": "md5:493cb80630036a82dbfda4a3a74e199d", "links": { "self": "https://zenodo.org/api/records/8415313/files/An%20Account%20of%20Active%20Inference%20Modeling%20v1.docx/content" } }, { "id": "f72ae1e5-e12a-4d65-ad93-f96a9cb8ccaa", "key": "An Account of Active Inference Modeling v1.pdf", "size": 55132, "checksum": "md5:b5c3ec407bf06e4432cb6b196f0e19b4", "links": { "self": "https://zenodo.org/api/records/8415313/files/An%20Account%20of%20Active%20Inference%20Modeling%20v1.pdf/content" } } ], "html_url": "https://zenodo.org/records/8415313", "doi_url": "https://doi.org/10.5281/zenodo.8415312", "record_url": "https://zenodo.org/records/8415312" }, { "record_id": "8377988", "doi": "10.5281/zenodo.8377987", "title": "Postdoc review (2020-2023) ~ September 25, 2023", "publication_date": "2023-09-25", "version": "v1.0", "resource_type": { "title": "Presentation", "type": "presentation" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute; COGSEC; University of California, Davis", "orcid": "0000-0001-6232-9096" } ], "description": "This presentation reviews the 3-year NSF postdoctoral fellowship of Daniel Ari Friedman (https://www.danielarifriedman.com/), from October 2020 to October 2023.
\n\nThis presentation will be livestreamed at 3pm PT on September 25, 2023, at the YouTube link: https://www.youtube.com/watch?v=RYwycyuaxoU
", "keywords": [ "Active Inference", "Cognitive Security", "Biology", "Entomology", "Biology" ], "related_identifiers": [], "files": [ { "id": "0492fecf-e595-4d96-ab79-58605fa8e125", "key": "DAF_Postdoc_Summary_9_25_2023.pptx", "size": 165935839, "checksum": "md5:7fa97d9f6ccab0eff995f62ad4e10ff9", "links": { "self": "https://zenodo.org/api/records/8377988/files/DAF_Postdoc_Summary_9_25_2023.pptx/content" } }, { "id": "f1462dfb-5e88-45a3-ba95-9523c998ce2e", "key": "DAF_Postdoc_Summary_9_25_2023.pdf", "size": 21941202, "checksum": "md5:174232f477d8a2bc98a7b67f50b0546f", "links": { "self": "https://zenodo.org/api/records/8377988/files/DAF_Postdoc_Summary_9_25_2023.pdf/content" } } ], "html_url": "https://zenodo.org/records/8377988", "doi_url": "https://doi.org/10.5281/zenodo.8377987", "record_url": "https://zenodo.org/records/8377987" }, { "record_id": "8266281", "doi": "10.5281/zenodo.8266280", "title": "The Active Inference Institute and Active Inference Ecosystem", "publication_date": "2023-08-19", "version": "001.1", "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "Active Inference Institute", "affiliation": "Active Inference Institute", "orcid": "0009-0008-7721-7407" }, { "name": "Aguirre, Ander", "affiliation": "Active Inference Institute, Ohio State University", "orcid": "0000-0002-6337-8292" }, { "name": "Boik, John", "affiliation": "Active Inference Institute", "orcid": "0000-0003-1289-7997" }, { "name": "Burian, Libor", "affiliation": "Active Inference Institute", "orcid": "0009-0007-6181-340X" }, { "name": "Brown, Matthew", "affiliation": "Active Inference Institute, ThoughtForge Inc.", "orcid": "0000-0002-7552-0989" }, { "name": "Cordes, RJ", "affiliation": "Active Inference Institute", "orcid": "0000-0002-9913-7159" }, { "name": "David, Scott", "affiliation": "Active Inference Institute, Information Risk and Synthetic Intelligence Research Initiative (IRSIRI), University of Washington - Applied Physics Laboratory.", "orcid": "0000-0003-0679-3286" }, { "name": "Douglass, David S", "affiliation": "Active Inference Institute", "orcid": "0000-0001-7894-8019" }, { "name": "Fernandez-Maquieira, Pablo", "affiliation": "Active Inference Institute, NFT-Crap" }, { "name": "Friedman, Daniel A", "affiliation": "Active Inference Institute, University of California (Davis)", "orcid": "0000-0001-6232-9096" }, { "name": "Grimm, Holly", "affiliation": "Active Inference Institute,", "orcid": "0009-0001-6181-2569" }, { "name": "Guénin–Carlut, Avel", "affiliation": "Active Inference Institute, Verses Lab, University of Sussex, Kairos Research", "orcid": "0000-0001-8239-7264" }, { "name": "Iennaco, Maria Luiza", "affiliation": "Active Inference Institute, University of São Paulo", "orcid": "0000-0002-5407-4852" }, { "name": "Knight, V Bleu", "affiliation": "Active Inference Institute", "orcid": "0000-0002-9894-1989" }, { "name": "Mikhailova, Alexandra", "affiliation": "Active Inference Institute, University of California (Davis)", "orcid": "0000-0002-8699-7125" }, { "name": "Rahmjoo, Ali", "affiliation": "Active Inference Institute", "orcid": "0000-0002-3244-7419" }, { "name": "Razi, Adeel", "affiliation": "Active Inference Institute, Turner Institute for Brain and Mental Health, Monash University, Australia 12. Wellcome Centre for Human NeuroImaging, University College London, CIFAR Azrieli Global Scholars program, CIFAR, Toronto, Canada", "orcid": "0000-0002-0779-9439" }, { "name": "Smékal, Jakub", "affiliation": "Active Inference Institute,", "orcid": "0000-0003-4989-4968" }, { "name": "Tamari, Ronen", "affiliation": "Active Inference Institute, Hebrew University of Jerusalem, Common SenseMakers", "orcid": "0000-0002-6049-591X" }, { "name": "Tickles, Dean", "affiliation": "Active Inference Institute,", "orcid": "0000-0003-2213-0773" }, { "name": "Vyatkin, Alex", "affiliation": "Active Inference Institute,", "orcid": "0000-0003-1306-4620" } ], "description": "This document briefly surveys the current state of the Active Inference Institute and Active Inference Ecosystem, and outlines our future directions. It will be versioned as a living representation (both cyclic and updating) of ecosystems both general and local, describing the past, present, and future actions of the Active Inference Institute.
", "keywords": [ "Active Inference", "Active Inference Ecosystem", "Active Inference Institute" ], "related_identifiers": [], "files": [ { "id": "f05311ac-11ba-46b7-83af-e64d895b71af", "key": "ActiveInference_Institute-Ecosystem_2023_v1-1.odt", "size": 631775, "checksum": "md5:38b260b291b4545a5ac07cb0ad2c217a", "links": { "self": "https://zenodo.org/api/records/8266281/files/ActiveInference_Institute-Ecosystem_2023_v1-1.odt/content" } }, { "id": "aac56cd8-9035-4893-913f-17706109a6a7", "key": "ActiveInference_Institute-Ecosystem_2023_v1-1.docx", "size": 1178338, "checksum": "md5:830baec6ca5d0530d5e9bc96198e0f6f", "links": { "self": "https://zenodo.org/api/records/8266281/files/ActiveInference_Institute-Ecosystem_2023_v1-1.docx/content" } }, { "id": "8111fa71-ea19-49bb-a392-b2c42f74bca1", "key": "ActiveInference_Institute-Ecosystem_2023_v1-1.pdf", "size": 939049, "checksum": "md5:8727f52a8c9456f102b6e23755cbe4fa", "links": { "self": "https://zenodo.org/api/records/8266281/files/ActiveInference_Institute-Ecosystem_2023_v1-1.pdf/content" } } ], "html_url": "https://zenodo.org/records/8266281", "doi_url": "https://doi.org/10.5281/zenodo.8266280", "record_url": "https://zenodo.org/records/8266280" }, { "record_id": "8229512", "doi": "10.5281/zenodo.8228934", "title": "Transcript of Active Inference GuestStream 049.1: \"Clickbait, consciousness science, and responsible journalism\"", "publication_date": "2023-07-26", "version": "v1.1", "resource_type": { "title": "Other", "type": "other" }, "creators": [ { "name": "Peters, Megan A. K.", "affiliation": "Department of Cognitive Sciences, University of California, Irvine", "orcid": "0000-0002-0248-0816" }, { "name": "Bradford, Nora", "affiliation": "Department of Cognitive Sciences, University of California, Irvine", "orcid": "0000-0001-8154-3784" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Transcript from livestream on July 25, 2023 at the Active Inference Institute.
\n\nYouTube watch link: https://www.youtube.com/watch?v=dUXfgzKHV1c
\n\nRepository with updated transcripts and accessory files: https://github.com/ActiveInferenceInstitute/ActiveInferenceJournal/tree/main/GuestStream/GuestStream_049
\n\nInformation on the Institute: https://www.activeinference.org/
", "keywords": [ "Consciousness", "Science", "Communication" ], "related_identifiers": [], "files": [ { "id": "e268ebda-340d-4bc7-8252-f6a03c9c6387", "key": "GuestStream_049-1_transcript.pdf", "size": 69428, "checksum": "md5:3ac050acd9e3c6a66ed0b6cf805ff93f", "links": { "self": "https://zenodo.org/api/records/8229512/files/GuestStream_049-1_transcript.pdf/content" } }, { "id": "73d26cf6-e4ca-4972-ab2d-deaa28159cb4", "key": "GuestStream_049-1_transcript.odt", "size": 54757, "checksum": "md5:38e6d0d97a5fedc99d93595fcc3e664d", "links": { "self": "https://zenodo.org/api/records/8229512/files/GuestStream_049-1_transcript.odt/content" } } ], "html_url": "https://zenodo.org/records/8229512", "doi_url": "https://doi.org/10.5281/zenodo.8228934", "record_url": "https://zenodo.org/records/8228934" }, { "record_id": "8164667", "doi": "10.5281/zenodo.8164666", "title": "Generative Research Teams: Active Inference Compositions For Research and Meta-Science", "publication_date": "2023-07-19", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" }, { "name": "Smékal, Jakub", "affiliation": "Active Inference Institute", "orcid": "0000-0003-4989-4968" } ], "description": "The Generative Research Team (GRT) is a synthesis of human, computational, and informational entities that employs Active Inference, systems engineering, and cognitive security to explore research topics. Roles within the GRT are modular and composable, allowing for flexible resource and attention allocation. The GRT can be designed to address various areas of concern such as Research, Peer Review, Funding, Communication, Cryptography, and more, using implementations that blend human and computational capacities. Tools like Active Blockference and cadCAD, along with Cognitive Security concepts like Narrative Information Management (NIM) and Verifiable Information Ecosystem (VIE), ensure situational awareness and reliability in research trajectories. Here we provide both a worked and a sketched example of a GRT with specific roles and functions. Through collaborative environments, innovation, resilient architectures, and meta-prompting, the GRT adapts to unexpected changes. Effective communication strategies facilitate wide dissemination of research findings. The primary novel contributions here include the exploration of augmented architectures, the integration of Active Inference as a cognitive kernel into GRTs with shared intelligence, and the application of cognitive models for enhanced research processes. Additionally lists of related work and tools are provided, reflecting some of the contemporary work in this space. In the future, advanced GRT will be able to navigate uncertain landscapes and produce impactful outcomes. Today we are using GRT to study Active Inference; tomorrow we will use Active Inference to study GRT.
\n\nAll code used is available at https://github.com/ActiveInferenceInstitute/ActiveBlockference/tree/main/GRTs
\n\nAn interactive Coda document hosts information related to GRT: https://coda.io/@active-inference-institute/generative-research-teams-grt/sketched-example-2
", "keywords": [ "Active Inference", "Generative Model", "Generative Research Team", "Cognitive Modeling", "Large Language Models", "Autonomous Agents", "Research Team", "Open Science", "Decentralized Science" ], "related_identifiers": [], "files": [ { "id": "f45934d7-9e7c-49dd-92c4-6f102f3955fd", "key": "GenerativeResearchTeams_7_19_2023.odt", "size": 192207, "checksum": "md5:3d47f1e749834b23958bfb480cb709df", "links": { "self": "https://zenodo.org/api/records/8164667/files/GenerativeResearchTeams_7_19_2023.odt/content" } }, { "id": "df84c433-8a08-4b6e-943f-dd8facbc1895", "key": "GenerativeResearchTeams_7_19_2023.docx", "size": 472330, "checksum": "md5:630d2efd1e1f3d8f73b9cd7402b11cc1", "links": { "self": "https://zenodo.org/api/records/8164667/files/GenerativeResearchTeams_7_19_2023.docx/content" } }, { "id": "0e93e4c5-00b7-4658-822d-aced53e74a86", "key": "GenerativeResearchTeams_7_19_2023.pdf", "size": 376476, "checksum": "md5:f3ce48cdea559a3cd7ebb8362dc35f41", "links": { "self": "https://zenodo.org/api/records/8164667/files/GenerativeResearchTeams_7_19_2023.pdf/content" } } ], "html_url": "https://zenodo.org/records/8164667", "doi_url": "https://doi.org/10.5281/zenodo.8164666", "record_url": "https://zenodo.org/records/8164666" }, { "record_id": "8118156", "doi": "10.5281/zenodo.8118155", "title": "Modern Nostr Index Card-based Knowledge Engineering", "publication_date": "2023-07-05", "version": "v1", "resource_type": { "title": "Other", "type": "other" }, "creators": [ { "name": "Claros, Andrew", "affiliation": "Complexity Adventures", "orcid": "0000-0002-7522-0548" }, { "name": "Friedman, Daniel", "affiliation": "Complexity Adventures", "orcid": "0000-0001-6232-9096" } ], "description": "Some concepts explored related to Knowledge Engineering, Nostr, Large Language Models, Complexity, and more.
", "keywords": [ "Nostr", "Complexity", "Large Language Model", "Knowledge Engineering" ], "related_identifiers": [], "files": [ { "id": "a4166d6a-639b-4b05-9e55-5ec9e33e04f2", "key": "Index_Card_7_5_2023.pdf", "size": 42755, "checksum": "md5:206da6aa987e5e8ebeb4aacf8771d1e0", "links": { "self": "https://zenodo.org/api/records/8118156/files/Index_Card_7_5_2023.pdf/content" } } ], "html_url": "https://zenodo.org/records/8118156", "doi_url": "https://doi.org/10.5281/zenodo.8118155", "record_url": "https://zenodo.org/records/8118155" }, { "record_id": "7855582", "doi": "10.5281/zenodo.7855581", "title": "Of Ants & Aging", "publication_date": "2023-04-22", "version": "v1", "resource_type": { "title": "Presentation", "type": "presentation" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Presentation given via remote appearAnts at "Curing Aging 2023", on April 22nd 2023 (https://www.curing-aging.com/).
