# SPC-07 Versioned evaluation set

Domain: SPC Agent Specification & Pre-Deployment Assurance · HI-AAF v1.3 · Public review · https://humanintel.net/standard/spc/spc-07

A versioned evaluation set is maintained per agent and re-executed on every material change. Results are retained as evidence.

Each agent has a versioned evaluation set that is maintained alongside the agent's specification. The evaluation set is re-executed on every material change, and results are retained as evidence. The evaluation set evolves as new failure modes are discovered, ensuring that previously identified risks remain covered.

## Maturity

- L1 Ad hoc: Controls exist informally; documentation is incomplete; no consistent review.
- L2 Documented: Controls are written down; ownership is assigned; review cadence is defined.
- L3 Operated: Controls are followed in practice; evidence is collected; deviations are tracked. Published criterion for SPC-07: Evaluation set is version-controlled; execution history shows re-runs on material changes; results are retained and accessible for audit; the set has been updated to cover newly discovered failure modes.
- L4 Measured: Control effectiveness is measured against documented thresholds; trends are reported.
- L5 Continuously Improved: Controls evolve based on incident learning; maturity gains are evidenced over time.

## Evidence an assessor asks for

- Evaluation set is version-controlled.
- Execution history shows re-runs on material changes.
- Results are retained and accessible for audit.
- The set has been updated to cover newly discovered failure modes.

## Framework mappings

- NIST AI RMF: MANAGE 3.1, MANAGE 3.2
- ISO/IEC 42001: A.6.2.6
- SOC 2 (TSC): CC8.1, CC8.2
- EU AI Act: Art. 9(7)
- Singapore: MAIGF Testing & Assurance, AI Verify Reproducibility

Mappings are directional: meeting this control evidences but does not by itself satisfy the external requirement.

## Related

- Cited by OUT-12 Model version pinning: https://humanintel.net/standard/out/out-12
- Cited by MON-08 Post-incident learning loop: https://humanintel.net/standard/mon/mon-08
- Glossary: Material change: https://humanintel.net/standard/glossary#material-change

## Cite this control

Human Intelligence. HI-AAF v1.3, SPC-07 Versioned evaluation set. Public review edition, July 2026. https://humanintel.net/standard/spc/spc-07