eric/project-work
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tried to package, had to rerun detectors

Browse Source
This commit is contained in:
Eric Bell
2026-09-27 07:43:59 -04:00
parent 2b6898ab84
commit 31e690ab35
8 changed files with 201 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/staleness.json
View File

@@ -1,6 +1,6 @@
{
"version": 1,
"generatedAt": "2026-09-27T10:18:40.511Z",
"generatedAt": "2026-09-27T11:29:28.756Z",
"referenceRuns": [
{
"runId": "reward-0.4100-p7644rd",
@@ -34,12 +34,10 @@
"detectors": [
{
"report": "detector-answer-obviousness.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:12:26.866Z",
"changed": [],
"capturedAt": "2026-09-27T10:39:09.551Z",
"capturedBy": "stamp"
},
{
@@ -54,82 +52,74 @@
},
{
"report": "detector-credential-leakage.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:14:05.275Z",
"changed": [],
"capturedAt": "2026-09-27T10:46:06.445Z",
"capturedBy": "stamp"
},
{
"report": "detector-cross-task-reference.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:14:55.949Z",
"changed": [],
"capturedAt": "2026-09-27T10:50:07.873Z",
"capturedBy": "stamp"
},
{
"report": "detector-dimension-misapplication.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:33:02.998Z",
"changed": [],
"capturedAt": "2026-09-27T10:56:37.840Z",
"capturedBy": "stamp"
},
{
"report": "detector-fact-check-rubric-claims.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T22:50:16.107Z",
"changed": [],
"capturedAt": "2026-09-27T11:12:22.622Z",
"capturedBy": "stamp"
},
{
"report": "detector-good-response-defined.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:21:06.289Z",
"changed": [],
"capturedAt": "2026-09-27T11:14:33.977Z",
"capturedBy": "stamp"
},
{
"report": "detector-good-response-exhaustiveness.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:42:44.698Z",
"changed": [],
"capturedAt": "2026-09-27T11:16:21.813Z",
"capturedBy": "stamp"
},
{
"report": "detector-meaningful-failure.md",
"status": "fresh",
"method": "checksums",
"changed": [],
"capturedAt": "2026-09-27T10:27:37.476Z",
"capturedBy": "stamp"
},
{
"report": "detector-offline-verifiability.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T22:42:43.142Z",
"changed": [],
"capturedAt": "2026-09-27T11:20:45.984Z",
"capturedBy": "stamp"
},
{
"report": "detector-over-hinting.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T20:24:19.762Z",
"changed": [],
"capturedAt": "2026-09-27T11:21:54.713Z",
"capturedBy": "stamp"
},
{
@@ -137,7 +127,7 @@
"status": "fresh",
"method": "checksums",
"changed": [],
"capturedAt": "2026-09-27T09:59:48.629Z",
"capturedAt": "2026-09-27T11:23:34.524Z",
"capturedBy": "stamp"
},
{
@@ -160,22 +150,18 @@
},
{
"report": "detector-rubric-generality.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T22:51:22.886Z",
"changed": [],
"capturedAt": "2026-09-27T11:24:49.860Z",
"capturedBy": "stamp"
},
{
"report": "detector-snapshot-leakage.md",
"status": "stale",
"status": "fresh",
"method": "checksums",
"changed": [
"holistic rubric (tests/holistic-rubric.md)"
],
"capturedAt": "2026-09-26T22:52:10.722Z",
"changed": [],
"capturedAt": "2026-09-27T11:26:49.794Z",
"capturedBy": "stamp"
}
]