", "keywords": [ "Ants", "Aging" ], "related_identifiers": [], "files": [ { "id": "84b0a19e-0d86-4aa9-92ac-1b2404720438", "key": "DAF_Ants_Aging_4_22_2023.pptx", "size": 35602043, "checksum": "md5:61f6447c5f2008fdaabd76743cf1c445", "links": { "self": "https://zenodo.org/api/records/7855582/files/DAF_Ants_Aging_4_22_2023.pptx/content" } }, { "id": "a003a236-c18f-4960-ad90-dbefe811e9ca", "key": "DAF_Ants_Aging_4_22_2023.pdf", "size": 6327601, "checksum": "md5:a627336bcd822a8b3030ef01ce01cb1e", "links": { "self": "https://zenodo.org/api/records/7855582/files/DAF_Ants_Aging_4_22_2023.pdf/content" } } ], "html_url": "https://zenodo.org/records/7855582", "doi_url": "https://doi.org/10.5281/zenodo.7855581", "record_url": "https://zenodo.org/records/7855581" }, { "record_id": "7838653", "doi": "10.5281/zenodo.7838652", "title": "Slides for Iris", "publication_date": "2023-04-17", "version": "1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Some initial slides from today.
\nFor context see: @speakerjohnash
This paper introduces Generalized Notation Notation (GNN), a novel approach to generative model representation that facilitates communication, understanding, and application of Active Inference across various domains. GNN complements the Active Inference Ontology as a flexible and expressive language for education and modeling, by providing a standardized method for describing cognitive models. In this paper we introduce GNN, and provide a Step-by-Step example of what GNN looks like in practice. We then explore "the Triple Play", a pragmatic approach to expressing GNN in linguistic, visual, and executable cognitive models. By situating GNN within the broader context of cognitive modeling and Active Inference, this work aims to bridge and respect the gaps among different modeling settings. The goal of this work is to facilitate interdisciplinary research and application, ultimately promoting the advancement of the field.
\n\nGithub: https://github.com/ActiveInferenceInstitute/GeneralizedNotationNotation
\nCoda: https://coda.io/@active-inference-institute/generalized-notation-notation
This document is a grant application to Protocol Labs, from Active Inference Institute (Active Blockference project).
\n\nThe grant was submitted in October 2022 and was not funded.
\n\nLearn more, get in touch, get involved, or fund us:
\n\nhttps://www.activeinference.org/
", "keywords": [ "Active Inference", "Hypercerts", "Active Blockference", "cadCAD", "Systems Engineering" ], "related_identifiers": [], "files": [ { "id": "840f0789-06ba-4772-9396-2568cbc8b4be", "key": "AII _ Blockference _ Protocol Labs Research RFP.pdf", "size": 76972, "checksum": "md5:399ec3dfa9ea6a3b90374c427cec3aca", "links": { "self": "https://zenodo.org/api/records/7626769/files/AII%20_%20Blockference%20_%20Protocol%20Labs%20Research%20RFP.pdf/content" } } ], "html_url": "https://zenodo.org/records/7626769", "doi_url": "https://doi.org/10.5281/zenodo.7626768", "record_url": "https://zenodo.org/records/7626768" }, { "record_id": "7519132", "doi": "10.5281/zenodo.7514367", "title": "William Blake & Buckminster Fuller: Lives in Juxtaposition (A study in Comprehensivity)", "publication_date": "2023-01-08", "version": "2", "resource_type": { "title": "Presentation", "type": "presentation" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "University of California (Davis), Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Slides for a presentation, initially for 52 Living Ideas on January 8th 2023 at 6pm PT.
\n\nThis is a work in progress, presented for educational and collaborative reasons.
\n\nWatch on YouTube: https://youtu.be/JGI0vx_aBdM
", "keywords": [ "William Blake", "Buckminster Fuller", "Comprehensivity" ], "related_identifiers": [], "files": [ { "id": "4f3c6560-7a77-4fbe-9d7b-a05009d85665", "key": "Blake-Fuller_Lives_in_Juxtaposition-DAF-2023.pptx", "size": 100694868, "checksum": "md5:be6baa8eabf8a0544e4bc99b2a6eedab", "links": { "self": "https://zenodo.org/api/records/7519132/files/Blake-Fuller_Lives_in_Juxtaposition-DAF-2023.pptx/content" } }, { "id": "6c799090-d0bf-4f96-9c93-60c47be2823a", "key": "FullerBlake_DAF_1_9_2023_Recording.mp4", "size": 377051147, "checksum": "md5:8cf77d3e3d7f339136dedf550d5e31cf", "links": { "self": "https://zenodo.org/api/records/7519132/files/FullerBlake_DAF_1_9_2023_Recording.mp4/content" } }, { "id": "56747505-03a7-4b31-bc4f-01158f871fce", "key": "Blake-Fuller_Lives_in_Juxtaposition-DAF-2023.pdf", "size": 16838192, "checksum": "md5:0c6516a8f92e53aff6ecdf830e7aa516", "links": { "self": "https://zenodo.org/api/records/7519132/files/Blake-Fuller_Lives_in_Juxtaposition-DAF-2023.pdf/content" } } ], "html_url": "https://zenodo.org/records/7519132", "doi_url": "https://doi.org/10.5281/zenodo.7514367", "record_url": "https://zenodo.org/records/7514367" }, { "record_id": "7484994", "doi": "10.5281/zenodo.6320574", "title": "An Active Inference Ontology for Decentralized Science: from Situated Sensemaking to the Epistemic Commons", "publication_date": "2022-12-26", "version": "3", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute, Complexity Weekend", "orcid": "0000-0001-6232-9096" }, { "name": "Applegate-Swanson, Shaun", "affiliation": "Active Inference Institute, Complexity Weekend", "orcid": "0000-0001-9474-6038" }, { "name": "Balbuena, Jessica Angeli", "affiliation": "Active Inference Institute, Complexity Weekend", "orcid": "0000-0003-2741-4476" }, { "name": "Choudhury, Arhan", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6897-2947" }, { "name": "Cordes, RJ", "affiliation": "Active Inference Institute, Complexity Weekend", "orcid": "0000-0002-9913-7159" }, { "name": "El Damaty, Shady", "affiliation": "OpSci", "orcid": "0000-0002-2318-4477" }, { "name": "Guénin—Carlut, Avel", "affiliation": "Active Inference Institute, Kairos Reseearch", "orcid": "0000-0001-8239-7264" }, { "name": "Knight, V. Bleu", "affiliation": "Active Inference Institute, Complexity Weekend", "orcid": "0000-0002-9894-1989" }, { "name": "Metelkin, Ivan", "affiliation": "Active Inference Institute", "orcid": "0000-0003-2899-6690" }, { "name": "Shrivastava, Siddhant", "affiliation": "Active Inference Institute, Complexity Weekend, Kernel", "orcid": "0000-0002-9688-4730" }, { "name": "Singh, Amit Kumar", "affiliation": "Active Inference Institute", "orcid": "0000-0002-8870-9676" }, { "name": "Smékal, Jakub", "affiliation": "Active Inference Institute, OpSci", "orcid": "0000-0003-4989-4968" }, { "name": "Tuttle. Caleb", "affiliation": "OpSci", "orcid": "0000-0002-8469-2221" }, { "name": "Vyatkin, Alexander", "affiliation": "Active Inference Institute", "orcid": "0000-0003-1306-4620" } ], "description": "In this work, we examine science from the vantage points of blockchain technology and its connection to decentralized science (DeSci). We consider science as a collective process using Active Inference, an integrative framework that models the cognitive processes of perception, planning, and action selection in terms of Bayesian probabilities and updating. We present the Active Entity Ontology for Science (AEOS, available at coda.io/@active-inference-institute/active-entity-ontology-for-science-aeos) as a composable and versionable system for modeling various science systems, using the Active Inference entity partitioning. Such DeSci systems are considered from the perspective of BOLTS (Business, Operations, Legal, Technical, Social). Further steps for developing and utilizing AEOS in the context of scientific ecosystems are provided.
", "keywords": [ "Active Inference", "Decentralized Science", "DeSci", "Science", "Ontology", "Sensemaking", "Epistemic Commons" ], "related_identifiers": [], "files": [ { "id": "eb7a6a91-c51f-41de-ab2a-43c314c143ac", "key": "v3_ActInf-DeSci-AEOS-2022.pdf", "size": 1034196, "checksum": "md5:3ac260088a1115736202e2b75d77ae54", "links": { "self": "https://zenodo.org/api/records/7484994/files/v3_ActInf-DeSci-AEOS-2022.pdf/content" } }, { "id": "60d91e72-5ac0-4336-bf54-f9385e5cf12a", "key": "v3_ActInf-DeSci-AEOS-2022.odt", "size": 836967, "checksum": "md5:b8718aeedbb578c300046987e9d474b9", "links": { "self": "https://zenodo.org/api/records/7484994/files/v3_ActInf-DeSci-AEOS-2022.odt/content" } } ], "html_url": "https://zenodo.org/records/7484994", "doi_url": "https://doi.org/10.5281/zenodo.6320574", "record_url": "https://zenodo.org/records/6320574" }, { "record_id": "7449368", "doi": "10.5281/zenodo.7449367", "title": "The Free Energy Principle & Active Inference: a Systematic Literature Analysis", "publication_date": "2022-12-16", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Knight, Virginia Bleu", "affiliation": "Active Inference Institute, New Mexico State University, Las Cruces NM. Department of Biology", "orcid": "0000-0002-9894-1989" }, { "name": "Cordes, RJ", "affiliation": "Cognitive Security and Education Forum (COGSEC), Active Inference Institute", "orcid": "0000-0002-9913-7159" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute, Cognitive Security and Education Forum (COGSEC), University of California, Davis. Department of Entomology & Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "Here we perform a literature analysis of publications in scientific literature using the term “Free Energy Principle” or “Active Inference”, with an emphasis on works written by Karl J Friston. For a subset of papers with accessible full texts, we performed manual annotation (related to structural, visual, and mathematical features) and automated analyses (related to the terms in the Active Inference Institute’s Active Inference Ontology). The initial analysis here, at the scale of thousands of citations and hundreds of annotated papers, is presented as a first step towards the development of systems which could:
\n\nEncompass increased scope of relevant works, including non-textual
\n\tIntegrate multiple forms of annotation and participation
\n\tFacilitate integration of manual and artificial contributions
\n\tFeature richer interfaces for use in learning & research
\n\tAddress field-specific local questions and provide transferable approaches
\n\tSpeak to broader questions in the history and philosophy of science
\n\tThis project is maintained by the Active Inference Institute.
\nThis project has an interactive Coda site and a Github repository.
This document is a call for participation in the initiative "Towards Active Diffusion: A Tale of Multiple (den)Cities" (2023-AD). The work will characterize mathematical formalisms and computational applications of Active Inference and Diffusion Models, and explore relevant applications.
", "keywords": [ "Active Inference", "Diffusion Model", "Catechism" ], "related_identifiers": [], "files": [ { "id": "248e8ae1-f81b-4eac-8080-bc5917007cb0", "key": "Active Diffusion Catechism.pdf", "size": 104247, "checksum": "md5:74caf35adab90a094ba644d530048fb1", "links": { "self": "https://zenodo.org/api/records/7443848/files/Active%20Diffusion%20Catechism.pdf/content" } } ], "html_url": "https://zenodo.org/records/7443848", "doi_url": "https://doi.org/10.5281/zenodo.7443847", "record_url": "https://zenodo.org/records/7443847" }, { "record_id": "7401875", "doi": "10.5281/zenodo.7401874", "title": "Transcript of discussions on: \"Communication as Socially Extended Active Inference: An Ecological Approach to Communicative Behavior\"", "publication_date": "2022-09-14", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Tison, Rémi", "affiliation": "Department of Philosophy, UQAM" }, { "name": "Tickles, Dean", "affiliation": "Active Inference Institute" }, { "name": "Knight, Bleu", "affiliation": "Active Inference Institute" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Discussion with an author of the 2021 paper “Communication as Socially Extended Active Inference: An Ecological Approach to Communicative Behavior” by Remi Tison & Pierre Poirier. https://www.tandfonline.com/doi/abs/10.1080/10407413.2021.1965480
\n\n\n\n
Session #048.0, September 2, 2022 https://www.youtube.com/watch?v=zqiZjjY9H7M
\n\nSession 048.1, September 7, 2022 https://www.youtube.com/watch?v=nWFM5zrdmG8
\n\nSession 048.1, September 7, 2022 https://www.youtube.com/watch?v=nWFM5zrdmG8
", "keywords": [], "related_identifiers": [], "files": [ { "id": "c0def277-06e5-481b-b238-b85288a63482", "key": "ActInf Livestream 048 ~ 'Communication as Socially Extended Active Inference'.odt", "size": 140338, "checksum": "md5:6aa364676b2b9e61d3e34ed3d71f2931", "links": { "self": "https://zenodo.org/api/records/7401875/files/ActInf%20Livestream%20048%20~%20'Communication%20as%20Socially%20Extended%20Active%20Inference'.odt/content" } } ], "html_url": "https://zenodo.org/records/7401875", "doi_url": "https://doi.org/10.5281/zenodo.7401874", "record_url": "https://zenodo.org/records/7401874" }, { "record_id": "7400786", "doi": "10.5281/zenodo.7400785", "title": "A Worked Example of the Bayesian Mechanics of Classical Objects", "publication_date": "2022-10-12", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Sakthivadivel, Dalton AR", "affiliation": "VERSES Research Lab, Los Angeles, CA, 90016, USA Department of Mathematics, Stony Brook University, Stony Brook, NY, USA Department of Physics and Astronomy, Stony Brook University, Stony Brook, NY, USA", "orcid": "0000-0002-7907-7611" }, { "name": "Rahmjoo, Ali", "affiliation": "Active Inference Institute" }, { "name": "Smékal, Jakub", "affiliation": "Active Inference Institute" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Transcripts of discussions of the 2022 preprint "A Worked Example of the Bayesian Mechanics of Classical Objects" by Dalton A R Sakthivadivel. https://arxiv.org/abs/2206.12996
\n\nSession 049.0, September 30, 2022 https://www.youtube.com/watch?v=OtX2Fpzn7KA
\n\nSession 049.1, October 5, 2022 https://www.youtube.com/watch?v=dAtC-Enmc8M
\n\nSession 049.2, October 12, 2022 https://www.youtube.com/watch?v=2SuBJBEg9LI
\n\n", "keywords": [], "related_identifiers": [], "files": [ { "id": "ad28d854-25b8-4801-8c9e-0b6d0160f1a3", "key": "ActInf_Livestream_49_'A Worked Example of the Bayesian Mechanics of Classical Objects'.odt", "size": 123535, "checksum": "md5:18b9ab965053f5ef71c1001a1ecd781e", "links": { "self": "https://zenodo.org/api/records/7400786/files/ActInf_Livestream_49_'A%20Worked%20Example%20of%20the%20Bayesian%20Mechanics%20of%20Classical%20Objects'.odt/content" } } ], "html_url": "https://zenodo.org/records/7400786", "doi_url": "https://doi.org/10.5281/zenodo.7400785", "record_url": "https://zenodo.org/records/7400785" }, { "record_id": "7400709", "doi": "10.5281/zenodo.7400708", "title": "Interoception as modeling, allostasis as control", "publication_date": "2022-11-03", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Sennesh, Eli", "affiliation": "Northeastern University, Boston, MA , United States" }, { "name": "Theriault, Jordan", "affiliation": "Northeastern University, Boston, MA , United States" }, { "name": "Douglass, Dave", "affiliation": "Active Inference Institute", "orcid": "0000-0001-7894-8019" }, { "name": "Tennant, Ian", "affiliation": null }, { "name": "Tickles, Dean", "affiliation": "Active Inference Institute" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "
Transcript of discussions of the 2022 paper “Interoception as modeling, allostasis as control” by Eli Sennesh, Jordan Theriault, Dana Brooks, Jan-Willemvan de Meent, Lisa Feldman Barrett, & Karen S. Quigley https://www.sciencedirect.com/science/article/abs/pii/S0301051121002350
\n\nSession 050.0, October 17, 2022 https://www.youtube.com/watch?v=l7r0ISlr-Hc
\n\nSession 050.1, October 20, 2022 https://www.youtube.com/watch?v=tGd-mgSdbio
\n\nSession 050.2, November 3, 2022 https://www.youtube.com/watch?v=4o-LmkycAC0
\n\n", "keywords": [], "related_identifiers": [], "files": [ { "id": "6b80b440-57c1-4de5-9339-2ae0a35ed3bc", "key": "ActInf Livestream ", "size": 124907, "checksum": "md5:e7929a38f1d65de970a553936af3a239", "links": { "self": "https://zenodo.org/api/records/7400709/files/ActInf%20Livestream%20/content" } } ], "html_url": "https://zenodo.org/records/7400709", "doi_url": "https://doi.org/10.5281/zenodo.7400708", "record_url": "https://zenodo.org/records/7400708" }, { "record_id": "7394901", "doi": "10.5281/zenodo.7394900", "title": "On free will or the lack thereof", "publication_date": "2022-12-03", "version": null, "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Sapolsky, Robert", "affiliation": "Stanford University", "orcid": "0000-0002-7435-5838" }, { "name": "Mikhailova, Alexandra", "affiliation": "University of California, Davis", "orcid": "0000-0002-8699-7125" }, { "name": "Friedman, Daniel", "affiliation": "University of California, Davis", "orcid": "0000-0001-6232-9096" } ], "description": "
In this interview, Robert Sapolsky outlines his view on Free Will and related topics. The discussion anticipates his upcoming book Determined: The Science of Life Without Free Will. Various topics are covered at the intersection of neuroscience with philosophy, education, and the criminal justice system.
