bhargavchintam/aureproof - 4 Help Wanted Issues

Open Issues Need Help

AP-048: Appoint the independent reviewer and agree review cadence 6 days ago

help wanted P0 adr

An open-source integrity layer for AI-agent evaluations: task-health records, signed re-scorable evidence bundles, and pre-registered pass/fail/inconclusive regression decisions.

Python

#ai-agents#ai-evaluation#attestation#benchmark#evaluation#in-toto#llm-evaluation#python#reproducibility#security#sigstore

AP-050: Finish Code of Conduct reporting contact and license provenance 7 days ago

help wanted P0 policy

bhargavchintam/aureproof

An open-source integrity layer for AI-agent evaluations: task-health records, signed re-scorable evidence bundles, and pre-registered pass/fail/inconclusive regression decisions.

Python

#ai-agents#ai-evaluation#attestation#benchmark#evaluation#in-toto#llm-evaluation#python#reproducibility#security#sigstore

AP-056: Validate task health or the gate on a design partner's own logs 21 days ago

help wanted P0 research

bhargavchintam/aureproof

An open-source integrity layer for AI-agent evaluations: task-health records, signed re-scorable evidence bundles, and pre-registered pass/fail/inconclusive regression decisions.

Python

#ai-agents#ai-evaluation#attestation#benchmark#evaluation#in-toto#llm-evaluation#python#reproducibility#security#sigstore

AP-049: Qualify a dedicated Linux evaluation host 21 days ago

help wanted P0 security

bhargavchintam/aureproof

An open-source integrity layer for AI-agent evaluations: task-health records, signed re-scorable evidence bundles, and pre-registered pass/fail/inconclusive regression decisions.

Python

#ai-agents#ai-evaluation#attestation#benchmark#evaluation#in-toto#llm-evaluation#python#reproducibility#security#sigstore