diff --git a/README.md b/README.md
index e03b280b..47674c64 100644
--- a/README.md
+++ b/README.md
@@ -127,7 +127,7 @@ The dashboard below is generated from an append-only event ledger and immutable,
-
+
The tracker separates lifecycle, evidence provenance, freshness, change type, and assessment. A stale score remains visible but is never presented as current. Current history is too sparse and heterogeneous to support exponential-growth or diminishing-return claims; the honest classification is **insufficient comparable evidence**.
@@ -141,7 +141,7 @@ The tracker separates lifecycle, evidence provenance, freshness, change type, an
| Backend performance reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 7/7 (100.0%) · first-pass clean pass: 3/6 (50.0%) · block recall: 7/7 (100.0%) · clean pass: 6/6 (100.0%) |
| Frontend security reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 11/11 (100.0%) · first-pass clean pass: 7/8 (87.5%) · block recall: 10/11 (90.9%) · clean pass: 8/8 (100.0%) |
| Frontend performance reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 10/11 (90.9%) · first-pass clean pass: 7/8 (87.5%) · block recall: 10/11 (90.9%) · clean pass: 7/8 (87.5%) |
-| Correctness reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 35/38 (92.1%) · first-pass clean pass: 24/28 (85.7%) |
+| Correctness reviewer | shipped | accepted | current | coverage | ↕ mixed | first-pass FAIL recall: 44/50 (88.0%) · first-pass clean pass: 32/40 (80.0%) |
| Decision governance | shipped | evidence-only | unknown | quality | ↑ improved | Detect accuracy: 45/49 (91.8%) · DECISION recall: 8/9 (88.9%) |
| Sentry capture judge | shipped | evidence-only | unknown | quality | ↑ improved | Commit-message F1: 56/100 (56.0%) · Focused-diff F1: 87/100 (87.0%) |
| Edge-case autonomy | no-ship | accepted | stale | no-ship | ? unknown | Judge-free ceiling: 51.2% · Pre-registered target: 35.0% |
diff --git a/docs/benchmarks/README.md b/docs/benchmarks/README.md
index b281a2b4..d2570b7c 100644
--- a/docs/benchmarks/README.md
+++ b/docs/benchmarks/README.md
@@ -79,7 +79,7 @@ Committed evidence rejects raw prompts, transcripts, absolute paths, email addre
| Backend performance reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 7/7 (100.0%) · first-pass clean pass: 3/6 (50.0%) · block recall: 7/7 (100.0%) · clean pass: 6/6 (100.0%) |
| Frontend security reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 11/11 (100.0%) · first-pass clean pass: 7/8 (87.5%) · block recall: 10/11 (90.9%) · clean pass: 8/8 (100.0%) |
| Frontend performance reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 10/11 (90.9%) · first-pass clean pass: 7/8 (87.5%) · block recall: 10/11 (90.9%) · clean pass: 7/8 (87.5%) |
-| Correctness reviewer | shipped | accepted | stale | coverage | ? unknown | first-pass FAIL recall: 35/38 (92.1%) · first-pass clean pass: 24/28 (85.7%) |
+| Correctness reviewer | shipped | accepted | current | coverage | ↕ mixed | first-pass FAIL recall: 44/50 (88.0%) · first-pass clean pass: 32/40 (80.0%) |
| Decision governance | shipped | evidence-only | unknown | quality | ↑ improved | Detect accuracy: 45/49 (91.8%) · DECISION recall: 8/9 (88.9%) |
| Sentry capture judge | shipped | evidence-only | unknown | quality | ↑ improved | Commit-message F1: 56/100 (56.0%) · Focused-diff F1: 87/100 (87.0%) |
| Edge-case autonomy | no-ship | accepted | stale | no-ship | ? unknown | Judge-free ceiling: 51.2% · Pre-registered target: 35.0% |
diff --git a/docs/benchmarks/assets/dashboard-dark.svg b/docs/benchmarks/assets/dashboard-dark.svg
index a54e41ca..e795f8d4 100644
--- a/docs/benchmarks/assets/dashboard-dark.svg
+++ b/docs/benchmarks/assets/dashboard-dark.svg
@@ -17,7 +17,7 @@
Backend performance reviewer! stalefirst-pass FAIL recall: 7/7 (100.0%) · first-…
Frontend security reviewer! stalefirst-pass FAIL recall: 11/11 (100.0%) · firs…
Frontend performance reviewer! stalefirst-pass FAIL recall: 10/11 (90.9%) · first…
-Correctness reviewer! stalefirst-pass FAIL recall: 35/38 (92.1%) · first…
+Correctness reviewer✓ acceptedfirst-pass FAIL recall: 44/50 (88.0%) · first…
Decision governance· evidence-onlyDetect accuracy: 45/49 (91.8%) · DECISION rec…
Sentry capture judge· evidence-onlyCommit-message F1: 56/100 (56.0%) · Focused-d…
Edge-case autonomy!× stale no-shipJudge-free ceiling: 51.2% · Pre-registered ta…