", "keywords": [ "Free Will", "Human Behavior", "Legal System", "Philosophy", "Complexity" ], "related_identifiers": [], "files": [ { "id": "d6f29363-41af-41e1-bd29-dcc48cc89a4a", "key": "ALIUS Interview-Robert Sapolsky (2022).pdf", "size": 296824, "checksum": "md5:0b4d6fd4dc62f8032ceacc1c8251b679", "links": { "self": "https://zenodo.org/api/records/7394901/files/ALIUS%20Interview-Robert%20Sapolsky%20(2022).pdf/content" } } ], "html_url": "https://zenodo.org/records/7394901", "doi_url": "https://doi.org/10.5281/zenodo.7394900", "record_url": "https://zenodo.org/records/7394900" }, { "record_id": "7400536", "doi": "10.5281/zenodo.7400525", "title": "Canonical neural networks perform active inference", "publication_date": "2022-11-09", "version": "v1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Isomura, Takuya", "affiliation": "Brain Intelligence Theory Unit, RIKEN Center for Brain Science, Wako, Saitama, 351-0198, Japan" }, { "name": "Daniel Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Transcript of a three-session series of discussions of the paper "Canonical neural networks perform active inference" by Takuya Isomura, Hideaki Shimazaki & Karl J. Friston. https://www.nature.com/articles/s42003-021-02994-2
\n\nLS #051.0: Background and context. https://www.youtube.com/watch?v=ZASG-rtkXDk
\n\nLS #051.1: First participatory group discussion. https://www.youtube.com/watch?v=IM_NlUzyq8M
\n\nLS #051.2: Second participatory group discussion. https://www.youtube.com/watch?v=hY_CajLpt9Q
", "keywords": [], "related_identifiers": [], "files": [ { "id": "0cc1e7df-1530-4c32-8ab5-1599ba978ea3", "key": "ActInf Livestream ", "size": 94605, "checksum": "md5:c37752811003e536a699c95f3a2d42be", "links": { "self": "https://zenodo.org/api/records/7400536/files/ActInf%20Livestream%20/content" } } ], "html_url": "https://zenodo.org/records/7400536", "doi_url": "https://doi.org/10.5281/zenodo.7400525", "record_url": "https://zenodo.org/records/7400525" }, { "record_id": "7377256", "doi": "10.5281/zenodo.7377255", "title": "Predictive Processing Interpretation of the Mirror Test and Implications of a Reflection Prediction for Human Cognition", "publication_date": "2022-11-29", "version": "1", "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Sean O'Connor", "affiliation": "Independent Researcher", "orcid": "0000-0002-0858-5635" }, { "name": "Daniel Ari Friedman", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "The "mirror test" has been used as a behavioral measure of mirror self-recognition for a variety of species. In this article we apply a predictive processing interpretation to the results of the mirror test in order to offer a novel perspective with which to understand mirror self-recognition and self-directed behavior. Furthermore, we hypothesize that a “reflection prediction”, upon which our predictive processing interpretation of the mirror test is built, may also offer a novel perspective to understand how humans locate themselves relative to a mirror, imitate others, and are self-aware from a social perspective. As we show that a reflection prediction may help to explain how these traits may emerge in human cognition, we also point out that atypical reflection predictions or atypical use of a reflection prediction may help to explain instances where these traits are atypical in certain individuals.
", "keywords": [ "Mirror self-recognition", "Mirror test", "Self-directed behavior", "Active inference", "Predictive processing", "Sensory attenuation", "Mirror neuron", "Body Image", "Psycopathology", "Autism", "Depersonalization Disorder", "Schizophrenia", "Body integrity identity disorder", "Imitation", "Self-Awareness", "Theory of mind", "George Herbert Mead" ], "related_identifiers": [], "files": [ { "id": "9909a61e-fc18-4fef-8a24-e07ee9e63c2e", "key": "Predictive Processing Interpretation of the Mirror Test.pdf", "size": 206849, "checksum": "md5:0b44a22c04817c12f6928c01954ab245", "links": { "self": "https://zenodo.org/api/records/7377256/files/Predictive%20Processing%20Interpretation%20of%20the%20Mirror%20Test.pdf/content" } } ], "html_url": "https://zenodo.org/records/7377256", "doi_url": "https://doi.org/10.5281/zenodo.7377255", "record_url": "https://zenodo.org/records/7377255" }, { "record_id": "7267947", "doi": "10.5281/zenodo.7259006", "title": "Transcript of: Mark Solms, \"Consciousness as Precision Optimization: Some Physiological and Philosophical Considerations\", ActInf GuestStream #016", "publication_date": "2022-10-27", "version": "1.1", "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "Solms, Mark", "affiliation": "Department of Psychology, University of Cape Town, Cape Town, South Africa", "orcid": "0000-0003-4828-3882" }, { "name": "Douglass, David S", "affiliation": "Active Inference Institute", "orcid": "0000-0001-7894-8019" }, { "name": "Sillett, Stephen", "affiliation": "Active Inference Institute, Community Psychologist, Facilitator, Participatory Theatre Director PhD Candidate, Salomons Institute for Applied Psychology, Canterbury Christ Church University. Founder of InFusion Lab, Member of Global Psychosocial Network. Co-Founder of Aiding Dramatic Change in Development", "orcid": "0000-0003-1046-1946" }, { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute & Department of Entomology and Nematology, University of California, Davis, USA.", "orcid": "0000-0001-6232-9096" } ], "description": "This document is an enhanced transcript of the live presentations and group discussions with Mark Solms in 2022 at the Active Inference Institute. The focus is the 2018 paper "How and Why Consciousness Arises: Some Considerations from Physics and Physiology" by Mark Solms and Karl Friston.
", "keywords": [ "Active Inference", "Consciousness", "Neuroanatomy", "Psychology", "Free Energy Principle", "Livestream" ], "related_identifiers": [], "files": [ { "id": "04128f5e-3cca-4bc1-a1da-55e9fc5b5392", "key": "ActInfLab GuestStream ", "size": 5617660, "checksum": "md5:4ca4a24abe17a56ff3ec26110a3a3dfd", "links": { "self": "https://zenodo.org/api/records/7267947/files/ActInfLab%20GuestStream%C2%A0/content" } }, { "id": "25e23f11-5058-4dcb-bec6-47a96499e5ae", "key": "ActInf GuestStream ", "size": 29079868, "checksum": "md5:adc84134700133ac6f8bcdd86b12ae5d", "links": { "self": "https://zenodo.org/api/records/7267947/files/ActInf%20GuestStream%C2%A0/content" } } ], "html_url": "https://zenodo.org/records/7267947", "doi_url": "https://doi.org/10.5281/zenodo.7259006", "record_url": "https://zenodo.org/records/7259006" }, { "record_id": "7093837", "doi": "10.5281/zenodo.7093836", "title": "TrustFinder: Recommendations for a Community-Based System for Finding Trusted Sources and Evaluating Claims", "publication_date": "2022-08-25", "version": "1.0", "resource_type": { "title": "Book chapter", "type": "publication", "subtype": "section" }, "creators": [ { "name": "R.J. Cordes", "affiliation": "Active Inference Lab; COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "Scott David", "affiliation": "Active Inference Lab; Information Risk and Synthetic Intelligence Research Initiative (IRSIRI), University of Washington - Applied Physics Laboratory" }, { "name": "Daniel Friedman", "affiliation": "Active Inference Lab; COGSEC; University of California, Davis, Department of Entomology and Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "There is a broadly recognized need for better situational awareness within the information environment. Each year, millions of articles, books, documents, and datasets are published. Amidst this flood of information, even those with significant experience and expertise in the knowledge economy are struggling to evaluate and vet claims. This document builds on the feedback of dozens of experts across myriad fields submitted to the University of Washington Applied Physics Lab’s Verified Information Exchange Environments Program, to present recommendations for a sociotechnical system, “TrustFinder”, for collaborative management of the information supply chain. TrustFinder implements controls and standards, web and document annotation affordances, argument representation frameworks, and crowdsourcing design principles in order to harness the work of global research communities. The ultimate goal of TrustFinder is to structure the information environment to such an extent that it enables users to find trusted sources of information and rapidly assess concepts and claims.
", "keywords": [ "Sensemaking", "Mechanism Design", "System Specification" ], "related_identifiers": [], "files": [ { "id": "efa7eeb6-d881-43cf-a719-d66faee42b54", "key": "VIE-IG_1.pdf", "size": 1666008, "checksum": "md5:bf57331b67cd9618c325e85b02be327e", "links": { "self": "https://zenodo.org/api/records/7093837/files/VIE-IG_1.pdf/content" } } ], "html_url": "https://zenodo.org/records/7093837", "doi_url": "https://doi.org/10.5281/zenodo.7093836", "record_url": "https://zenodo.org/records/7093836" }, { "record_id": "6904427", "doi": "10.5281/zenodo.6904426", "title": "Tracking Public Sensemaking through Rhetorical Annotation of Image Memes", "publication_date": "2022-07-25", "version": "1.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Mridula Mascarenhas", "affiliation": "California State University, Monterey Bay, CA. School of Humanities & Communication" }, { "name": "RJ Cordes", "affiliation": "COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "Bleu Knight", "affiliation": "Active Inference Institute; New Mexico State University, Las Cruces, NM. Department of Biology" }, { "name": "Sarah Murphy", "affiliation": "Seemeless Solutions" }, { "name": "Daniel A. Friedman", "affiliation": "COGSEC; Active Inference Institute; University of California, Davis, Department of Entomology and Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "Political polarization and declining trust in institutions are driving societal destabilization and radicalization. Recently there has been increased interest in online misinformation intervention and deterrence, for example through the use of machine learning on language use. We argue that addressing crises in the information environment will require a sharper situational awareness and a deeper understanding of how beliefs emerge and crystallize, as well as greater connectivity in the work of teams and organizations in order to reduce the effects of bias and partisanship in collection and analysis. Image memes play an increasingly important role in public sensemaking and discourse and the emergence of public beliefs. Despite their significance, image memes have proven to be a very difficult category of artifact to collect, classify, and analyze in aggregate. In this white paper, the function and form of image memes are discussed, the challenges of performing image meme collection and analysis within the context of emergent, interdisciplinary teams are detailed, and requirements and recommendations for alleviating these challenges are offered.
", "keywords": [ "Sensemaking", "Memes", "Knowledge Management", "Narrative", "Rhetorical Analysis" ], "related_identifiers": [], "files": [ { "id": "22a31c86-dae1-4075-ad76-1f0173eaa07f", "key": "ECOMEME2-v1.0.pdf", "size": 4247899, "checksum": "md5:644a535cb85f2b945efaf6b2c912c67e", "links": { "self": "https://zenodo.org/api/records/6904427/files/ECOMEME2-v1.0.pdf/content" } } ], "html_url": "https://zenodo.org/records/6904427", "doi_url": "https://doi.org/10.5281/zenodo.6904426", "record_url": "https://zenodo.org/records/6904426" }, { "record_id": "5797072", "doi": "10.5281/zenodo.5797040", "title": "Transcript of: Karl Friston, 1st Applied Active Inference Symposium, Active Inference Lab, June 21, 2021", "publication_date": "2021-12-21", "version": "v2.0", "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "Friston, Karl", "affiliation": "Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London, London WC1N 3AR, UK", "orcid": "0000-0001-7984-8909" }, { "name": "Douglass, David Standish", "affiliation": "ActInfLab, American Society for Cybernetics", "orcid": "0000-0001-7894-8019" }, { "name": "Iennaco de Vasconcelos, Maria Luiza", "affiliation": "ActInfLab, University of São Paulo, São Paulo, Brazil. Department of Philosophy", "orcid": "0000-0002-5407-4852" }, { "name": "Sillett, Stephen", "affiliation": "ActInfLab, Canterbury Christ Church University, Salomons Institute for Applied Psychology", "orcid": "0000-0003-1046-1946" }, { "name": "Sganzerla, Lorena", "affiliation": "ActInfLab, Berlin School of Mind and Brain - Humboldt-Universität zu Berlin", "orcid": "0000-0002-5384-6232" }, { "name": "Tickles, Dean", "affiliation": "ActInfLab,", "orcid": "0000-0003-2213-0773" }, { "name": "Metelkin, Ivan", "affiliation": "ActInfLab, Systems Management School (Moscow)", "orcid": "0000-0003-2899-6690" }, { "name": "Vyatkin, Alex", "affiliation": "ActInfLab, Systems Management School (Moscow)", "orcid": "0000-0003-1306-4620" }, { "name": "Friedman, Daniel Ari", "affiliation": "ActInfLab, University of California, Davis, USA, Department of Entomology & Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "On June 21st, 2021, Active Inference Lab (activeinference.org/) hosted its first Applied Active Inference Symposium, featuring Professor Karl Friston. The Symposium was structured in three sections, corresponding to the Organizational Units of the Active Inference Lab: Education, Communication, and Tools. This publication reflects an edited and enriched transcript of the proceedings of the Symposium.
