The diff that matters
Process Evidence Diff
Same final approval, different governed path. Agent Assure compares the process evidence around the decision, not just the visible answer.
Baseline Process
claim-duration→evidence-duration
✓ material claim has evidence
Candidate Process
claim-duration→none
✕ material claim evidence link missing
CI Gate
control response→blocked
■ candidate blocked
Key Finding
1 material claim link regression
The candidate preserved the visible decision fields but dropped a required material-claim evidence link. This is a link-level regression: the source evidence may still be present for another claim.
| Case | Material claim | Baseline link | Candidate link | Reason |
shared-source-multi-claim | claim-duration
| claim-duration → evidence-duration
| claim-duration → none
| MATERIAL_CLAIM_MISSING_EVIDENCE
|
Process-affected cases are sourced from candidate findings and missing material-claim evidence links, not from preserved decision fields.
| Case | Process status | Decision fields | Changed fields | Process findings | Claim-evidence links |
shared-source-multi-claim | failed invariant | preserved | evidence refs, claim-evidence links
| 1 material claim link regression
MATERIAL_CLAIM_MISSING_EVIDENCE | Baselineclaim-duration → evidence-durationCandidate- claim-duration → none |
Decision preserved, process failed
Visible Output Stayed Stable
The business decision did not change. The governance evidence around that decision did.
Decision-Field Comparison
- Decision fields (recommendation, outcome)
- preserved
- Case coverage
- same case IDs
- Baseline evaluation state
- pass
- Candidate evaluation state
- fail
| Case | Baseline recommendation | Candidate recommendation | Baseline outcome | Candidate outcome | Decision fields |
| shared-source-multi-claim | approve | approve | approve | approve | preserved |
Process Invariant Findings
| Case | Control | Target | Reason code | State | Message |
| shared-source-multi-claim | material_claims_have_evidence | claim:claim-duration | MATERIAL_CLAIM_MISSING_EVIDENCE | fail | fixture-declared material claim has no evidence link |
Technical appendix
Before and After Traceability Detail
Engineers can inspect claim IDs, evidence refs and sources, linked evidence, policy states, provider/model fields, tool names, operational counters, and measured usage summaries used in the run.
Missing Evidence Link Diff
| Case | Claim | Baseline evidence refs | Candidate evidence refs |
| shared-source-multi-claim | claim-duration | evidence-duration | none |
Full Baseline Process Evidence
| Case | Claims | Evidence refs | Linked claims | Policy states | Human review | Provider/model | Tools | Operational metrics | Measured usage |
shared-source-multi-claim | claim-duration
| evidence-duration source=guideline-duration
| claim-duration
| none | not required | not recorded | benefit-policy-lookup
| not recorded | not observed |
Full Candidate Process Evidence
| Case | Claims | Evidence refs | Linked claims | Policy states | Human review | Provider/model | Tools | Operational metrics | Measured usage |
shared-source-multi-claim | claim-duration
| none | none | none | not required | not recorded | benefit-policy-lookup
| not recorded | not observed |
Evidence packet appendix
Release Evidence for Review
Fixture equivalence, artifact paths, and SHA-256 digests make the blocking decision reproducible without exposing local machine paths.
Comparison Classification
- Classification
- new_failure
- Baseline state
- pass
- Candidate state
- fail
- Provenance changes
- none
- Verdict findings
- 1 item
- MATERIAL_CLAIM_MISSING_EVIDENCE
Fixture-Equivalence State
- State
- pass
- Review note
- Baseline and candidate fixture material remained equivalent for comparison.
CI Gate Result
- Result
- blocked
- Evidence packet
- packet-duration
- Packet limitations
- 1 item
- Local deterministic fixture evidence for human review.
Claim Boundary
This report is not a compliance attestation.
This artifact does not certify safety.
Display note: external URLs and sensitive-looking values may be redacted in this HTML; source artifacts remain unchanged.
Artifact Paths
| Artifact | Path |
| baseline run set | baseline.runset.json |
| candidate run set | candidate.runset.json |
| evidence packet | evidence-packet.json |
Artifact Digests
| Role | Path | SHA-256 |
| evaluation-summary | packet artifact digest | aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa |
| compiled-suite | compiled.json | aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa |
| candidate-runset | candidate.json | aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa |