78 lines
3.5 KiB
JSON
78 lines
3.5 KiB
JSON
{
|
|
"actor": "rollout-lead",
|
|
"contract": "controls-bootstrap",
|
|
"explanation": "The count contradiction is a run-scope mix-up, not a failed instrument. Independently counted JSONL lines and checked records: Astra smoke run-df1472c13f31db3a4d5361f0 has 24 events; Terra verifier run-cb15199f9272fe496bd10a8a has 67. Prior checkpoint b467 and verdict explicitly describe the Astra architecture-review smoke, not their own Terra session. A checkpoint session identifies its authoring quantum, not the experiment described by its summary. Both scoped observations survive. No source/input/binary changes or test failures; existing 37-test package remains valid evidence and may be reused, with refreshed explicit-ID verdicts. Final verdict must name both reviewed run IDs instead of ambiguous actual-run wording.",
|
|
"id": "d-2570bf9c76ae66711bdac461",
|
|
"invalidated_checkpoint": "campaign/runtime/checkpoints/controls-bootstrap-afbcef41803eb3ff4be76392.json",
|
|
"invalidated_evidence": [
|
|
{
|
|
"axis": "control-tests",
|
|
"binaries": [
|
|
{
|
|
"path": "tools/campaign.py",
|
|
"sha256": "c7b7c7a30d907bba8e59386dee8704d7f3f5e978fcf709b686e37996fa465c31"
|
|
},
|
|
{
|
|
"path": "tools/run_agent.py",
|
|
"sha256": "0f5ccb53dcde59b64fe999768737b6cbd2dabcc1272e5605c1f1ecd86e5d5d2b"
|
|
}
|
|
],
|
|
"id": "controls-suite",
|
|
"inputs": [
|
|
{
|
|
"path": "verify/campaign/test_controls.py",
|
|
"sha256": "108460f4e90c4cb7036642e85de581e31fd70c478533c32364691260461814fc"
|
|
},
|
|
{
|
|
"path": "campaign/contract.schema.json",
|
|
"sha256": "a2c76ec042ca097a57c3c05c1e519e392d498d387a31808c7d0f70482d43c201"
|
|
},
|
|
{
|
|
"path": "campaign/rollout/controls_evidence.py",
|
|
"sha256": "bfaf4e523b2ca39c0ecdab94adf0b2b19a3da68aab8a0fcba69a613aed46588a"
|
|
}
|
|
],
|
|
"integrated": true,
|
|
"outcomes": [
|
|
{
|
|
"artifact": {
|
|
"path": "campaign/evidence/controls-suite-1788991911311171323.json",
|
|
"sha256": "bd6ae3eba3d3df606e0410676819db47a46094571d0680edbf9b907bf90d693e"
|
|
},
|
|
"criterion": "controls-negative-paths",
|
|
"status": "pass"
|
|
}
|
|
],
|
|
"path": "campaign/evidence/controls-suite-1788991911311171323.json",
|
|
"sha256": "bd6ae3eba3d3df606e0410676819db47a46094571d0680edbf9b907bf90d693e",
|
|
"source": {
|
|
"engine": {
|
|
"commit": "7741d42fc5e4e761e6449bdaf0e4a61d00036a23",
|
|
"path": "/home/alex/sots-engine"
|
|
},
|
|
"re": {
|
|
"commit": "3bfde5a70d874a723e797a695bbd847fd82c0aa7",
|
|
"path": "/home/alex/sots-re"
|
|
}
|
|
},
|
|
"source_binding": {
|
|
"engine": {
|
|
"commit": "7741d42fc5e4e761e6449bdaf0e4a61d00036a23",
|
|
"path": "/home/alex/sots-engine",
|
|
"sha256": "ccd8e02083e8d2e2b3e97976ace2273c8f924dfc02a39e919004eaf3544c50fd"
|
|
},
|
|
"re": {
|
|
"commit": "3bfde5a70d874a723e797a695bbd847fd82c0aa7",
|
|
"path": "/home/alex/sots-re",
|
|
"sha256": "6696fd5201e144843617cbf6d78b41b5287ad5dcc9fa1e8aaa861d52b64e72e8"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"model": "openai/gpt-6-astra",
|
|
"probe": "Compare event_count and JSONL counts for the TWO distinct run IDs, each with own error/session/stop/source records; preserve 24 for df147 and 67 for cb151. No code or full-suite rerun required if hashes remain identical.",
|
|
"role": "lead",
|
|
"schema": "sots-decision/1",
|
|
"surprise": "s-4a7d66ebd7d8a8f3ec59f11d",
|
|
"timestamp": "2026-09-09T22:20:09.557458+00:00"
|
|
}
|