> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [FINDINGS.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/FINDINGS.md)
- [hypotheses/f06-checks-review-recovery.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/hypotheses/f06-checks-review-recovery.md)

# F06 — Checks, review and recovery

> Source narrative: values not linked to an eligible claim ledger row are source-reported and not independently promoted here.

**Hypothesis:** H62–H74 ask whether checks, review, and recovery improve defect detection or completion at acceptable cost. The public page treats false blocks and test quality as risks to measure; it does not qualify a default veto or repair policy.

**What ran:** L6 adds an offline, request-scoped auditor replay with 79 valid verdicts from 80 requests ([CL-L6-AUDITOR-ADVISORY-REPLAY](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/claim-ledger.jsonl)); neither auditor met both predeclared targets. L3b is **VALID** for its registered rule (REPAIR minus CONTINUE rescues = 2, threshold ≥2); its KEEP applies to these eight selected failures only, with arm counts on the round page. Other records include offline review and contract audits, offline best-of analysis, over-strict test replay, and saved-candidate counterfactuals.

**Result:** L3b's observed difference for the selected failures is conditional on a private per-test no-regression check; it does not validate a general KEEP policy. Most scored cells lack Standard records, host captures followed execution, rule timing is unproven, and deviation and exposure are disclosed on the round page. No reconciled prospective review Build comparison is recorded. Unit: offline audit cases and candidate counterfactuals remain separate from official Build passes. Status: descriptive or interim; no general live efficacy estimate.

**What it does not show:** Offline counts do not establish that a reviewer improves acceptance, that checks preserve defect detection while reducing time, or that recovery increases completion.

**Evidence:** [F06 hypothesis page](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/hypotheses/f06-checks-review-recovery.md), [L3b repair vs continue](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/l3b-repair-vs-continue/README.md), [L6 auditor replay](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/l6-auditor-replay/README.md), [L6 status-only claim](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/claim-ledger.jsonl), [offline review](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/offline-review/README.md), [offline review 3](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/offline-review3/README.md), [offline contract audit](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/offline-contract-audit/README.md), [offline A/A selection analysis](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/offline-aa-bo3/README.md), [over-strict replay](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/overstrict-replay/README.md), [candidate counterfactual](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/candidate-counterfactual/README.md), [recovery inventory](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/x-recovery/README.md). Spec map: [acceptance tests](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/EVIDENCE-MAP.md#24-acceptance-tests-and-stack-adapters), [verification](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/EVIDENCE-MAP.md#37-verification-and-base-relative-checks), and [review and selection](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/EVIDENCE-MAP.md#38-verdict-audit-selection).

## Related records

### Related hypotheses

- [H62](/hypotheses/h62/)
- [H63](/hypotheses/h63/)
- [H64](/hypotheses/h64/)
- [H65](/hypotheses/h65/)
- [H66](/hypotheses/h66/)
- [H67](/hypotheses/h67/)
- [H68](/hypotheses/h68/)
- [H69](/hypotheses/h69/)
- [H70](/hypotheses/h70/)
- [H71](/hypotheses/h71/)
- [H72](/hypotheses/h72/)
- [H73](/hypotheses/h73/)
- [H74](/hypotheses/h74/)

### Related experiments

- [l6-auditor-replay](/rounds/l6-auditor-replay/)
- [studio-kogen](/rounds/studio-kogen/)
- [studio-kogen-80a4](/rounds/studio-kogen-80a4/)
- [studio-shaper-pilot](/rounds/studio-shaper-pilot/)
- [x-continuation](/rounds/x-continuation/)
- [x-recovery](/rounds/x-recovery/)
- [x-review](/rounds/x-review/)

### Related claims

- [CL-L6-AUDITOR-ADVISORY-REPLAY](/claims/cl-l6-auditor-advisory-replay/)
- [CL-WA-studio-kogen-80a4-lifecycle-and-outcome](/claims/cl-wa-studio-kogen-80a4-lifecycle-and-outcome/)
- [CL-WA-studio-kogen-lifecycle-and-outcome](/claims/cl-wa-studio-kogen-lifecycle-and-outcome/)
- [CL-WA-studio-shaper-pilot-lifecycle-and-outcome](/claims/cl-wa-studio-shaper-pilot-lifecycle-and-outcome/)
- [CL-WA-x-continuation-reported-x-continuation-live](/claims/cl-wa-x-continuation-reported-x-continuation-live/)
- [CL-WA-x-continuation-reported-x-continuation-scripted-provider](/claims/cl-wa-x-continuation-reported-x-continuation-scripted-provider/)
- [CL-WA-x-recovery-reported-x-recovery](/claims/cl-wa-x-recovery-reported-x-recovery/)
- [CL-WA-x-review-reported-x-review-checklist](/claims/cl-wa-x-review-reported-x-review-checklist/)
- [CL-WA-x-review-reported-x-review-repair](/claims/cl-wa-x-review-reported-x-review-repair/)
- [CL-WA-x-review-reported-x-review-semantic-repair](/claims/cl-wa-x-review-reported-x-review-semantic-repair/)