", "keywords": [ "Active Inference", "Free Energy Principle", "Symposium", "ActInfLab", "Bayesian Inference", "Education", "Communication", "Tools", "Generative Model" ], "related_identifiers": [ { "identifier": "youtube.com/watch?v=INRaCBikpso", "relation": "isDocumentedBy", "resource_type": "video", "scheme": "handle" }, { "identifier": "youtube.com/watch?v=X2GwqUVLlcs", "relation": "isDocumentedBy", "resource_type": "video", "scheme": "handle" }, { "identifier": "youtube.com/watch?v=hW9IiOujS1E", "relation": "isDocumentedBy", "resource_type": "video", "scheme": "handle" } ], "files": [ { "id": "8aa9e556-df27-4519-a5fd-b32c00d0aa66", "key": "v2 - Karl Friston, Applied Active Inference Symposium, ActInfLab, June 21, 2021.pdf", "size": 4775810, "checksum": "md5:f08ab8aa4bfc18d661fc86b344a88ac9", "links": { "self": "https://zenodo.org/api/records/5797072/files/v2%20-%20Karl%20Friston,%20Applied%20Active%20Inference%20Symposium,%20ActInfLab,%20June%2021,%202021.pdf/content" } } ], "html_url": "https://zenodo.org/records/5797072", "doi_url": "https://doi.org/10.5281/zenodo.5797040", "record_url": "https://zenodo.org/records/5797040" }, { "record_id": "5759807", "doi": "10.5281/zenodo.5750934", "title": "Active Inference in Modeling Conflict", "publication_date": "2021-12-02", "version": "v1.2", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Scott David", "affiliation": "Active Inference Lab; Information Risk and Synthetic Intelligence Research Initiative (IRSIRI), University of Washington - Applied Physics Laboratory" }, { "name": "Richard J. Cordes", "affiliation": "Active Inference Lab; COGSEC; Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel A. Friedman", "affiliation": "Active Inference Lab; COGSEC; University of California, Davis, Department of Entomology and Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "In this paper, we integrate conflict studies with Active Inference, a developing framework which provides an integrative and systems-level perspective on cognition and behavior. This formalization, the Active Inference Conflict (AIC) model, situates conflict in terms of a multiscale process of communication, trust, and relationship management enacted by interacting entities. The AIC model helps capture and extend the insights of previous models applied to aspects of conflict and war, such as OODA loops (observe-orient-decide-act), the generations of warfare model, and the Rumsfeld Matrix. The AIC model aids in the analysis of pertinent aspects of modern conflict, such as cyber, psychological, biological, informational, financial, and ideological conflict, that are not amenable to coherent or consistent analysis using traditional models of human conflict. AIC is demonstrated to be of use in both monitoring and studying conflict, as well as in designing systems intended to facilitate controlled or managed conflict in scenarios characterized by business, operations, legal, technical, and social (BOLTS) components. Insights and implications from qualitative use are used as a foundation for offering recommendations for future research and social systems design.
", "keywords": [ "Active Inference", "Conflict", "BOLTS", "NIM" ], "related_identifiers": [], "files": [ { "id": "89613d02-2c9f-480b-bbc8-16d5affd7b1e", "key": "AIC v1_2.pdf", "size": 1025494, "checksum": "md5:bb07e5a4aa1e3d20f26885fb169bf5c6", "links": { "self": "https://zenodo.org/api/records/5759807/files/AIC%20v1_2.pdf/content" } } ], "html_url": "https://zenodo.org/records/5759807", "doi_url": "https://doi.org/10.5281/zenodo.5750934", "record_url": "https://zenodo.org/records/5750934" }, { "record_id": "5573947", "doi": "10.5281/zenodo.5573946", "title": "Digital Rhetorical Ecosystem Analysis: Sensemaking of Digital Memetic Discourse", "publication_date": "2021-10-16", "version": "1.1", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Mridula Mascarenhas", "affiliation": "California State University Monterey Bay, School of Humanities and Communication" }, { "name": "Richard J. Cordes", "affiliation": "COGSEC; Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel A. Friedman", "affiliation": "COGSEC; University of California, Davis, Department of Entomology and Nematology", "orcid": "0000-0001-6232-9096" } ], "description": "This paper makes a case for integrating frameworks from two different knowledge domains, rhetorical studies and ecological studies, to catalog, monitor, and study digital image meme data, in order to support a more robust understanding of how memes produce and disseminate online narratives. In the digital public sphere, the primacy of image-based communication motivates an over-reliance on the image meme for public argumentation. Despite its ubiquity, the image meme format is currently understudied in large scale digital data analyses, relative to text -based formats such as natural language and hashtags. We argue that using a rhetorical approach (which emphasizes message form and audience) in large-scale analyses of multimedia and other digital artifacts can enhance analytic tools for categorizing, indexing, searching, and modeling online discourse. Further, by integrating a rhetorical and an ecosystem approach to studying digital discourse, we can formally trace multimedia rhetorical artifacts like image memes across platforms, media types, and languages. Combined rhetorical and ecosystem analyses can reveal how digital artifacts like image memes create, sustain, and disrupt public narratives and, thereby, socio-political dynamics. Three key elements of our approach are a) recognizing how parsimony and polysemy give image memes narrative power, b) focusing on how image memes engage audiences through identity construction, and c) applying “Rhetorical Ecosystem” mapping, based upon toolkit transfer and system design implications. Drawing from concepts in rhetoric, ecology, and complex systems analysis we introduce a Digital Rhetorical Ecosystem three-tiered model (DRE3) to explain how memes impact public narratives and beliefs. We then explore implications of this DRE3 model for the design and development of systems for computational analysis of digital discourse.
", "keywords": [ "Rhetoric", "Ecology", "Memes", "Sensemaking", "SCADA", "NIM" ], "related_identifiers": [], "files": [ { "id": "56004760-82bf-4a55-b018-62bd5cdedade", "key": "ECOMEME v1.1.pdf", "size": 2259667, "checksum": "md5:eb16ffcd28e2f9ed173392af7ab59944", "links": { "self": "https://zenodo.org/api/records/5573947/files/ECOMEME%20v1.1.pdf/content" } } ], "html_url": "https://zenodo.org/records/5573947", "doi_url": "https://doi.org/10.5281/zenodo.5573946", "record_url": "https://zenodo.org/records/5573946" }, { "record_id": "5573287", "doi": "10.5281/zenodo.5565577", "title": "Narrative Information Management", "publication_date": "2021-10-12", "version": "1.1", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "Complexity Weekend; COGSEC; Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Shaun Applegate-Swanson", "affiliation": "Complexity Weekend; Microsoft", "orcid": "0000-0001-9474-6038" }, { "name": "Daniel Ari Friedman", "affiliation": "Complexity Weekend; COGSEC; Active Inference Lab; University of California, Davis, Department of Entomology and Nematology", "orcid": "0000-0001-6232-9096" }, { "name": "Virginia Bleu Knight", "affiliation": "Complexity Weekend; Active Inference Lab" }, { "name": "Alexandra Mikhailova", "affiliation": "Complexity Weekend; University of California, Davis, Center for Neuroscience", "orcid": "0000-0002-8699-7125" } ], "description": "There are many areas of research defined by their interest in information dynamics related to facilitating organizational sensemaking, such as knowledge management, information management, and library science, and many more areas of research, disciplines, and even hobbies which are facing information-related challenges. While all may be concerned with very similar challenges, lack of information exchange and common ontology between these areas may be causing silos, missed opportunities, and potentially even friction among areas. In this paper, we address the need for synthesis and exchange of knowledge, tools, and approaches among various fields by proposing Narrative Information Management (NIM) as a unifying term and framework for the fundamental features and challenges of facilitating collective sensemaking. Through this framework, we offer an initial common set of features of impactful information systems found in literature on information-focused disciplines, such as knowledge management, and explore what insights and ad-hoc solutions may be found in an eclectic set of fields facing information challenges, including personal finance, ancestry research, hybrid cloud infrastructure security, translational neuroscience, and genomics. Finally, we offer recommendations for future research.
", "keywords": [ "Sensemaking", "NIM", "Narrative", "Information Management", "Knowledge Management" ], "related_identifiers": [], "files": [ { "id": "83df7500-6581-4164-be99-624faff7256f", "key": "NIM21 v1.1.pdf", "size": 738658, "checksum": "md5:59b2857ed60d7fa16d8ac5b8a29d3473", "links": { "self": "https://zenodo.org/api/records/5573287/files/NIM21%20v1.1.pdf/content" } } ], "html_url": "https://zenodo.org/records/5573287", "doi_url": "https://doi.org/10.5281/zenodo.5565577", "record_url": "https://zenodo.org/records/5565577" }, { "record_id": "5034809", "doi": "10.5281/zenodo.5034808", "title": "Knowledge Management Archipelago", "publication_date": "2021-06-26", "version": "v1.0", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Daniel Ari Friedman", "affiliation": "University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" }, { "name": "Richard J. Cordes", "affiliation": "Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" } ], "description": "The theory and practice of knowledge management shares concerns and approaches with a number of other areas of research, some of which preceded its formalization as a field. In the age of the internet, the challenges that the field of knowledge management addresses, such as the difficulty of synthesizing, interpreting, and managing large streams of information, are no longer confined to professional disciplines and are present in everyday life. The commonality and timelessness of these concerns presents a potential problem for the field of knowledge management that, ironically, the field itself often seeks to address: the creation of silos, sometimes referred to as “islands”, in the knowledge base. The purpose of this paper is to present an exploratory bibliometric analysis of the various areas of research which share concerns, approach, and scope in common with knowledge management. Search-strings associated with selected areas of research were used to query Google Scholar in various combinations in search of co-occurrence, results were quantified and visualized. The results show variable couplings and differential prevalence of keywords, and serve as a starting point for targeted analyses and next steps.
", "keywords": [ "Knowledge Management", "Information Management", "Bibliometrics", "Library Science", "Intellectual Capital Management", "Command and Control Systems", "SCADA", "Data Fusion", "Information Fusion" ], "related_identifiers": [], "files": [ { "id": "f35d3f51-36dd-486e-94d7-8556671f81c7", "key": "KnowledgeManagementArchipelago_1_0.pdf", "size": 1029707, "checksum": "md5:1b1b9a19f0c7c7f40b3cb279f4ec464b", "links": { "self": "https://zenodo.org/api/records/5034809/files/KnowledgeManagementArchipelago_1_0.pdf/content" } } ], "html_url": "https://zenodo.org/records/5034809", "doi_url": "https://doi.org/10.5281/zenodo.5034808", "record_url": "https://zenodo.org/records/5034808" }, { "record_id": "4633921", "doi": "10.5281/zenodo.4624298", "title": "Collaborative Writing for Catechism-Based Teams", "publication_date": "2021-03-19", "version": "v1.2", "resource_type": { "title": "Working paper", "type": "publication", "subtype": "workingpaper" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel Ari Friedman", "affiliation": "University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" } ], "description": "Asynchronous and remote collaborative written projects (research, field guides, code, etc.) in emergent, interdisciplinary teams can be an incredibly productive and enjoyable pursuit. The convergence of diverse perspectives, personalities, and expertise in the rapid production of written deliverables can provide immense value and insight, not just to the situation, problem, or opportunity space the team was formed to address, but also to the disciplines each author brought to the table. Yet, asynchronous and remote collaborative writing can also be rather perilous. Managing deadlines, handling disputes, communicating, staying on mission, managing resources, collective editing (and over-editing), and avoiding contradiction are only some of the challenges. While the presence of a catechism-styled operations order and the use of a team “Facilitator” can greatly improve the likelihood of success, making sure all of the authors have an alignment on protocol and etiquette while writing as a catechism-based team prevents unnecessary misunderstandings and keeps things on schedule.
\n
\nThis "3-Paragraph Order" for Collaborative Writing, or C-3PO, is meant to rapidly onboard authors to collaborative writing procedures and etiquette.
The Facilitator’s Catechism (FC) is an operations order formatted as a project-management document. The FC is intended to be used & refined by remote teams in order to greatly increase organizational alignment, project comparability, reliability, and productivity in the pursuit of timely deliverables while reducing work-about-work. It is built from the battle-tested, project management techniques used by the National Militaries and by the Defense Advanced Research Projects Agency. This playbook is meant to be a document that assists with that adoption, ensuring clarity and providing a Single Source of Truth (SSoT) for the intents of its application and its usage. It offers context on the background of catechisms (Part I), a step-by-step guide on how to deploy it for the first time (Part II), and examples, templates, further reading, and resources for making it a part of your regular individual or team work-flow (Supplemental Resources).