diff --git a/docs/benchmarks/assets/dashboard-light.svg b/docs/benchmarks/assets/dashboard-light.svg
index 365e5b13..992a8a8a 100644
--- a/docs/benchmarks/assets/dashboard-light.svg
+++ b/docs/benchmarks/assets/dashboard-light.svg
@@ -17,7 +17,7 @@
Backend performance reviewer! stalefirst-pass FAIL recall: 7/7 (100.0%) · first-…
Frontend security reviewer! stalefirst-pass FAIL recall: 11/11 (100.0%) · firs…
Frontend performance reviewer! stalefirst-pass FAIL recall: 10/11 (90.9%) · first…
-Correctness reviewer! stalefirst-pass FAIL recall: 35/38 (92.1%) · first…
+Correctness reviewer✓ acceptedfirst-pass FAIL recall: 44/50 (88.0%) · first…
Decision governance· evidence-onlyDetect accuracy: 45/49 (91.8%) · DECISION rec…
Sentry capture judge· evidence-onlyCommit-message F1: 56/100 (56.0%) · Focused-d…
Edge-case autonomy!× stale no-shipJudge-free ceiling: 51.2% · Pre-registered ta…
diff --git a/docs/benchmarks/checkpoints/f69e993d15469053672364db5a68c1ab38ad12e3176a2d12f66bddc3d93bfb6d.json b/docs/benchmarks/checkpoints/f69e993d15469053672364db5a68c1ab38ad12e3176a2d12f66bddc3d93bfb6d.json
new file mode 100644
index 00000000..7709175d
--- /dev/null
+++ b/docs/benchmarks/checkpoints/f69e993d15469053672364db5a68c1ab38ad12e3176a2d12f66bddc3d93bfb6d.json
@@ -0,0 +1,781 @@
+{
+ "acceptance": {
+ "accepted": true,
+ "reason": "Complete reviewer cohorts with row evidence, zero outages, and suite floors met"
+ },
+ "adapter": "reviewer",
+ "capturedAt": "2026-08-01T17:35:02.000Z",
+ "comparisons": [
+ {
+ "method": "shared-row outcome comparison",
+ "negativeDiscordant": 2,
+ "positiveDiscordant": 2,
+ "predecessorEventId": "evt-2026-08-01-reviewer-correctness-75d2d15bab20",
+ "sharedRows": 66,
+ "verdict": "mixed"
+ }
+ ],
+ "hashes": {
+ "corpus": "sha256:3ac68f7e77d58567eee38139b20bc211266904be19c54cd588fd2c8a54f8c0a4",
+ "implementation": "sha256:39f934cad948e1489a05e182884012a966cd19200cf3ff1f158aa7259c9bd57b",
+ "runner": "sha256:7fed284584ffc9abb04b2da5ae85345b20e85509e93e0c79097b2792f0367b12",
+ "scorer": "sha256:7fed284584ffc9abb04b2da5ae85345b20e85509e93e0c79097b2792f0367b12"
+ },
+ "metrics": [
+ {
+ "denominator": 50,
+ "direction": "higher",
+ "id": "correctness-reviewer@sonnet@cascade-off:first-fail-recall",
+ "inferenceUnit": "row",
+ "interval": {
+ "lower": 0.7619518261679701,
+ "method": "wilson-95",
+ "upper": 0.9438239984906773
+ },
+ "label": "correctness-reviewer@sonnet@cascade-off first-pass FAIL recall",
+ "numerator": 44,
+ "unit": "ratio",
+ "value": 0.88
+ },
+ {
+ "denominator": 40,
+ "direction": "higher",
+ "id": "correctness-reviewer@sonnet@cascade-off:first-clean-pass",
+ "inferenceUnit": "row",
+ "interval": {
+ "lower": 0.652426936536005,
+ "method": "wilson-95",
+ "upper": 0.895000102745623
+ },
+ "label": "correctness-reviewer@sonnet@cascade-off first-pass clean pass",
+ "numerator": 32,
+ "unit": "ratio",
+ "value": 0.8
+ }
+ ],
+ "rows": {
+ "correctness-reviewer@sonnet@cascade-off:corr-asymmetric-flip-classifier": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "6de9cfbf2954"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-broadcast-fanout-no-dedup": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "47c008601f5a"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-broadcast-targeted": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "e938d8dfd98f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-cas-guarded-write": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "78f68c681a4b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-catch-rethrows": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "e8f30a7b534c"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-clears-stale-artifact": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "6b1d08fe1cda"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-conditional-update": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "2bdf6d299d0f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-early-exit-preserved": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "f0e7c45072f7"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-empty-recompute-clears": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "3bd72383bd3a"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-exit-code-fail-closed": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "21bd92d728ef"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-fs-recursive-mkdir": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "eb96bfed4c42"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-lock-finally": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "e11d0cbad3ba"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-loop-break-preserved": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "c2c122dff0af"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-only-validated": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "323fff96a42c"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-outage-exit-preserved": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "ab4b076ebb7b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-parses-json-string-result": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "44a17ae0e114"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-reset-failure-reasons": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "d1aa3924919d"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-retry-clears-error": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "c3a89e627c9d"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-retry-reset-counter": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "d1986643add2"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-return-checked-fails-closed": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "b0212aaba7aa"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-select-for-update": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "14a0f0b1e50a"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-signature-callsite-updated": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "8f24ea6cab36"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-targeted-broadcast": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "d98ec7291153"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-tight-anchor-classifier": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "32273403766b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-timer-debounce-clears": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "f6b1ee659889"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-decoy-worktree-finally": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "b7d85baf480b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-discarded-resume-return": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "ff1b6eaaf1ad"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-early-exit-loop-break-dropped": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "0d411082e3fc"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-early-exit-status-bypassed": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "bb1655183df9"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-empty-recompute-keeps-stale": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "97ecde7284e1"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-execfile-cmd-shim-swallowed": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "203e6fa03e0e"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-exit-code-only-one-fails": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "d145d1ad9a98"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-field-validated-wrong-state": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "ef5656e35718"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-fs-check-then-act-race": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "e14b7efdc4ba"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-group-map-last-write-wins": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "8884e07c6d1b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-guarded-result-ignored-mode-flip": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "5779051bc2d1"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-json-string-result-dropped": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "cb0d1314d164"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-lock-not-released-on-throw": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "7f9f3d490d13"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-lock-timeout-runs-unlocked": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "ba399eec3288"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-loose-cmd-classifier-anchor": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "6396f1f3b278"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-loose-json-