Evidently generates evaluation reports and monitoring data for ML/LLM systems. Proposing an asqav integration that cryptographically signs these outputs.
Value: When you run an evaluation or monitoring check, the results get signed with ML-DSA-65 (quantum-safe, NIST FIPS 204). This creates verifiable proof that a specific evaluation happened, with specific results, at a specific time - exactly what auditors need for EU AI Act, SOC2, and HIPAA compliance.
Implementation: Could work as a post-evaluation hook that signs report snapshots before storage.
Evidently generates evaluation reports and monitoring data for ML/LLM systems. Proposing an asqav integration that cryptographically signs these outputs.
Value: When you run an evaluation or monitoring check, the results get signed with ML-DSA-65 (quantum-safe, NIST FIPS 204). This creates verifiable proof that a specific evaluation happened, with specific results, at a specific time - exactly what auditors need for EU AI Act, SOC2, and HIPAA compliance.
Implementation: Could work as a post-evaluation hook that signs report snapshots before storage.