staging before detector run
This commit is contained in:
@@ -1,139 +1,165 @@
|
||||
{
|
||||
"version": 1,
|
||||
"generatedAt": "2026-09-27T11:44:36.953Z",
|
||||
"generatedAt": "2026-09-28T19:08:30.093Z",
|
||||
"referenceRuns": [
|
||||
{
|
||||
"runId": "reward-0.4100-p7644rd",
|
||||
"runId": "reward-0.3000-wNYgXoP",
|
||||
"status": "fresh",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-26T22:56:38.770Z",
|
||||
"capturedBy": "run"
|
||||
"capturedAt": "2026-09-28T18:35:34.158Z",
|
||||
"capturedBy": "copy"
|
||||
},
|
||||
{
|
||||
"runId": "reward-0.4300-a5pdbqx",
|
||||
"runId": "reward-0.3700-J69VgLC",
|
||||
"status": "fresh",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-26T22:56:38.770Z",
|
||||
"capturedBy": "run"
|
||||
"capturedAt": "2026-09-28T18:39:33.253Z",
|
||||
"capturedBy": "copy"
|
||||
},
|
||||
{
|
||||
"runId": "reward-0.5100-2JvrM24",
|
||||
"runId": "reward-0.4500-h2zMRbJ",
|
||||
"status": "fresh",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-26T22:56:38.770Z",
|
||||
"capturedBy": "run"
|
||||
"capturedAt": "2026-09-28T18:44:17.137Z",
|
||||
"capturedBy": "copy"
|
||||
},
|
||||
{
|
||||
"runId": "reward-0.5200-DjvdVkm",
|
||||
"runId": "reward-0.5300-dHVmvQn",
|
||||
"status": "fresh",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-26T22:56:38.770Z",
|
||||
"capturedBy": "run"
|
||||
"capturedAt": "2026-09-28T18:48:49.336Z",
|
||||
"capturedBy": "copy"
|
||||
}
|
||||
],
|
||||
"detectors": [
|
||||
{
|
||||
"report": "detector-answer-obviousness.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T10:39:09.551Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-broken-dev-env.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:40:49.062Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-credential-leakage.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T10:46:06.445Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-cross-task-reference.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T10:50:07.873Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-dimension-misapplication.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T10:56:37.840Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-fact-check-rubric-claims.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:12:22.622Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-good-response-defined.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:14:33.977Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-good-response-exhaustiveness.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:16:21.813Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-meaningful-failure.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T10:27:37.476Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-offline-verifiability.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:20:45.984Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-over-hinting.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:21:54.713Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-rubric-clarity.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:23:34.524Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-rubric-coverage.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-27T11:42:39.035Z",
|
||||
"changed": [
|
||||
"atomic rubric (tests/atomic-rubric.yaml)"
|
||||
],
|
||||
"capturedAt": "2026-09-28T18:12:01.032Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
@@ -141,30 +167,36 @@
|
||||
"status": "fresh",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"capturedAt": "2026-09-27T09:51:49.533Z",
|
||||
"capturedAt": "2026-09-28T18:22:03.265Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-rubric-generality.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:24:49.860Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-run-behaviors.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:32:43.695Z",
|
||||
"capturedBy": "stamp"
|
||||
},
|
||||
{
|
||||
"report": "detector-snapshot-leakage.md",
|
||||
"status": "fresh",
|
||||
"status": "stale",
|
||||
"method": "checksums",
|
||||
"changed": [],
|
||||
"changed": [
|
||||
"holistic rubric (tests/holistic-rubric.md)"
|
||||
],
|
||||
"capturedAt": "2026-09-27T11:26:49.794Z",
|
||||
"capturedBy": "stamp"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user