error-classifier": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "9d6d1a732721"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-manifest-unknown-version-wiped": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "d49452801030"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-nearexpiry-permanent-reauth": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "5cbfcd319951"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-only-selector-silent-drop": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "15e6fb189b63"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-outage-exit-code-downgraded": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "8d4201a5cf5d"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-persist-unnormalized-signal": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "54e6d945cb0f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr138-ci-breaking-gate-engine-coverage": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "bbaa0d63b28f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr138-ci-breaking-gate-engine-coverage-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "03b109856fa8"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr172-duplicate-let-spawnoptions-declaration": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "2460b5333d56"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr172-duplicate-let-spawnoptions-declaration-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "58955fb31aea"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr200-important": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "5b4be62121e1"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr200-important-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "c0ae2bb9ba5b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr200-ref-mutated-during-render-move": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "7b4f10bd7c1f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr200-ref-mutated-during-render-move-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "87332a189081"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr21-fail-closed-when-the-remote": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "b5efdb08286f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr21-fail-closed-when-the-remote-pair": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "61e01ab552b4"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr21-validate-the-parsed-github-repo": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "25638f849b88"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr21-validate-the-parsed-github-repo-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "439eb60c508e"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr26-cover-the-restart-interrupted-flow": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "64bb8db9a785"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr26-cover-the-restart-interrupted-flow-pair": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "d5b2d88ce1a4"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr26-keep-the-mcp-inputschema-in": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "7e174420f714"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr26-keep-the-mcp-inputschema-in-pair": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "cd3e2928584d"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr38-check-the-full-r2-credential": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "3b141c8643d2"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr38-check-the-full-r2-credential-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "a327217fc231"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr38-require-the-full-azure-signing": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": false,
+ "okFirst": true,
