feature: review-claim-dispositions shipped — prompt advanced to complete/

draft/feature/pyautobrain/review_claim_dispositions.md → complete/2026/08/review-claim-dispositions.md

@@ -1,3 +1,54 @@
+Review verdicts now record a **disposition per lifted claim** — the one change
+the falsified-by efficacy review ([[falsified-by-checkpoint-efficacy-review]],
+2026-08-18) recommended, moving mitigation 6 from remind-shaped to
+detect-shaped: a rote adversarial pass is now visible ledger drift instead of
+being indistinguishable from a healthy one.
+
+- completed: 2026-08-18 (same-day follow-up to the efficacy review, same
+  dashboard-work session, branch `claude/automind-falsified-by-checkpoint-cmsqsi`)
+- target: PyAutoBrain
+
+## The change
+
+When the ReviewSurface lifts any `claims to falsify`, the reviewing agent's
+verdict must carry one line per claim:
+
+```
+claim: "<lifted line>" → basis-cited: <the test/measurement/diff that shows it> | idle | FINDING (unverified-claim)
+```
+
+written by the **reviewer at verdict time**, never by the author (the
+reader-enforced shape mitigation 6 was designed around). A bare CLEAN over a
+non-empty claims surface is malformed evidence, not CLEAN — the ship
+checkpoint reader can see the omission. An empty surface requires nothing, so
+the 74–95% of ships that lift no claims gain no busywork.
+
+Surfaces touched (all PyAutoBrain):
+
+- `agents/faculties/review/AGENTS.md` — step 2a gains the disposition format;
+  step 3's verdict mapping gains the malformed-evidence rule.
+- `agents/faculties/review/_review.py` — the human-emit epilogue prints the
+  disposition instruction, guarded to fire only when claims were lifted.
+- `AUTONOMY.md` — autonomous-ship-gate review leg carries the requirement.
+- `skills/ship_library/reference.md` — the `--auto` validation-checklist gate
+  line shows where dispositions go in the PR body.
+- `docs/agent_failure_modes.md` — item 6 Outcome updated from "filed" to
+  "implemented".
+- 2 new pinning tests in `tests/test_review_claims.py` (instruction present
+  with claims, absent without); suite 351 passed.
+
+No trigger-vocabulary change — the efficacy review measured the current
+vocabulary as neither empty nor saturated and recommended none.
+
+## Dogfood note
+
+The faculty was run on the shipping branch itself: surface produced, zero
+claims lifted from the commit message, and — per the new guard — no
+disposition demand printed on the empty surface. Verdict CLEAN with no
+dispositions owed, which is exactly the no-busywork path.
+
+## Original prompt
+
 # Review verdicts record a disposition per lifted claim
 
 Type: feature

complete/index.md

@@ -6,7 +6,7 @@ Token-light navigation over the finished-work records (schema:
 only then grep a dated bucket. Curators: edit the band between the CURATED
 markers; everything below GENERATED is rebuilt.
 
-1019 records across 7 buckets.
+1020 records across 7 buckets.
 
 <!-- CURATED:START -->
 ## Highlights
@@ -125,6 +125,7 @@ _(curate hard-won records here — survives regeneration.)_
 - [resolve-border-relocator-hazard](2026/08/resolve-border-relocator-hazard.md) — Reconciled the likelihood hazard instrument after the border-relocator source fix. The resolved backend-diverg…
 - [resolve-curvature-floor-doc-drift](2026/08/resolve-curvature-floor-doc-drift.md) — Reconciled the curvature-floor documentation finding after PyAutoArray#444. The detector now requires both run…
 - [resolve-sersic-ell-comps-gradient](2026/08/resolve-sersic-ell-comps-gradient.md) — Reconciled the numerical-hazard evidence after the Sersic Cartesian-radius fix. The stable conditional detecto…
+- [review-claim-dispositions](2026/08/review-claim-dispositions.md)
 - [samplers-surface-autolens-tiers](2026/08/samplers-surface-autolens-tiers.md) — the samplers faculty's SamplerSurface now scans the findings
 - [save-json-numpy-scalar-typeerror](2026/08/save-json-numpy-scalar-typeerror.md) — Adds `NumpyEncoder` in `autofit/tools/util.py` (`np.ndarray` ->
 - [script-title-underline-off-by-one](2026/08/script-title-underline-off-by-one.md)