", "keywords": [ "Small Teams", "Project Management", "Operations Orders", "Remote Work" ], "related_identifiers": [], "files": [ { "id": "e58ce2e9-38c4-4ca8-a619-dae30aad8855", "key": "FaciliatorsCatechismPlaybook.pdf", "size": 2670641, "checksum": "md5:deb5b1f5413a27e98d84521b4c53f1af", "links": { "self": "https://zenodo.org/api/records/4579414/files/FaciliatorsCatechismPlaybook.pdf/content" } } ], "html_url": "https://zenodo.org/records/4579414", "doi_url": "https://doi.org/10.5281/zenodo.4579413", "record_url": "https://zenodo.org/records/4579413" }, { "record_id": "4383230", "doi": "10.5281/zenodo.4383229", "title": "The Innovator's Catechism", "publication_date": "2020-12-21", "version": "v1", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "COGSEC; Remotor Consulting Group; Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel A. Friedman", "affiliation": "COGSEC; Remotor Consulting Group; University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" }, { "name": "Steven E. Phelan", "affiliation": "Fayetteville State University, Dept. of Graduate & Professional Studies in Business", "orcid": "0000-0003-3897-3273" } ], "description": "Innovation teams formed in incubators, research accelerators, hackathon weekends, and within organizations need to quickly align on narrative, workflow, and objectives in order to achieve success. Many of these teams disintegrate or fail to perform due to lack of alignment. Operations orders, such as those in use by the military, have demonstrable impact on organizational efficacy and success. This paper summarizes the history, development, and impact of military operations orders, discusses the history and development of their business counterparts, and presents the “The Innovator’s Catechism”, a catechism-styled operations order for use by early-stage innovation teams. This operations order is built from the “Facilitator’s Catechism”, an operations order for rapidly formed research teams, with acknowledgment for the special information requirements present for emergent and early-stage teams that are market-facing.
", "keywords": [ "Entrepreneurship", "Remote Teams", "OPORD", "High Reliability Organizations", "Small Teams" ], "related_identifiers": [], "files": [ { "id": "f3a8bc10-180a-4a96-b37c-4ffa0155b0dd", "key": "The Innovators Catechism.pdf", "size": 2008642, "checksum": "md5:2fd99dcfb1cdc0c630d23d80f0c54db2", "links": { "self": "https://zenodo.org/api/records/4383230/files/The%20Innovators%20Catechism.pdf/content" } } ], "html_url": "https://zenodo.org/records/4383230", "doi_url": "https://doi.org/10.5281/zenodo.4383229", "record_url": "https://zenodo.org/records/4383229" }, { "record_id": "4203765", "doi": "10.5281/zenodo.4062540", "title": "The Facilitator's Catechism", "publication_date": "2020-10-01", "version": "v2", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "COGSEC; Remotor Consulting Group; Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel Ari Friedman", "affiliation": "COGSEC; Remotor Consulting Group; University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" } ], "description": "This paper discusses the origins and evolution of Operations Orders from antiquity to modern times and the impact of Operations Orders on organizational sensemaking. Perspectives from research on Complexity Science, Organizational Psychology, High Reliability Organizations, Memetics, Logistics, Knowledge Management Systems, and Active Inference are used to consider the historical, contemporary, and future requirements and constraints of Operations Orders. Examples of traditional military Operations Orders and their civilian counterparts are detailed in context with their respective environments and requirements. Key characteristics of survivability, contemporary and future requirements, and current limitations of extant Operations Orders are addressed in order to inform the proposal of a new Operations Order format for use by Process Facilitators of military, intelligence, and civilian teams: the “Facilitator’s Catechism”.
", "keywords": [ "OPORD", "Operations Orders", "Military History", "Remote Teams", "Complexity", "High Reliability Organizations", "Organizational Sensemaking", "Complex Threat Surfaces", "Small Teams", "Systems Engineering", "Active Inference" ], "related_identifiers": [], "files": [ { "id": "feab0837-71c7-4929-b3c2-3efc644906ce", "key": "The Facilitators Catechismv2.pdf", "size": 1981417, "checksum": "md5:b08e045d5cba93b3d80cb3be109f2501", "links": { "self": "https://zenodo.org/api/records/4203765/files/The%20Facilitators%20Catechismv2.pdf/content" } } ], "html_url": "https://zenodo.org/records/4203765", "doi_url": "https://doi.org/10.5281/zenodo.4062540", "record_url": "https://zenodo.org/records/4062540" }, { "record_id": "4170026", "doi": "10.5281/zenodo.4170025", "title": "Reimagining Maps", "publication_date": "2020-10-31", "version": "v1", "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "COGSEC, Atlantic Council GeoTech Center", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel Ari Friedman", "affiliation": "University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" }, { "name": "Mikel Maron", "affiliation": "Mapbox" } ], "description": "Reimagining Maps was written after participation in a National Geospatial-Intelligence Agency Incubator hosted on Polyplexus.
\n
\nThe field of cartography sits at the intersection of applied mathematics, engineering, geology, geography, user experience, and graphic design. Methodologies and concepts from cartography have been creatively applied in a variety of fields, such as the application of spatial mapping techniques to information in knowledge management, or the use of itinerary visualization methods in non-spatial journeys such as learning maps in learning management systems. These fields have been subjected to their own forms of development and evolution leading to new methodologies and concepts somewhat removed from their origins. Cartography itself has undergone a great deal of technology-driven development but would look very different today had it been developed as a new field through the creative application of methodologies and concepts from those it inspired. As the modern information and logistical context presents new challenges and thus new demands for maps, we propose a “reimagining of maps” through an interdisciplinary synthesis inspired by the interdisciplinary origins of maps themselves.
Comprehensive frameworks for Teams should include various functionalities and structures in order to capture the broad range of affordances available for modern Remote Teams, including, but not limited to, synchronous & asynchronous communications, memes, geospatial maps, hardware/software use, and contact escalation. We suggest that Systems Engineering provides guidelines to define the functions of Ontologies, Narratives, Formal documents, and Tools (ONFT) within the context of the life cycle of any System of Interest. Following this ONFT assessment it is possible to break out to sub-systems levels and mechanistic analysis. In this paper we explore how a new generation of ONFT for Remote Teams could be based on Active Inference, a process theory related to the Free Energy Principle. Effective ONFT based upon Active Inference could lead to the realization of lightweight and powerful epistemic tools to guide everyday decision-making in an embodied, enactive fashion. Such a technology for Remote Teams would lead to fundamental changes in various aspects of Team function, for example the efficiency of a Team’s production of artifacts or self-reported “phenomenology of the working day”.
", "keywords": [ "Active Inference", "Free Energy Principle", "Remote Teams", "Communication", "Technology" ], "related_identifiers": [], "files": [ { "id": "50ce1563-27db-4f88-9502-1bbdae548ee4", "key": "AIN1_Act_Inf_Narratives_v1.pdf", "size": 3810012, "checksum": "md5:dbdb6ffd6728b56d45c3eae20b421c4b", "links": { "self": "https://zenodo.org/api/records/4021163/files/AIN1_Act_Inf_Narratives_v1.pdf/content" } } ], "html_url": "https://zenodo.org/records/4021163", "doi_url": "https://doi.org/10.5281/zenodo.4021162", "record_url": "https://zenodo.org/records/4021162" }, { "record_id": "3986085", "doi": "10.5281/zenodo.3986084", "title": "Emergent Teams for Complex Threats", "publication_date": "2020-05-15", "version": null, "resource_type": { "title": "Journal article", "type": "publication", "subtype": "article" }, "creators": [ { "name": "Richard J. Cordes", "affiliation": "COGSEC", "orcid": "0000-0002-9913-7159" }, { "name": "Daniel Ari Friedman", "affiliation": "University of California, Davis, Department of Entomology", "orcid": "0000-0001-6232-9096" } ], "description": "While the underlying, fundamental principles of warfare have long remained unchanged, recent social and technological developments have necessitated new approaches to conflict management. Specifically, the introduction of nuclear weapons and the maintenance of large military budgets during peacetime in the latter half of the 20th century have changed the risk calculus of conflict among state and non-state actors. Consequently, the operating environment has changed. Extant, centralized actors have experienced new adversities such as ideological warfare and sustained low intensity and gray zone conflict while new, decentralized participants have emerged and evolved. Nation states, as a part of normal operations, now have to contend with the potential for novel, emergent hazards from a myriad of Complex Threat Surfaces in littoral and other environments. We highlight how Complexity Science has been of use in the analysis of Complex Threat Surfaces in the military and within civilian organizations, particularly High Reliability Organisations or HROs. This paper discusses the intersection of Complexity Science and Military Science by focusing on analysis of counterinsurgency and counterterrorism operations. We highlight rapid reorganization, pooling collective expertise, and the assembly of novel organizational components as a potential basis for developing spontaneous expertise, actionable intelligence, and solutions to the aforementioned novel, emergent hazards.
", "keywords": [ "Gray Zone Warfare", "OSINT", "Remote Teams", "Small Teams", "Organizational Sensemaking", "High Reliability Organizations", "Complex Threat Surfaces", "Counterterrorism", "Complexity", "Insurgency", "Counterinsurgency", "Terrorism", "Low Intensity Conflict" ], "related_identifiers": [], "files": [ { "id": "a7142ed9-47de-4bfd-9c53-fac29e7fe782", "key": "CordesFriedman2020.pdf", "size": 186028, "checksum": "md5:4079c630aa07d20f6882666839c0db5f", "links": { "self": "https://zenodo.org/api/records/3986085/files/CordesFriedman2020.pdf/content" } } ], "html_url": "https://zenodo.org/records/3986085", "doi_url": "https://doi.org/10.5281/zenodo.3986084", "record_url": "https://zenodo.org/records/3986084" }, { "record_id": "14861596", "doi": "10.5281/zenodo.14861595", "title": "Biofirm Development with First Principles First and the Active Inference Institute at the Applied Active Inference Symposium 2024", "publication_date": "2025-02-12", "version": null, "resource_type": { "title": "Presentation", "type": "presentation" }, "creators": [ { "name": "John Clippinger", "affiliation": "Bioform Labs" }, { "name": "Andrew Pashea", "affiliation": "Active Inference Institute", "orcid": "0009-0004-4061-6296" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Multiple presentations given during the Active Inference Institute's 4th annual Applying Active Inference Symposium, 2024 over the course of November 13th-15th 2024
\n", "keywords": [], "related_identifiers": [], "files": [ { "id": "3d1d5ab1-7ec9-4af3-b835-b942aedf0a9e", "key": "BIOFIBIOFIRM_v2.pptx", "size": 3792928, "checksum": "md5:53ce1262b604dcb50ffdd9c5794b8d69", "links": { "self": "https://zenodo.org/api/records/14861596/files/BIOFIBIOFIRM_v2.pptx/content" } }, { "id": "73d3da89-5194-4e3f-ba05-b3611a5efc4d", "key": "John H Clippinger & Andrew Pashea_ “BioFirm Workshop part 2_.mp4", "size": 505106551, "checksum": "md5:8848c5c177713a0f203d254753df2b3a", "links": { "self": "https://zenodo.org/api/records/14861596/files/John%20H%20Clippinger%20&%20Andrew%20Pashea_%20%E2%80%9CBioFirm%20Workshop%20part%202_.mp4/content" } }, { "id": "99f0d868-65d3-4e35-86e1-dfefefdcf33b", "key": "Day3_Roundtable.mp4", "size": 461527767, "checksum": "md5:d1b32b277206d7e787ba54e35fb7def5", "links": { "self": "https://zenodo.org/api/records/14861596/files/Day3_Roundtable.mp4/content" } }, { "id": "c47bc0e1-842f-4bb3-8f88-e7a761baf43d", "key": "Andrew Pashea - Active Inference Symposium 2024 (1).pptx", "size": 4354599, "checksum": "md5:2984988f9f109126dcbe41d0563b7d03", "links": { "self": "https://zenodo.org/api/records/14861596/files/Andrew%20Pashea%20-%20Active%20Inference%20Symposium%202024%20(1).pptx/content" } }, { "id": "3d83e3f1-3555-434b-bd52-e5bd0b4d2a09", "key": "John H Clippinger “Workshop part 1_ Introduction to Applying Active Inference“.mp4", "size": 271640214, "checksum": "md5:c7b2ff0d303453b772e49bb1078dd090", "links": { "self": "https://zenodo.org/api/records/14861596/files/John%20H%20Clippinger%20%E2%80%9CWorkshop%20part%201_%20Introduction%20to%20Applying%20Active%20Inference%E2%80%9C.mp4/content" } } ], "html_url": "https://zenodo.org/records/14861596", "doi_url": "https://doi.org/10.5281/zenodo.14861595", "record_url": "https://zenodo.org/records/14861595" }, { "record_id": "14738798", "doi": "10.5281/zenodo.13626536", "title": "Con-cat-enate: emulation of Cat Hippocampus", "publication_date": "2025-01-25", "version": null, "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "Djuwidja, Andrew", "affiliation": "Active Inference Institute" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "
Updated
\n\n
added a number of pages at the start (from page 2)
\nthat describes the entire system and whats missing
\napologies for not giving this overview of
\nwhat would happen given those missing parts
\nand the purpose of demo0.01 which substitute those parts
\nto see whether the break down of the 10 miliscond to (longer period)
\nwith each handwritten sim, does stack chems as mentioned;
\nand thus imply correct behavior
\nsome of the documents mentioning demo 0.01
\nand its motivation wasnt included (mentioned in the catpilot)
\ntherefore might cause confusion (ontop of also not really mentioning
\nwhat would each of the missing part cause,)
\nmuch apologies
\n\n
part 1 and part 2 updated of the emulated cat
\ngoes along with these documents:
\npilot:
https://zenodo.org/records/14737043
beacons:
https://zenodo.org/records/14737060
bevcyc:
https://zenodo.org/records/14737076
", "keywords": [], "related_identifiers": [], "files": [ { "id": "bbfede13-dd47-452e-8599-de94113fa56f", "key": "0125cat.pdf", "size": 1423535, "checksum": "md5:e7a2e42e1fbc53e043d1149e19f4b0cc", "links": { "self": "https://zenodo.org/api/records/14738798/files/0125cat.pdf/content" } } ], "html_url": "https://zenodo.org/records/14738798", "doi_url": "https://doi.org/10.5281/zenodo.13626536", "record_url": "https://zenodo.org/records/13626536" }, { "record_id": "14737157", "doi": "10.5281/zenodo.14737156", "title": "Graphspeak: of language and handshake", "publication_date": "2025-01-25", "version": null, "resource_type": { "title": "Preprint", "type": "publication", "subtype": "preprint" }, "creators": [ { "name": "djuwidja, andrew", "affiliation": "Active Inference Institute", "orcid": "0009-0006-9402-2412" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "
An experiment on decomposing language
\nonto initially established graph-theory representation
\napplied then onto some pre-selected transformations
\n(commonly used context/tool related transmutes) (t1,t2,t3)
\nthen upon some layers of decomposition
\nfinding out the shared context / what we label as
\na handshake; for the purpose of education / others
", "keywords": [], "related_identifiers": [], "files": [ { "id": "5513e8be-416f-493a-a4ee-da909f832292", "key": "graph.pdf", "size": 635951, "checksum": "md5:8b9d8d8fc39a455724a6a303add1d881", "links": { "self": "https://zenodo.org/api/records/14737157/files/graph.pdf/content" } } ], "html_url": "https://zenodo.org/records/14737157", "doi_url": "https://doi.org/10.5281/zenodo.14737156", "record_url": "https://zenodo.org/records/14737156" }, { "record_id": "14737076", "doi": "10.5281/zenodo.14737075", "title": "BevCyc - posit on primitive drivers of creatures", "publication_date": "2025-01-25", "version": null, "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "djuwidja, andrew", "affiliation": "Active Inference Institute", "orcid": "0009-0006-9402-2412" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Posits a bev-cyc as primitive driver of creatures / to use in agentic system
\nrepresents a cycle of homeostasis to accomplish by
\ndivisible action sequences; that are actually states that break down onto muscle % tension
\nfollows / posits to experiment / emulate ideas of morphogenesis / morphospace (dr levin's)
\non differing scale of time & checkpoints
\nto run with a modulator layer ; to then apply in either a static | n n n n n n | autofilling nodes
\nfor inputs from hippocampus systems; or a decreasing one that emulates stage-of-state
\nor the cycle involved
", "keywords": [], "related_identifiers": [], "files": [ { "id": "e702a2e5-11d5-4aeb-8924-07003e48728c", "key": "bevcyc.pdf", "size": 739198, "checksum": "md5:d4bec636a129c606a5b271d418ddb6a3", "links": { "self": "https://zenodo.org/api/records/14737076/files/bevcyc.pdf/content" } } ], "html_url": "https://zenodo.org/records/14737076", "doi_url": "https://doi.org/10.5281/zenodo.14737075", "record_url": "https://zenodo.org/records/14737075" }, { "record_id": "14737060", "doi": "10.5281/zenodo.14737059", "title": "Beacons - pre emulation of social cortex", "publication_date": "2025-01-25", "version": null, "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "djuwidja, andrew", "affiliation": "Active Inference Institute", "orcid": "0009-0006-9402-2412" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "primitive emulation of social cortex
\ncurrently only about tagging object types and labeled objects
\nin simulations and having them refer to a table of
\ncategory and response, which might include a sim of their own
\nsensitive to cues such as mood or transferable cues of
\nwhen the object type is called; then \"emulated\" in the mind
\na pulse-to-response only version of the associated objects for this purpose
\n( should update with more social cortex posits soon )
", "keywords": [], "related_identifiers": [], "files": [ { "id": "e2bb541e-8c9c-455a-9844-ed157618b204", "key": "beacons.pdf", "size": 561920, "checksum": "md5:2ddc1adc113195de7e60a1cd5d779597", "links": { "self": "https://zenodo.org/api/records/14737060/files/beacons.pdf/content" } } ], "html_url": "https://zenodo.org/records/14737060", "doi_url": "https://doi.org/10.5281/zenodo.14737059", "record_url": "https://zenodo.org/records/14737059" }, { "record_id": "14737043", "doi": "10.5281/zenodo.14737042", "title": "Con-cat-enate: pilot overview", "publication_date": "2025-01-25", "version": null, "resource_type": { "title": "Other", "type": "publication", "subtype": "other" }, "creators": [ { "name": "djuwidja, andrew", "affiliation": "Active Inference Insitute", "orcid": "0009-0006-9402-2412" }, { "name": "Friedman, Daniel", "affiliation": "Active Inference Institute", "orcid": "0000-0001-6232-9096" } ], "description": "Short overview of the concatenate amateur cat
\nCombined with Beacons Bevcyc
\nand demo 0.01 plan
", "keywords": [], "related_identifiers": [], "files": [ { "id": "b149b3f6-cbad-46d0-9b1d-3e2715c7c344", "key": "catpilot.pdf", "size": 1129982, "checksum": "md5:ba8745ca466b875d07158fdcd3ec7e8d", "links": { "self": "https://zenodo.org/api/records/14737043/files/catpilot.pdf/content" } } ], "html_url": "https://zenodo.org/records/14737043", "doi_url": "https://doi.org/10.5281/zenodo.14737042", "record_url": "https://zenodo.org/records/14737042" }, { "record_id": "23306201", "doi": "10.5281/zenodo.23306200", "title": "antropy: native multidimensional entropy and configurable complexity analysis", "publication_date": "2026-10-11", "version": "0.3.1", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute" } ], "description": "antropy v0.3.1 provides typed, configurable entropy and complexity methods for native multidimensional data, including high-dimensional sample entropy (HDSE), related local-template estimators, probability and dependence measures, ordinal measures, FFT/SVD entropy, resource planning and whole-observation inference. This software archive includes reproducible synthetic experiments, prospective power and null-calibration studies, tests, documentation, configuration plans, provenance and the methods manuscript rendered through the pinned docxology/template pipeline. Synthetic demonstrations do not establish biological sample sizes or reproduce the original HDSE paper’s empirical results. Version 0.3.1 adds an authenticated root-level copy of the rendered manuscript; the underlying scientific study snapshots retain their original producer metadata. Repository: https://github.com/docxology/antropy.
", "keywords": [ "entropy", "HDSE", "complexity", "reproducibility" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/antropy/releases/tag/v0.3.1", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "85ef3cb8-cada-4548-99dd-b62d78202923", "key": "antropy_hd-0.3.1.tar.gz", "size": 16746773, "checksum": "md5:e9b69011db390697626bac99b844c702", "links": { "self": "https://zenodo.org/api/records/23306201/files/antropy_hd-0.3.1.tar.gz/content" } }, { "id": "9416ebe5-3a6a-405c-9c53-0542225740f5", "key": "manifest.json", "size": 247596, "checksum": "md5:859a2d6f5e79f4ed20e0d2091efe551a", "links": { "self": "https://zenodo.org/api/records/23306201/files/manifest.json/content" } }, { "id": "cc4047c4-64ad-4981-8805-fff482cd2d93", "key": "release-identity.json", "size": 102371, "checksum": "md5:4e0b5c7afc9c5a07d70f833c4b34f713", "links": { "self": "https://zenodo.org/api/records/23306201/files/release-identity.json/content" } }, { "id": "f901e0fb-9e0a-4661-bad7-ed83117d3da9", "key": "antropy-methods.pdf", "size": 1817938, "checksum": "md5:c5af5f2aae4a9dbfeefb236fec50ae58", "links": { "self": "https://zenodo.org/api/records/23306201/files/antropy-methods.pdf/content" } }, { "id": "31d858b2-c481-4b11-9795-1445afc08aca", "key": "antropy_hd-0.3.1-py3-none-any.whl", "size": 53037, "checksum": "md5:d359519aa3b4bf1be5c21aa38662004f", "links": { "self": "https://zenodo.org/api/records/23306201/files/antropy_hd-0.3.1-py3-none-any.whl/content" } }, { "id": "360a6710-0462-4766-8e59-06a623de0993", "key": "antropy-v0.3.1-source.zip", "size": 17874917, "checksum": "md5:a98f8898f84e3937565e922abfe896c6", "links": { "self": "https://zenodo.org/api/records/23306201/files/antropy-v0.3.1-source.zip/content" } }, { "id": "c6b5f41a-43ba-4d92-90dd-b49c6f6e124a", "key": "release-verification.json", "size": 8816, "checksum": "md5:8fd879b9ac2f9861ed095b3dde1882bb", "links": { "self": "https://zenodo.org/api/records/23306201/files/release-verification.json/content" } }, { "id": "fea15a50-2f7c-475d-a89f-a74c6eb6191d", "key": "SHA256SUMS", "size": 628, "checksum": "md5:f242308778e7d556b7d7be17230b3de9", "links": { "self": "https://zenodo.org/api/records/23306201/files/SHA256SUMS/content" } } ], "html_url": "https://zenodo.org/records/23306201", "doi_url": "https://doi.org/10.5281/zenodo.23306200", "record_url": "https://zenodo.org/records/23306200" }, { "record_id": "22970974", "doi": "10.5281/zenodo.16903351", "title": "A template/ approach to Reproducible Generative Research: Architecture and Ergonomics from Configuration through Publication", "publication_date": "2026-09-26", "version": "v3.8.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": null } ], "description": "e2beba886 render: regenerate active_inference sheaf artifacts + receipts against fresh render\ndfe97d140 render: full receipt refresh against tracked ET manuscript (gitignore negation, 25/25 regenerated)\n3eebf194b render: regenerate template_experiment_tree outputs against post-#104 infrastructure\n472b896bb render: regenerate 4 recovered exemplars (autopoiesis, code_project, pools_rules_tools, methods_paper)\nf579e968b render: regenerate all-25 rendered outputs + validation reports + provenance receipts (release sync)\n721bd0819 docs(counts): sync counts with merged main; drop stray experiment_tree tests/init.py\n2cd451660 docs(counts): sync with merged tree after main update; drop stray experiment_tree tests/init.py\n804231a49 docs(counts): regenerate counts for merged tree; drop stray experiment_tree tests/init.py\n1f68f8ee6 test: parity gate expects --project-workers auto\n49de2598b ci: public-matrix receipt runner uses --project-workers auto\nd39f2478d fix(rendering): make manuscript hydration override timeout configurable via MANUSCRIPT_HYDRATION_TIMEOUT\n49a011cf5 fix(experiment_tree): lazy injection import so the strict contract holds on bare interpreters; refresh coverage provenance + formal receipts\n38dd40e90 fix(deps): provide pyyaml to the public-exemplars sync group (experiment_tree hydration + renderer)\n7cd234db6 fix(experiment_tree): declare pyyaml runtime dependency (hydration + renderer need it)\n8268e80d4 render: final campaign pass — experiment_tree hydration bootstrap + yaml venv fix + resolved-manuscript injection; full 25-exemplar strict audit pass\n297226d57 render: campaign receipts for all 25 public exemplars (refresh_rendered_provenance --all-public)\ne92c5fd20 chore(active_inference): stage refreshed render artifacts into the cached index\n9ad67965a chore(experiment_tree): admit web, slides, and figures render outputs for validation\n1b30b90c6 chore(experiment_tree): admit render outputs (pdf, reports receipts) for the release lane\n2825a36bf chore: ignore omp session-local state\nfbd45dc9f test(rendering): assert the probe marker inside stdout, not as the final line\n52b24bf40 chore(rendering+export): docx export bucket, drop superseded beamer escape, trim stale docs\nb6b53fc4c fix(rendering): escape & in beamer href URL arguments; widen hydration budget\nf57d6a492 chore(textbook): record receipt-runner test results\n3e5df357b test(rendering): strip UV_FROZEN from the isolated beamer safe-area probe\na6a5e7b58 chore(rendering+export): docx export bucket, drop superseded beamer escape, trim stale docs\n620da6e92 fix(rendering): escape & in beamer href URL arguments; widen hydration budget\n9d5db049c chore(textbook): record receipt-runner test results\n34488a30d counts: refresh generated COUNTS.md for current infrastructure tree\nf53f28ce5 fix(rendering): sanitize EPUB chapter XHTML before the cover-accessibility pass\nf6684565d fix(rendering): repair raw-HTML damage in EPUB chapter XHTML before package validation\n17d3b4c56 docs: add doc pair for docs/manuscript (README + AGENTS) satisfying the pair lint\n0f27e06bc docs: complete docs/ and manuscript/ compliance (docs-audit 2026-08-29)\n6e57e15de export_bundle: add docx bucket (output/docx/*.docx) for daf-press cycle-1 (dp-B16); publishing configs' exports list DOCX, exporter previously dropped it. Bucket only appears non-empty in bundles; empty-dir test updated\n83d2b4ebc chore(docs): architecture overview svg newline normalization\n500f77235 chore(exemplars): re-bind gold_refinement + textbook artifact manifests to tracked outputs after rebase\n06a85155f docs: regenerate architecture overview for the current infrastructure inventory\n37e1a7dcb docs(counts): re-sync coverage provenance + counts after rebase onto origin/main\n9ed9d8b02 chore(experiment_tree): admit the committed experiment tree as a shippable artifact\n323b9d5af chore(experiment_tree): track artifact manifest, doc-pair newline normalization\n90a0db3b8 chore(active_inference): refresh artifact manifest digests\nf2f3d17d7 fix(gold_refinement): convert src/init.py to a no-import namespace shim\n06442a73d fix(ci): re-apply chrome locate fix, bump anyio across all locks, refresh provenance\n1d12ba777 fix(roster): finish experiment_tree integration + regenerate CODEOWNERS\n9bef7b17b fix(release+roster): 3.8.0 release prep, 25-exemplar roster refresh, evidence and CI repairs\nffcef6bdd docs(publishing): document combined-artifact naming rule and leaf-link override path\n573bef7e5 fix(exemplars): experiment-tree forkability rubric + methods aggregate count 25\nfb3a8f87e fix(exemplars): complete experiment-tree registration drift; repoint pitch-deck diligence citations\nd6cebd4d5 fix(advanced): bind palette claim to the shared meta source via repository-relative path\n40cd1f562 docs(counts): refresh coverage provenance source hashes and counts after tree changes
", "keywords": [], "related_identifiers": [ { "identifier": "https://github.com/docxology/template/tree/v3.8.0", "relation": "isSupplementTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "102f065b-8fbc-47e3-b64d-81540aba53fa", "key": "docxology/template-v3.8.0.zip", "size": 135021628, "checksum": "md5:6efbec43dcd29dd2ab4519d2cd38c87e", "links": { "self": "https://zenodo.org/api/records/22970974/files/docxology/template-v3.8.0.zip/content" } } ], "html_url": "https://zenodo.org/records/22970974", "doi_url": "https://doi.org/10.5281/zenodo.16903351", "record_url": "https://zenodo.org/records/16903351" }, { "record_id": "21763245", "doi": "10.5281/zenodo.21763244", "title": "THALIA: Typed Harness with Analytical Lexical-Integrated Architecture", "publication_date": "2026-08-02", "version": "0.1.0", "resource_type": { "title": "Software", "type": "software" }, "creators": [ { "name": "Friedman, Daniel Ari", "affiliation": null } ], "description": "THALIA is an executable research harness for long-context memory systems. It combines typed stage contracts, inspectable context selection, evidence-preserving episodic state, lexical-first retrieval, and bounded compiler search with source-bound evaluation and reproducible artifact checks. The deterministic results are finite diagnostic evidence; model-quality, integrity-advantage, and production-readiness claims remain separately gated.