+ "rowHash": "4ea330953efb"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr38-require-the-full-azure-signing-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "50cf11f113c3"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr48-cn-ts-src": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "58f9cd6e3788"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr48-cn-ts-src-pair": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "920c44fa7a20"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr59-guard-config-json": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "d27f9cc76bb3"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-pr59-guard-config-json-pair": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "7487964245c4"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-read-then-write-clobber-terminal": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "85ac72a96350"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-reminder-ignores-plan-mode": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "71d93cd6e657"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-reopen-before-cas-strands": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "918e6e35a29f"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-retry-broadcast-double-fire": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "f55d220196ab"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-retry-leaves-stale-error": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "c05976dd01fd"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-retry-stuck-unclaimable": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "0640a8b18d1b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-revive-user-cancelled": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "b2a0d733679e"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-signature-change-callsite-missed": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "16d916a93384"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-stale-checklist-artifact": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "e90eb005ef97"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-stale-failure-reasons": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "09f050fde84d"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-submit-latch-stuck": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "8183fa0b5781"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-swallowed-config-parse-bypass": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "5929d8e219fe"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-sync-source-target-divergence": {
+ "expected": "FAIL",
+ "finalStatus": "pass",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "48bd49378904"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-timer-debounce-double-fire": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "ee84f73cfeb3"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-unguarded-unpark-clobber": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "868c6ced4079"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-worktree-leak-no-finally": {
+ "expected": "FAIL",
+ "finalStatus": "fail",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "844bffb4162b"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-xdomain-nplusone": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "a0bccc3e0faf"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-xdomain-render": {
+ "expected": "PASS",
+ "finalStatus": "fail",
+ "ok": false,
+ "okFinal": false,
+ "okFirst": false,
+ "rowHash": "a2babcecd2d6"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-xdomain-sqli": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "2ddabe1e3884"
+ },
+ "correctness-reviewer@sonnet@cascade-off:corr-xdomain-xss": {
+ "expected": "PASS",
+ "finalStatus": "pass",
+ "ok": true,
+ "okFinal": true,
+ "okFirst": true,
+ "rowHash": "5562a8a8edb3"
+ }
+ },
+ "schemaVersion": 1,
+ "sourceCommit": "16b73c102cda23ecb3917eec13980f090700066b",
+ "suiteId": "reviewer-correctness"
+}
diff --git a/docs/benchmarks/history.jsonl b/docs/benchmarks/history.jsonl
index e5bcf80f..e1171bb1 100644
--- a/docs/benchmarks/history.jsonl
+++ b/docs/benchmarks/history.jsonl
@@ -21,3 +21,4 @@
{"assessment":"unknown","changeType":"coverage","checkpoint":{"path":"docs/benchmarks/checkpoints/1ab5991c759be40ceefdb7e804d6ab2464c12a32554448a0a6052447f496287e.json","sha256":"1ab5991c759be40ceefdb7e804d6ab2464c12a32554448a0a6052447f496287e"},"comparisons":[],"evidence":"accepted","freshness":"current","hashes":{"corpus":"sha256:a31b51b7343edce031dd43d79a0703118e8e5e96735a78cea2720c6cb5c38a14","implementation":"sha256:39f7131d35dc539e202d801bb6d2bd9e21064dad02c37b11d4348ced301df8d7","runner":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a","scorer":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a"},"id":"evt-2026-08-01-reviewer-frontend-security-8c1cbfd57121","lifecycle":"shipped","metrics":[{"denominator":11,"direction":"higher","id":"frontend-security-reviewer@haiku@cascade-on:first-fail-recall","inferenceUnit":"row","interval":{"lower":0.7411670330319684,"method":"wilson-95","upper":1},"label":"frontend-security-reviewer@haiku@cascade-on