research-evidence-agent

KO | EN

gitlite — search

#javascript #ai #golang #android #docker #macos #nodejs #java #windows #cli #awesome-list #pytorch #security #open-source

research-evidence-agent

(★ 15)

Local-first provenance manifests and optional AI audits for research evidence bundles

research-evidence-agent 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# research-evidence-agent

`research-evidence-agent` is a local-first provenance and claim–evidence audit
tool for computational and experimental research bundles.

It keeps four evidence layers explicit:

- raw experiment;
- reprocessed data;
- model output or inference; and
- synthetic illustration.

The deterministic core creates SHA-256 manifests, applies user-reviewable path
rules, flags unclassified or sensitive-looking files, and checks whether a claim
ledger cites evidence of a compatible type. It never interprets scientific values.

An optional OpenAI Agents SDK layer can review aggregate counts and issue codes.
By default, the agent receives neither file contents nor individual filenames.

## Quick start

```bash
python -m pip install -e ".[dev]"
research-evidence-agent demo --output-dir outputs/demo-bundle
pytest
```

Scan a real local bundle without uploading it:

```bash
research-evidence-agent scan ./my-study --output manifest.json
research-evidence-agent audit manifest.json claims.json
```

## Claim ledger

```json
{
  "claims": [
    {
      "id": "claim-1",
      "text": "A directly observed trend.",
      "claim_type": "observation",
      "evidence": ["ev-0123456789ab"]
    }
  ]
}
```

An `observation` without raw evidence fails. Model-only support cannot be silently
rewritten as an observation. Warnings and errors are machine-readable so the tool
can run in CI before a report or data package is released.

## Optional OpenAI agent

```bash
python -m pip install -e ".[agent]"
export OPENAI_API_KEY="..."
export OPENAI_MODEL="gpt-5.6-terra"
research-evidence-agent agent ./my-study
```

The Agents SDK wraps one aggregate-only function tool. The model organizes the
risk report; deterministic code owns hashing, classification and validation. See
[the agent boundary](docs/agent-boundary.md).

## Scope boundary

This package helps prevent category errors and provenance loss. It does not prove
that an experiment is correct, a model is valid, a paper claim is causal, or a
dataset may legally be redistributed. Human domain review remains required.

BSD-3-Clause licensed.

## AI × engineering × research portfolio

Companion repositories:

- [`tailaware-rve`](https://github.com/zxxasdfrty/tailaware-rve) — tail-aware
  scientific surrogate diagnostics;
- [`engineering-run-agent`](https://github.com/zxxasdfrty/engineering-run-agent) —
  read-only solver and scheduler triage; and
- [`synthetic-gpa-agent`](https://github.com/zxxasdfrty/synthetic-gpa-agent) —
  synthetic microscopy-method validation.

research-evidence-agent

research-evidence-agent 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

research-evidence-agent

research-evidence-agent 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README