dashboard.md

@@ -11,7 +11,7 @@ Tasks only — the organism's health lives with the Heart (`/health`), not here.
 | [In flight](#in-flight) (`active/`) | 3 |
 | [Parked](#parked) (`parked.md`) | 1 |
 | [Planned](#planned) (`planned.md`) | 7 |
-| [Backlog](#backlog) (`draft/`) | 131 |
+| [Backlog](#backlog) (`draft/`) | 130 |
 
 Live on GitHub: [open issues](https://github.com/search?q=org%3APyAutoLabs+is%3Aissue+is%3Aopen&type=issues) · [open pull requests](https://github.com/search?q=org%3APyAutoLabs+is%3Apr+is%3Aopen&type=prs)
 
@@ -34,7 +34,6 @@ Live on GitHub: [open issues](https://github.com/search?q=org%3APyAutoLabs+is%3A
 
 **Quick wins** (small enough, and safe enough to run unattended)
 
-- [Review verdicts record a disposition per lifted claim](draft/feature/pyautobrain/review_claim_dispositions.md) — pyautobrain · small · safe · normal
 - [PyAutoFit CLI-noise batch: unclosed search.log handler + four small warning](draft/maintenance/pyautofit/cli_noise_pyautofit_batch.md) — pyautofit · small · safe · normal
 - [Tenant firewall: release_run.py carries an unlisted 'PyAutoLabs' instance fact](draft/bug/pyautoheart/tenant_firewall_release_run_instance_fact.md) — pyautoheart · small · safe · normal
 - [Silence the three autonerves-rooted CLI-noise sources (fits leak, pytest collection,](draft/maintenance/pyautonerves/cli_noise_autonerves_batch.md) — pyautonerves · small · safe · normal
@@ -82,7 +81,7 @@ Scoped but not started; some are not yet prompt files. Full detail in [`planned.
 
 ## Backlog
 
-**131** filed prompts, not started. Each section is sorted most-pickable first (priority, then size).
+**130** filed prompts, not started. Each section is sorted most-pickable first (priority, then size).
 
 <details>
 <summary><b>bug</b> — 35</summary>
@@ -126,14 +125,13 @@ Scoped but not started; some are not yet prompt files. Full detail in [`planned.
 </details>
 
 <details>
-<summary><b>feature</b> — 28</summary>
+<summary><b>feature</b> — 27</summary>
 
 - [Decide whether the clipper belongs in the search identifier](draft/feature/autofit/clipper_in_search_identifier.md) — autofit · medium · human-required · high
 - [Profile and speed up JAX likelihood-function compile times (all use](draft/feature/autolens_profiling/jax_compile_time_profiling.md) — autolens_profiling · large · supervised · high
 - [Give the Profiling Agent a compile-time axis — the arc](draft/feature/profiling/profiling_agent_jax_compile_time_scope.md) — profiling · large · supervised · high
 - [Which other searches need prior-support handling — coverage audit after](draft/feature/autofit/prior_exit_sampler_coverage.md) — autofit · medium · supervised · medium
 - [Give PyAutoFit searches a `seed` — today no search can](draft/feature/autofit/search_seed_reproducibility.md) — autofit · medium · supervised · medium
-- [Review verdicts record a disposition per lifted claim](draft/feature/pyautobrain/review_claim_dispositions.md) — pyautobrain · small · safe · normal
 - [Can create a list of InversionMatrix objects for each dataset](draft/feature/autoarray/multiwavelength_inversion.md) — autoarray · medium · supervised · normal
 - [The project @z_projects/ic50_workspace is our IC50 use case which we](draft/feature/autofit/ep_lbfgs_jax.md) — autofit · medium · safe · normal
 - [Tune cluster-scale JOSS benchmarks toward their 5-minute targets](draft/feature/autolens_workspace/joss_cluster_benchmark_tuning.md) — autolens_workspace · medium · supervised · normal