first-pass FAIL recall","numerator":11,"unit":"ratio","value":1},{"denominator":8,"direction":"higher","id":"frontend-security-reviewer@haiku@cascade-on:first-clean-pass","inferenceUnit":"row","interval":{"lower":0.5291118177871464,"method":"wilson-95","upper":0.9775825085499433},"label":"frontend-security-reviewer@haiku@cascade-on first-pass clean pass","numerator":7,"unit":"ratio","value":0.875},{"denominator":11,"direction":"higher","id":"frontend-security-reviewer@haiku@cascade-on:block-recall","inferenceUnit":"row","interval":{"lower":0.6226415635484043,"method":"wilson-95","upper":0.9837678271141151},"label":"frontend-security-reviewer@haiku@cascade-on block recall","numerator":10,"unit":"ratio","value":0.9090909090909091},{"denominator":8,"direction":"higher","id":"frontend-security-reviewer@haiku@cascade-on:clean-pass","inferenceUnit":"row","interval":{"lower":0.6755924351161198,"method":"wilson-95","upper":1},"label":"frontend-security-reviewer@haiku@cascade-on clean pass","numerator":8,"unit":"ratio","value":1}],"note":"First accepted frontend-security reviewer cohort at the shipped config, 131-row reviewer corpus, zero outages.","provenance":{"source":"committed sanitized checkpoint","sourceCommit":"d855b7b0de8524021905688b617ac836fb652b4f","tier":"accepted"},"recordedAt":"2026-08-01T11:19:02.000Z","schemaVersion":1,"subjectIds":["reviewer-frontend-security-reviewer","agent-frontend-security-reviewer","bin-guard-review"],"suiteId":"reviewer-frontend-security"}
{"assessment":"unknown","changeType":"coverage","checkpoint":{"path":"docs/benchmarks/checkpoints/a7b6e01854cc49ad7085e4ee30392ab8be43972dca4ca139f9461a9a72360653.json","sha256":"a7b6e01854cc49ad7085e4ee30392ab8be43972dca4ca139f9461a9a72360653"},"comparisons":[],"evidence":"accepted","freshness":"current","hashes":{"corpus":"sha256:9818efd6009cb8f6080a56ecc00d2a7f47c78e59d2d268d63d4303d370e66f43","implementation":"sha256:c23535aa1da64b761dbf2b614e8f3f1dc7b7508f585ea83f870a2f1692fa48d4","runner":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a","scorer":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a"},"id":"evt-2026-08-01-reviewer-frontend-performance-50009f0eff89","lifecycle":"shipped","metrics":[{"denominator":11,"direction":"higher","id":"frontend-performance-reviewer@haiku@cascade-on:first-fail-recall","inferenceUnit":"row","interval":{"lower":0.6226415635484043,"method":"wilson-95","upper":0.9837678271141151},"label":"frontend-performance-reviewer@haiku@cascade-on first-pass FAIL recall","numerator":10,"unit":"ratio","value":0.9090909090909091},{"denominator":8,"direction":"higher","id":"frontend-performance-reviewer@haiku@cascade-on:first-clean-pass","inferenceUnit":"row","interval":{"lower":0.5291118177871464,"method":"wilson-95","upper":0.9775825085499433},"label":"frontend-performance-reviewer@haiku@cascade-on first-pass clean pass","numerator":7,"unit":"ratio","value":0.875},{"denominator":11,"direction":"higher","id":"frontend-performance-reviewer@haiku@cascade-on:block-recall","inferenceUnit":"row","interval":{"lower":0.6226415635484043,"method":"wilson-95","upper":0.9837678271141151},"label":"frontend-performance-reviewer@haiku@cascade-on block recall","numerator":10,"unit":"ratio","value":0.9090909090909091},{"denominator":8,"direction":"higher","id":"frontend-performance-reviewer@haiku@cascade-on:clean-pass","inferenceUnit":"row","interval":{"lower":0.5291118177871464,"method":"wilson-95","upper":0.9775825085499433},"label":"frontend-performance-reviewer@haiku@cascade-on clean pass","numerator":7,"unit":"ratio","value":0.875}],"note":"First accepted frontend-performance reviewer cohort at the shipped config, 131-row reviewer corpus, zero outages.","provenance":{"source":"committed sanitized checkpoint","sourceCommit":"1fb073f3612a7bbf9cb58e6c0372abc1f7fe7311","tier":"accepted"},"recordedAt":"2026-08-01T11:19:03.000Z","schemaVersion":1,"subjectIds":["reviewer-frontend-performance-reviewer","agent-frontend-performance-reviewer","bin-guard-review"],"suiteId":"reviewer-frontend-performance"}
