---
name: "Bounded AutoResearch for a Tiny Reproducible Machine-Learning Task"
description: "This paper presents Deterministic bounded AutoResearch for a small MNIST neural-network task, a public template exemplar that turns an AutoResearch loop into ordinary reproducible research infrastructure. The case study is intentionally small but con..."
tags: ["autoresearch", "reproducible-research", "machine-learning-benchmark", "artifact-readiness", "human-review", "local-artifact-integrity"]
domain: "Computational"
citation: "Daniel Ari Friedman (2026). *Bounded AutoResearch for a Tiny Reproducible Machine-Learning Task*. Computational."
doi: "10.5281/zenodo.20417016"
---

# Bounded AutoResearch for a Tiny Reproducible Machine-Learning Task

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

## Context

This work addresses topics in **Computational**: autoresearch, reproducible research, machine learning benchmark, artifact readiness.

## Methods

Primary methods and techniques applied in this work:

- Software pipeline design
- Data-driven analysis

## Key Findings

Core contributions and results:

- This paper presents Deterministic bounded AutoResearch for a small MNIST neural-network task, a public template exemplar that
turns an AutoResearch loop into ordinary reproducible research infrastruct
- The case study is intentionally small but concrete: 2000 training
and 500 test images from MNIST handwritten digit database are evaluated by the
bounded small MNIST neural-network classification loop.

## Related Works

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

## Validation

Verification points for this work:

- DOI: 10.5281/zenodo.20417016
- PDF SHA-256: e07b62850a1995935283d37a45c21d71fa7c4e69cdcc451c5a1ea8aee6d0c94a
- Pairing confidence: strong
- Last checked: 2026-07-01T00:30:08Z

## Prerequisites

- Familiarity with autoresearch, reproducible research, machine learning benchmark
- Background in Computational fundamentals
- Access to source repository: N/A

## Instructions

When working with this paper:

1. Reference the DOI for citation: `10.5281/zenodo.20417016`
2. Apply methods listed in the Methods section for related analysis.
3. Validate findings against the original PDF and metadata.