---
# docxology:generated-document SKILL.md; ownership=explicit-manifest
name: "Active Inference Multi-Track Exemplar"
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..."
tags: ["active-inference", "pymdp", "sophisticated-inference", "generalized-notation-notation", "lean"]
domain: "Computational"
citation: "Daniel Ari Friedman (2026). *Active Inference Multi-Track Exemplar*. Zenodo."
doi: "10.5281/zenodo.20417021"
---

# Active Inference Multi-Track Exemplar

**Daniel Ari Friedman** (2026) · Computational

## Context

This work addresses topics in **Computational**: active inference, pymdp, sophisticated inference, generalized notation notation.

## Methods

Primary methods and techniques applied in this work:

- **Bernoulli–Ising analytical oracle (K=2)** — Closed-form mutual information and free-energy decomposition on a symmetric Bernoulli–Ising toy, cross-checked by an independent exact recomputation via total correlation.
- **Deterministic pymdp T-maze rollout** — A minimal T-maze following pymdp sophisticated_inference examples, defaulting to state_inference with planning horizon policy_len = 2 and logged beliefs and actions.
- **Sheaf-indexed manuscript compose contract** — Binds 34 composable fragment types to manifest rows under an IMRAD outline, verifying sheaf axioms and negative controls before rendering.
- **Lean boundary-witness formalization** — Lean modules checked by lake build state small finite T-maze and graph-world witnesses, with axioms audited via #print axioms; explicitly not a broad formalization.
- **Artifact-hydrated reporting with validation gates** — Every reported number is hydrated from generated artifacts and cross-track claims are machine-checked by pipeline gates before the PDF is built.

## Key Findings

Core contributions and results:

- The paper frames its result as a methodological discipline rather than a domain claim: 6 sheaf axioms are machine-checked and 25 negative controls keep failure paths live.
- It reports 12/12 invariant checks passed and a sweep RMSE of 0 nats between analytical and empirical values on the coupling grid.
- The measured state_inference T-maze rollout reports mean belief entropy 0.3251 nats over 2 steps, with goal reached and action diversity 2.
- A coverage audit reports 95 present, 95 bound, and 0 missing cells on the IMRAD matrix.
- The author states the models are pedagogical and validate consistency and artifact wiring, not empirical claims about biological agents.

Methods and findings are summarized from the full text; each item is backed by a verbatim quote recorded in `metadata.json` (`evidence`, `key_findings_evidence`).

## Related Works

- [2023_NSFReporting](../2023_NSFReporting/)
- [2023_NaturalAIBased](../2023_NaturalAIBased/)
- [2025_AuBI](../2025_AuBI/)

## Validation

Verification points for this work:

- Canonical DOI: 10.5281/zenodo.20417021
- PDF SHA-256: f191b48f94394cab17069fd04502c59fc1c287e7893eb078e05ba4be04d4a04c
- Pairing confidence: strong
- Last checked: 2026-09-24T18:29:54Z

## Prerequisites

- Familiarity with active inference, pymdp, sophisticated inference
- Background in Computational fundamentals
- Access to source repository: docxology/template_active_inference

## Instructions

When working with this paper:

1. Reference the DOI for citation: `10.5281/zenodo.20417021`
2. Apply methods listed in the Methods section for related analysis.
3. Validate findings against the original PDF and metadata.