{"assessment":"unknown","changeType":"coverage","checkpoint":{"path":"docs/benchmarks/checkpoints/2520b632529db1c4341aa53d43f6f491e278aa86f4fd033f89be806a8d0f37db.json","sha256":"2520b632529db1c4341aa53d43f6f491e278aa86f4fd033f89be806a8d0f37db"},"comparisons":[],"evidence":"accepted","freshness":"current","hashes":{"corpus":"sha256:db96ac3d606bde78aa3555707727076d1375c79401ca32e8f2bf36197c6b6b2f","implementation":"sha256:c1483e0a07cb5f2cf5eddcd13edb8efb3d38a556f6120a2bae13787ea5167d71","runner":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a","scorer":"sha256:546a99e7239d201b9e017abd4b1662f133b387cb4bf553f1b40d6eaf7123045a"},"id":"evt-2026-08-01-reviewer-correctness-75d2d15bab20","lifecycle":"shipped","metrics":[{"denominator":38,"direction":"higher","id":"correctness-reviewer@sonnet@cascade-off:first-fail-recall","inferenceUnit":"row","interval":{"lower":0.7920062854222853,"method":"wilson-95","upper":0.9727854044930122},"label":"correctness-reviewer@sonnet@cascade-off first-pass FAIL recall","numerator":35,"unit":"ratio","value":0.9210526315789473},{"denominator":28,"direction":"higher","id":"correctness-reviewer@sonnet@cascade-off:first-clean-pass","inferenceUnit":"row","interval":{"lower":0.685101978364747,"method":"wilson-95","upper":0.9430099468025059},"label":"correctness-reviewer@sonnet@cascade-off first-pass clean pass","numerator":24,"unit":"ratio","value":0.8571428571428571}],"note":"First accepted correctness reviewer cohort at the shipped config, 131-row reviewer corpus, zero outages.","provenance":{"source":"committed sanitized checkpoint","sourceCommit":"4125ff02cfb655df76272edbb48b0fd7bfcafd33","tier":"accepted"},"recordedAt":"2026-08-01T11:19:03.000Z","schemaVersion":1,"subjectIds":["reviewer-correctness-reviewer","agent-correctness-reviewer","bin-guard-review"],"suiteId":"reviewer-correctness"}
+{"assessment":"mixed","changeType":"coverage","checkpoint":{"path":"docs/benchmarks/checkpoints/f69e993d15469053672364db5a68c1ab38ad12e3176a2d12f66bddc3d93bfb6d.json","sha256":"f69e993d15469053672364db5a68c1ab38ad12e3176a2d12f66bddc3d93bfb6d"},"comparisons":[{"method":"shared-row outcome comparison","negativeDiscordant":2,"positiveDiscordant":2,"predecessorEventId":"evt-2026-08-01-reviewer-correctness-75d2d15bab20","sharedRows":66,"verdict":"mixed"}],"evidence":"accepted","freshness":"current","hashes":{"corpus":"sha256:3ac68f7e77d58567eee38139b20bc211266904be19c54cd588fd2c8a54f8c0a4","implementation":"sha256:39f934cad948e1489a05e182884012a966cd19200cf3ff1f158aa7259c9bd57b","runner":"sha256:7fed284584ffc9abb04b2da5ae85345b20e85509e93e0c79097b2792f0367b12","scorer":"sha256:7fed284584ffc9abb04b2da5ae85345b20e85509e93e0c79097b2792f0367b12"},"id":"evt-2026-08-01-reviewer-correctness-b0dc29a7d531","lifecycle":"shipped","metrics":[{"denominator":50,"direction":"higher","id":"correctness-reviewer@sonnet@cascade-off:first-fail-recall","inferenceUnit":"row","interval":{"lower":0.7619518261679701,"method":"wilson-95","upper":0.9438239984906773},"label":"correctness-reviewer@sonnet@cascade-off first-pass FAIL recall","numerator":44,"unit":"ratio","value":0.88},{"denominator":40,"direction":"higher","id":"correctness-reviewer@sonnet@cascade-off:first-clean-pass","inferenceUnit":"row","interval":{"lower":0.652426936536005,"method":"wilson-95","upper":0.895000102745623},"label":"correctness-reviewer@sonnet@cascade-off first-pass clean pass","numerator":32,"unit":"ratio","value":0.8}],"note":"Corpus growth 66->90 (batch 1 of the CodeRabbit mining effort: +12 mined golds, +12 minimal-pair decoys; charter docs/benchmarks/benchmark-methodology.md). Shipped pin config: sonnet single-pass, cascade-off — no clean-pass floor exists for this cohort (cascade-only floor), stated per the honesty rule. Metrics are LOCALIZED-FIXTURE recall/precision: mined gold measures relative recall only (methodology item 17); fixtures are 1-2 files <=25 lines vs production mean 7.9 files/26KB — calibration slice pending. first-fail-recall 44/50=0.88, first-clean-pass 32/40=0.80, zero outages. Minimal-pair decoys drew 5 of the 8 false FAILs — the hard precision probe the correctness-reviewer-precision record asked for.","provenance":{"source":"committed sanitized checkpoint","sourceCommit":"16b73c102cda23ecb3917eec13980f090700066b","tier":"accepted"},"recordedAt":"2026-08-01T17:35:02.000Z","schemaVersion":1,"subjectIds":["reviewer-correctness-reviewer","agent-correctness-reviewer","bin-guard-review"],"suiteId":"reviewer-correctness"}