\nCode available at https://github.com/docxology/thalia
", "keywords": [ "agentic systems", "long-context memory", "retrieval-augmented generation", "reproducible research" ], "related_identifiers": [ { "identifier": "https://github.com/docxology/thalia", "relation": "isIdenticalTo", "resource_type": "software", "scheme": "url" } ], "files": [ { "id": "018bd1a3-8952-4e54-83c8-484bb63a0d62", "key": "thalia-0.1.0-source.tar.gz", "size": 842137, "checksum": "md5:b335e03ff5982c5222ad5505186c7312", "links": { "self": "https://zenodo.org/api/records/21763245/files/thalia-0.1.0-source.tar.gz/content" } }, { "id": "a276d5a8-f241-4b31-b6d0-dccc57ed1665", "key": "thalia-0.1.0.pdf", "size": 5005902, "checksum": "md5:8f40b5428ed4300bbc15d5df98ced972", "links": { "self": "https://zenodo.org/api/records/21763245/files/thalia-0.1.0.pdf/content" } }, { "id": "8a2a0c16-ebd9-455f-b6ab-71668c943a9b", "key": "thalia-0.1.0-artifacts.tar.gz", "size": 16736189, "checksum": "md5:2dcceb8e38a895b98af24f82923ee68b", "links": { "self": "https://zenodo.org/api/records/21763245/files/thalia-0.1.0-artifacts.tar.gz/content" } } ], "html_url": "https://zenodo.org/records/21763245", "doi_url": "https://doi.org/10.5281/zenodo.21763244", "record_url": "https://zenodo.org/records/21763244" }, { "record_id": "10360148", "doi": "10.5281/zenodo.10360056", "title": "A Natural AI Based on The Science of Computational Physics, Biology and Neuroscience: Policy and Societal Significance", "publication_date": "2023-12-12", "version": null, "resource_type": { "title": "Publication", "type": "publication" }, "creators": [ { "name": "Clippinger, John", "affiliation": "Bioform Labs" }, { "name": "de Vries, Bert", "affiliation": "Eindhoven University of Technology" }, { "name": "Noveck, Beth", "affiliation": "Northeastern University" }, { "name": "Fields, Chris", "affiliation": "Tufts University" }, { "name": "Slater, Cory", "affiliation": "Bioform Labs" }, { "name": "Friedman, Daniel Ari", "affiliation": "Active Inference Institute" }, { "name": "Silbersweig, David A.", "affiliation": "Harvard Medical School" }, { "name": "Lapenta, Francesco", "affiliation": "John Cabot University" }, { "name": "Grimm, Holly", "affiliation": "ML Engineer" }, { "name": "Emmett, Jeff", "affiliation": "BlockScience" }, { "name": "Shane, Joshua", "affiliation": "Bioform Labs" }, { "name": "Friston, Karl", "affiliation": "University College London" }, { "name": "Nkemnkia, Martin Nkafu", "affiliation": "Pontifical Lateran University, Italy" }, { "name": "Brown, Matthew", "affiliation": "ThoughtForge Inc." }, { "name": "Pirkowski, Matthew", "affiliation": "Bioform Labs" }, { "name": "Levin, Michael", "affiliation": "Levin Labs" }, { "name": "Zargham, Michael", "affiliation": "BlockScience" }, { "name": "Tuan, Nguyen Anh", "affiliation": "Boston Global Forum" }, { "name": "Achuthan, Krishnashree", "affiliation": "Amrita University" }, { "name": "Patterson, Thomas", "affiliation": "Harvard Kennedy School" }, { "name": "David, Scott L.", "affiliation": "University of Washington, Applied Physics Laboratory" }, { "name": "Kehler, Thomas", "affiliation": "CrowdSmart.ai" }, { "name": "Knight, Virginia Bleu", "affiliation": null }, { "name": "Nakayama, Yasuhide", "affiliation": "Former Japanese State Minister of Defense and Foreign Affairs" } ], "description": "Letter on: \"A Natural AI Based on The Science of Computational Physics, Biology and Neuroscience: Policy and Societal Significance\".
v1 released on December 12, 2023.
", "keywords": [ "Active Inference", "AI", "Natural", "Policy" ], "related_identifiers": [], "files": [ { "id": "d8393039-09b5-45fe-8e96-f89f9f5a0299", "key": "12-11-2023_Natural_AI_Letter_v1.1.pdf", "size": 67349, "checksum": "md5:06d514dc9e460133af3c9cb41834f629", "links": { "self": "https://zenodo.org/api/records/10360148/files/12-11-2023_Natural_AI_Letter_v1.1.pdf/content" } }, { "id": "3913d49a-53be-4a89-8513-e286d0c4ef2c", "key": "12-11-2023_Natural_AI_Letter_v1.1.docx", "size": 12406, "checksum": "md5:97577f1ca7c7e48de54e14931a5aea0e", "links": { "self": "https://zenodo.org/api/records/10360148/files/12-11-2023_Natural_AI_Letter_v1.1.docx/content" } } ], "html_url": "https://zenodo.org/records/10360148", "doi_url": "https://doi.org/10.5281/zenodo.10360056", "record_url": "https://zenodo.org/records/10360056" } ], "warnings": [], "sections": [ { "label": "ORCID work groups", "url": "https://pub.orcid.org/v3.0/0000-0001-6232-9096/works", "ok": true, "items": [ { "title": "Thoughtseeds: A Hierarchical and Agentic Framework for Investigating Thought Dynamics in Meditative States", "year": "2025", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/182842157" }, { "title": "Why Paleolithic Rockstars were both enigmatic and sporadic: A comment on: ‘Snakes and Ladders’ in paleoanthropology: From cognitive surprise to skillfulness a million years ago", "year": "2024", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/158837151" }, { "title": "Shared Protentions in Multi-Agent Active Inference", "year": "2024", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/156639002" }, { "title": "A guided tour through the spaces of particular “minds”: A Comment on “Path integrals, particular kinds, and strange things”", "year": "2023", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/146094079" }, { "title": "Distributed Science - The Scientific Process as Multi-Scale Active Inference", "year": "2023", "type": "preprint", "source": "Crossref", "path": "/0000-0001-6232-9096/work/144691944" }, { "title": "To comment or not to comment, that is the question!", "year": "2023", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/136675081" }, { "title": "A Variational Synthesis of Evolutionary and Developmental Dynamics", "year": "2023", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/137350514" }, { "title": "Open Access science needs Open Science Sensemaking (OSSm): open infrastructure for sharing scientific sensemaking data", "year": "2023", "type": "preprint", "source": "Crossref", "path": "/0000-0001-6232-9096/work/134292883" }, { "title": "Active Blockference: cadCAD with Active Inference for Cognitive Systems Modeling", "year": "2023", "type": "book-chapter", "source": "Crossref", "path": "/0000-0001-6232-9096/work/131294835" }, { "title": "The ant colony as a test for scientific theories of consciousness", "year": "2021", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/53977487" }, { "title": "The physiology of forager hydration and variation among harvester ant (Pogonomyrmex barbatus) colonies in collective foraging behavior", "year": "2019", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/55721201" }, { "title": "The Role of Dopamine in the Collective Regulation of Foraging in Harvester Ants", "year": "2018", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/48689097" }, { "title": "Partner Pen Play in Parallel (PPPiP): A New PPPiParadigm for Relationship Improvement", "year": "2018", "type": "journal-article", "source": "Multidisciplinary Digital Publishing Institute", "path": "/0000-0001-6232-9096/work/47511152" }, { "title": "Two lineages that need each other", "year": "2017", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/30693490" }, { "title": "Context-dependent expression of the foraging gene in field colonies of ants: the interacting roles of age, environment and task", "year": "2016", "type": "journal-article", "source": "Crossref", "path": "/0000-0001-6232-9096/work/26526723" }, { "title": "Ant Genetics: Reproductive Physiology, Worker Morphology, and Behavior", "year": "2016", "type": "journal-article", "source": "Crossref Metadata Search", "path": "/0000-0001-6232-9096/work/26034911" }, { "title": "Influence of nuclear structure on the formation of radiation-induced lethal lesions", "year": "2016", "type": "journal-article", "source": "Crossref Metadata Search", "path": "/0000-0001-6232-9096/work/23250259" }, { "title": "Commentary: Portuguese crypto-Jews: the genetic heritage of a complex history", "year": "2015", "type": "journal-article", "source": "Crossref Metadata Search", "path": "/0000-0001-6232-9096/work/23250252" }, { "title": "Could ehrlichial infection cause some of the changes associated with leukemia, myelodysplastic diseases and autoimmune disorders, and offer antibiotic treatment options?", "year": "2015", "type": "journal-article", "source": "Crossref Metadata Search", "path": "/0000-0001-6232-9096/work/23250253" }, { "title": "Large-Scale Coding Sequence Change Underlies the Evolution of Postdevelopmental Novelty in Honey Bees", "year": "2014", "type": "journal-article", "source": "Crossref Metadata Search", "path": "/0000-0001-6232-9096/work/23250256" } ] }, { "label": "Crossref ORCID DOI records", "url": "https://api.crossref.org/works?filter=orcid:0000-0001-6232-9096&rows=100", "ok": true, "items": [ { "title": "Active Blockference: cadCAD with Active Inference for Cognitive Systems Modeling", "doi": "10.1007/978-3-031-28719-0_10", "published": { "date-parts": [ [ 2023 ] ] }, "container": "Communications in Computer and Information Science", "type": "book-chapter" }, { "title": "To comment or not to comment, that is the question!", "doi": "10.1016/j.plrev.2023.06.002", "published": { "date-parts": [ [ 2023, 9 ] ] }, "container": "Physics of Life Reviews", "type": "journal-article" }, { "title": "A Variational Synthesis of Evolutionary and Developmental Dynamics", "doi": "10.3390/e25070964", "published": { "date-parts": [ [ 2023, 6, 21 ] ] }, "container": "Entropy", "type": "journal-article" }, { "title": "The Role of Dopamine in the Collective Regulation of Foraging in Harvester Ants", "doi": "10.1016/j.isci.2018.09.001", "published": { "date-parts": [ [ 2018, 10 ] ] }, "container": "iScience", "type": "journal-article" }, { "title": "A guided tour through the spaces of particular “minds”: A Comment on “Path integrals, particular kinds, and strange things”", "doi": "10.1016/j.plrev.2023.11.001", "published": { "date-parts": [ [ 2023, 12 ] ] }, "container": "Physics of Life Reviews", "type": "journal-article" }, { "title": "Why Paleolithic Rockstars were both enigmatic and sporadic: A comment on: ‘Snakes and Ladders’ in paleoanthropology: From cognitive surprise to skillfulness a million years ago", "doi": "10.1016/j.plrev.2024.04.010", "published": { "date-parts": [ [ 2024, 9 ] ] }, "container": "Physics of Life Reviews", "type": "journal-article" }, { "title": "Shared Protentions in Multi-Agent Active Inference", "doi": "10.3390/e26040303", "published": { "date-parts": [ [ 2024, 3, 29 ] ] }, "container": "Entropy", "type": "journal-article" }, { "title": "Partner Pen Play in Parallel (PPPiP): A New PPPiParadigm for Relationship Improvement", "doi": "10.3390/arts7030039", "published": { "date-parts": [ [ 2018, 8, 13 ] ] }, "container": "Arts", "type": "journal-article" }, { "title": "Distributed Science - The Scientific Process as Multi-Scale Active Inference", "doi": "10.31219/osf.io/dnw5k", "published": { "date-parts": [ [ 2023, 10, 17 ] ] }, "container": "", "type": "posted-content" }, { "title": "The physiology of forager hydration and variation among harvester ant (Pogonomyrmex barbatus) colonies in collective foraging behavior", "doi": "10.1038/s41598-019-41586-3", "published": { "date-parts": [ [ 2019, 3, 26 ] ] }, "container": "Scientific Reports", "type": "journal-article" }, { "title": "Thoughtseeds: A Hierarchical and Agentic Framework for Investigating Thought Dynamics in Meditative States", "doi": "10.3390/e27050459", "published": { "date-parts": [ [ 2025, 4, 24 ] ] }, "container": "Entropy", "type": "journal-article" }, { "title": "Context-dependent expression of the\n foraging\n gene in field colonies of ants: the interacting roles of age, environment and task", "doi": "10.1098/rspb.2016.0841", "published": { "date-parts": [ [ 2016, 8, 31 ] ] }, "container": "Proceedings of the Royal Society B: Biological Sciences", "type": "journal-article" }, { "title": "Two lineages that need each other", "doi": "10.1111/mec.13964", "published": { "date-parts": [ [ 2017, 2 ] ] }, "container": "Molecular Ecology", "type": "journal-article" }, { "title": "Open Access science needs Open Science Sensemaking (OSSm): open infrastructure for sharing scientific sensemaking data", "doi": "10.31222/osf.io/9nb3u", "published": { "date-parts": [ [ 2023, 5, 3 ] ] }, "container": "", "type": "posted-content" }, { "title": "The ant colony as a test for scientific theories of consciousness", "doi": "10.1007/s11229-019-02130-y", "published": { "date-parts": [ [ 2021, 2 ] ] }, "container": "Synthese", "type": "journal-article" } ] }, { "label": "Zenodo exact-name creator records", "url": "https://zenodo.org/api/records?q=metadata.creators.person_or_org.name%3A%22Friedman%2C+Daniel+Ari%22&size=25&sort=mostrecent", "ok": true, "items": [ { "title": "Generalized_Notation_Notation (GNN)", "doi": "10.5281/zenodo.23551166", "publication_date": "2026-10-22", "resource_type": "software", "version": "v4.3.0" }, { "title": "Active Assembly Theory and Practice", "doi": "10.5281/zenodo.23484108", "publication_date": "2026-10-19", "resource_type": "software", "version": "0.1.0" }, { "title": "iTrace: verification-first webcam eye-movement analysis (corrected manuscript)", "doi": "10.5281/zenodo.23419306", "publication_date": "2026-10-16", "resource_type": "software", "version": "manuscript-2026-10-16-310be17" }, { "title": "iTrace: verification-first webcam eye-movement analysis", "doi": "10.5281/zenodo.23404029", "publication_date": "2026-10-15", "resource_type": "software", "version": "0.5.0" }, { "title": "Active Inference as a Meta-Pragmatic Framework: Executable Models, Evidence, and the Discipline of Revision", "doi": "10.5281/zenodo.23397453", "publication_date": "2026-10-15", "resource_type": "publication", "version": "1.0.0" }, { "title": "Realizing Emptiness", "doi": "10.5281/zenodo.23383319", "publication_date": "2026-10-15", "resource_type": "software", "version": "3.0.0" }, { "title": "antropy: native multidimensional entropy and configurable complexity analysis", "doi": "10.5281/zenodo.23306201", "publication_date": "2026-10-11", "resource_type": "software", "version": "0.3.1" }, { "title": "Ento-Linguistics: Language, Ambiguity, and Scientific Communication in Entomology", "doi": "10.5281/zenodo.23287623", "publication_date": "2026-10-10", "resource_type": "publication", "version": "1.3.1" }, { "title": "daf-jev: Modular Decision Models, Orchestration, and Reproducible Evaluation", "doi": "10.5281/zenodo.23270982", "publication_date": "2026-10-09", "resource_type": "software", "version": "0.7.2" }, { "title": "Skillarum: Conditionally Reproducible Website-to-Agent-Skill Compilation", "doi": "10.5281/zenodo.23271010", "publication_date": "2026-10-09", "resource_type": "software", "version": "0.3.1" }, { "title": "Towards Lean 4 Formalization of the Free Energy Principle: AI-Driven Theorem Sketching and Verification for Active Inference and Bayesian Mechanics", "doi": "10.5281/zenodo.23220027", "publication_date": "2026-10-07", "resource_type": "publication", "version": "1.6.0" }, { "title": "fep_formal: Towards Lean 4 Formalization of the Free Energy Principle", "doi": "10.5281/zenodo.23225872", "publication_date": "2026-10-08", "resource_type": "software", "version": "v1.6.0" }, { "title": "CogSecSkills: Multiharness Agentic Skills for Cognitive Security", "doi": "10.5281/zenodo.23090954", "publication_date": "2026-10-01", "resource_type": "software", "version": "1.8.0" }, { "title": "A template/ approach to Reproducible Generative Research: Architecture and Ergonomics from Configuration through Publication", "doi": "10.5281/zenodo.22970974", "publication_date": "2026-09-26", "resource_type": "software", "version": "v3.8.0" }, { "title": "Robust Belief Sharing in Federated Active Inference: A Recovery-Tested Generalized-Variational Framework for Categorical Contamination-Aware Consensus", "doi": "10.5281/zenodo.22149133", "publication_date": "2026-09-19", "resource_type": "software", "version": "1.1.0" }, { "title": "The Witness Register: Co-Registration Without Aggregation", "doi": "10.5281/zenodo.22833511", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.1.1" }, { "title": "The Line Set: Holding Instruments Apart", "doi": "10.5281/zenodo.22833507", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.2.0" }, { "title": "Golden Line: Toward What Matters", "doi": "10.5281/zenodo.22833506", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.4.1" }, { "title": "Black Line: Strong Work in Public", "doi": "10.5281/zenodo.22833503", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.4.1" }, { "title": "Green Line: a capacity-under-development instrument", "doi": "10.5281/zenodo.22833492", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.1.0" }, { "title": "The Blue Line: A Stewardship Instrument for Maintained Commitments", "doi": "10.5281/zenodo.22833490", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.1.0" }, { "title": "The Violet Line: A Consent Ledger of Affected Parties", "doi": "10.5281/zenodo.22833488", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.1.0" }, { "title": "The Silver Line: A Memory-and-Succession Instrument", "doi": "10.5281/zenodo.22833486", "publication_date": "2026-09-18", "resource_type": "publication", "version": "0.1.0" }, { "title": "Cognitive Diagrams: Reviewing Categorical Accounts of Linguistic Case", "doi": "10.5281/zenodo.22774403", "publication_date": "2026-09-15", "resource_type": "publication", "version": "2.7.0" }, { "title": "Cognitive Diagrams: Reviewing Categorical Accounts of Linguistic Case", "doi": "10.5281/zenodo.22760881", "publication_date": "2026-09-14", "resource_type": "software", "version": "2.6.0" }, { "title": "Agentic Security and Operating Systems: A Deep Review and Prospectus of OpSec, Cognitive Security, and Agentic Cyber Security", "doi": "10.5281/zenodo.22754352", "publication_date": "2026-09-14", "resource_type": "publication", "version": "" }, { "title": "EvoJump: A Comprehensive Framework for Evolutionary Ontogenetic Analysis", "doi": "10.5281/zenodo.22667290", "publication_date": "2026-09-08", "resource_type": "software", "version": "0.5.2" }, { "title": "EvoJump: A Comprehensive Framework for Evolutionary Ontogenetic Analysis", "doi": "10.5281/zenodo.22667291", "publication_date": "2026-09-08", "resource_type": "software", "version": "0.5.2" }, { "title": "Cognitive Integrity Framework: Practical Applications and Deployment Guide (Part 3: Practitioner Guidance and Cross-Domain CIF-AD-OODA Applications)", "doi": "10.5281/zenodo.22134548", "publication_date": "2026-08-26", "resource_type": "publication", "version": "2.0" }, { "title": "Cognitive Integrity Framework: Computational Validation and Empirical Analysis (Part 2 of 3: Implementation, Empirical Analysis, and Adversarial Evaluation)", "doi": "10.5281/zenodo.22134546", "publication_date": "2026-08-26", "resource_type": "publication", "version": "2.0" }, { "title": "Cognitive Integrity Framework: Formal Foundations (Part 1 of 3: Theoretical Foundations)", "doi": "10.5281/zenodo.22134544", "publication_date": "2026-08-26", "resource_type": "publication", "version": "2.0" }, { "title": "docxplus — the Intelligent Document Container", "doi": "10.5281/zenodo.21985580", "publication_date": "2026-08-17", "resource_type": "software", "version": "1.0.1" }, { "title": "Active Skillference: A Validated Prerequisite Graph, Computational Claim Registry, and SkillTree Delivery Contract", "doi": "10.5281/zenodo.21865644", "publication_date": "2026-08-10", "resource_type": "software", "version": "1.0.0" }, { "title": "THALIA: Typed Harness with Analytical Lexical-Integrated Architecture", "doi": "10.5281/zenodo.21763245", "publication_date": "2026-08-02", "resource_type": "software", "version": "0.1.0" }, { "title": "White Line: A Typed Ledger for the Edge of the Claim", "doi": "10.5281/zenodo.21754242", "publication_date": "2026-08-02", "resource_type": "publication", "version": "0.7.0" }, { "title": "Personal Red Lines for Development", "doi": "10.5281/zenodo.21754240", "publication_date": "2026-08-02", "resource_type": "publication", "version": "0.3.0" }, { "title": "Active Inference Power Suite: Conditional Statistical Power under Controlled Generative Settings", "doi": "10.5281/zenodo.21695161", "publication_date": "2026-07-29", "resource_type": "publication", "version": "1.0.0" }, { "title": "SynthOBS & FractiSynth: A Golden-Ratio OBS Broadcast Console and Native Transducer", "doi": "10.5281/zenodo.21418953", "publication_date": "2026-07-17", "resource_type": "software", "version": "v1.618.0" }, { "title": "SynthOBS & FractiSynth: A Golden-Ratio OBS Broadcast Console and Native Transducer", "doi": "10.5281/zenodo.21418901", "publication_date": "2026-07-17", "resource_type": "software", "version": "1.618.0" }, { "title": "Mapping William Blake's Works: Evidence ledgers, source provenance, text-image diagnostics, and rights-bounded release controls", "doi": "10.5281/zenodo.21047574", "publication_date": "2026-06-29", "resource_type": "publication", "version": "" }, { "title": "Realizing Emptiness: Operational Surrogates for No-Self-Evidence, QRF Opacification, and Bayesian Model Reduction", "doi": "10.5281/zenodo.20834847", "publication_date": "2026-06-24", "resource_type": "publication", "version": "1.0.0" }, { "title": "COGANT: Deterministic Codebase-to-GNN Translation", "doi": "10.5281/zenodo.20705351", "publication_date": "2026-06-15", "resource_type": "publication", "version": "0.6.0" }, { "title": "DemoCreate: Declarative Audio-Visual Demo Generation for Software", "doi": "10.5281/zenodo.20693217", "publication_date": "2026-06-04", "resource_type": "software", "version": "0.6.2" }, { "title": "ENTO: an ENcrypted, Typed, Omnitrack container format for multimodal research data", "doi": "10.5281/zenodo.20647443", "publication_date": "2026-06-11", "resource_type": "software", "version": "0.4" }, { "title": "BeeStack: An Evidence-Typed Scaffold for Whole-Colony Honeybee Simulation", "doi": "10.5281/zenodo.20420557", "publication_date": "2026-05-27", "resource_type": "software", "version": "1.0" }, { "title": "Introduction to Biology: A Generative Approach", "doi": "10.5281/zenodo.20286478", "publication_date": "2026-05-26", "resource_type": "publication", "version": "1.0.0" }, { "title": "The Architecture of False Gods: William Blake, Professor Jiang, and the Active Inference Corrective to Single Vision", "doi": "10.5281/zenodo.20144984", "publication_date": "2026-05-12", "resource_type": "publication", "version": "v1" }, { "title": "A Living Meta-Analysis Architecture for Active Inference: Assertion Extraction, Nanopublications, and Hypothesis Scoring", "doi": "10.5281/zenodo.19897664", "publication_date": "2026-04-30", "resource_type": "publication", "version": "v2" }, { "title": "The Golden Compass and the Lunar Flux: William Blake, Bimetallic Meta-stability, and the Architecture of Value", "doi": "10.5281/zenodo.19335196", "publication_date": "2026-04-03", "resource_type": "publication", "version": "v1" }, { "title": "A template/ approach to Reproducible Generative Research: Architecture and Ergonomics from Configuration through Publication", "doi": "10.5281/zenodo.19139090", "publication_date": "2026-03-20", "resource_type": "publication", "version": "v1" }, { "title": "Before Pragmatism Had a Name: Blake's \"America A Prophecy\" Anticipates American Anticipatory Epistemology", "doi": "10.5281/zenodo.18984939", "publication_date": "2026-03-12", "resource_type": "publication", "version": "" }, { "title": "The Doors of Perception are the Threshold of Prediction: Active Inference and William Blake's Theory of Seeing", "doi": "10.5281/zenodo.18600041", "publication_date": "2026-02-12", "resource_type": "publication", "version": "v1" }, { "title": "The Ant Stack", "doi": "10.5281/zenodo.16782757", "publication_date": "2025-08-08", "resource_type": "other", "version": "v1.0" }, { "title": "On Cognitive Art & Science: Toward Wholeness From Both Sides", "doi": "10.5281/zenodo.16740439", "publication_date": "2025-08-04", "resource_type": "other", "version": "1.0" }, { "title": "CEREBRUM: Case-Enabled Reasoning Engine with Bayesian Representations for Unified Modeling", "doi": "10.5281/zenodo.15231156", "publication_date": "2025-04-16", "resource_type": "publication", "version": "1.4" }, { "title": "On Time", "doi": "10.5281/zenodo.15168382", "publication_date": "2025-04-07", "resource_type": "other", "version": "1.0" }, { "title": "MathArt Stream #8 ~ William Blake and Active Inference", "doi": "10.5281/zenodo.13711302", "publication_date": "2024-09-06", "resource_type": "presentation", "version": "" }, { "title": "Aligning Active Inference Ontology to SUMO", "doi": "10.5281/zenodo.11463326", "publication_date": "2024-06-03", "resource_type": "publication", "version": "" }, { "title": "Four-fold Fields of Quantum Dreams", "doi": "10.5281/zenodo.10798145", "publication_date": "2024-03-08", "resource_type": "publication", "version": "v1" }, { "title": "Push and Pull: A priming sequence", "doi": "10.5281/zenodo.10659375", "publication_date": "2024-02-14", "resource_type": "publication", "version": "1.0" }, { "title": "Way Finding in the Infinite Imaginarium: Juxtaposing Epistemic Tempos and Modes", "doi": "10.5281/zenodo.10601082", "publication_date": "2024-01-31", "resource_type": "publication", "version": "1.0" }, { "title": "Transcript of Chris Fields, \"Physics as Information Processing\" course in 2023", "doi": "10.5281/zenodo.10447643", "publication_date": "2023-12-31", "resource_type": "lesson", "version": "v1" }, { "title": "A snapshot and pipeline for tissue-specific gene expression meta-analysis in honey bees (Apis mellifera)", "doi": "10.5281/zenodo.10400745", "publication_date": "2023-12-18", "resource_type": "publication", "version": "v1.0" }, { "title": "A Natural AI Based on The Science of Computational Physics, Biology and Neuroscience: Policy and Societal Significance", "doi": "10.5281/zenodo.10360148", "publication_date": "2023-12-12", "resource_type": "publication", "version": "" }, { "title": "Enhanced NSF Postdoctoral Reporting via Synthetic Intelligence Language Processing", "doi": "10.5281/zenodo.10160657", "publication_date": "2023-11-20", "resource_type": "publication", "version": "v1" }, { "title": "Cognitive Sovereignty & Active Inference in the State of Exception", "doi": "10.5281/zenodo.10038232", "publication_date": "2023-10-24", "resource_type": "publication", "version": "v1.1" }, { "title": "The Properties, Processes, and Perspectives Inter-Framework (P3IF): Multiplexing interdisciplinary requirements frameworks to manage information risk and foster cognitive security", "doi": "10.5281/zenodo.10034512", "publication_date": "2023-10-23", "resource_type": "publication", "version": "" }, { "title": "An Account of Active Inference Modeling", "doi": "10.5281/zenodo.8415313", "publication_date": "2023-10-06", "resource_type": "publication", "version": "v1.0" }, { "title": "Postdoc review (2020-2023) ~ September 25, 2023", "doi": "10.5281/zenodo.8377988", "publication_date": "2023-09-25", "resource_type": "presentation", "version": "v1.0" }, { "title": "Of Ants & Aging", "doi": "10.5281/zenodo.7855582", "publication_date": "2023-04-22", "resource_type": "presentation", "version": "v1" }, { "title": "Slides for Iris", "doi": "10.5281/zenodo.7838653", "publication_date": "2023-04-17", "resource_type": "publication", "version": "1" }, { "title": "Generalized Notation Notation for Active Inference Models", "doi": "10.5281/zenodo.7803328", "publication_date": "2023-04-05", "resource_type": "publication", "version": "v1" }, { "title": "Systems Modeling and Cognitive Audits for Hypercert Ecosystems", "doi": "10.5281/zenodo.7626769", "publication_date": "2022-10-26", "resource_type": "publication", "version": "v1" }, { "title": "William Blake & Buckminster Fuller: Lives in Juxtaposition (A study in Comprehensivity)", "doi": "10.5281/zenodo.7519132", "publication_date": "2023-01-08", "resource_type": "presentation", "version": "2" }, { "title": "Transcript of: Mark Solms, \"Consciousness as Precision Optimization: Some Physiological and Philosophical Considerations\", ActInf GuestStream #016", "doi": "10.5281/zenodo.7267947", "publication_date": "2022-10-27", "resource_type": "publication", "version": "1.1" }, { "title": "Transcript of: Karl Friston, 1st Applied Active Inference Symposium, Active Inference Lab, June 21, 2021", "doi": "10.5281/zenodo.5797072", "publication_date": "2021-12-21", "resource_type": "publication", "version": "v2.0" }, { "title": "Active Inference & Behavior Engineering for Teams", "doi": "10.5281/zenodo.4021163", "publication_date": "2020-09-09", "resource_type": "publication", "version": "1" } ], "total": 77 } ] }