Merge pilot recovery into the semantic simplex schema delivery

2026-10-28 21:48:23 +08:00
parent 4eee78be09 1c265609d5
commit 3453d5c961
6 changed files with 347 additions and 42 deletions
@@ -0,0 +1,72 @@
+{
+  "experiment": "P0",
+  "status": "provider_blocked",
+  "decision": null,
+  "decision_withheld_reason": "Incomplete detector outputs after DashScope Arrearage; no GO/PARTIAL/NO-GO is valid.",
+  "cohort_size": 65,
+  "completed_items": 42,
+  "items_with_failures": 23,
+  "missing_components": {
+    "judge": 22,
+    "role": 20
+  },
+  "request_attempts": 131,
+  "max_calls": 400,
+  "remaining_request_budget": 269,
+  "usage": {
+    "calls": 89,
+    "prompt_tokens": 37699,
+    "completion_tokens": 7790
+  },
+  "model": "qwen-max",
+  "temperature": 0.0,
+  "items_sha256": "487ecd22919a5e3b0174a2846ab8fe7c0daf4d3feccccf8ea6571aec04c41bed",
+  "labels_sha256": "1552dba85e75426799151384e7e28c9a0b1072ed4c862df0876df89920d2a638",
+  "results_sha256": "fce402e6eab460a48bb9a8e94140bb23f305843ab46d227bbffa5100d7de69e5",
+  "prompt_hashes": {
+    "source": "382f9a7b5a0cfb2d50d525f884dc806f45adaa59bcc45e388920c4759db1546f",
+    "judge": "7ab92682bd71d78a212471289f0f01db39d6b68f49d44df65d7b1c9e34ebb5e2"
+  },
+  "labels": {
+    "type": "single AI annotator; not human gold",
+    "frozen": true,
+    "count": 65
+  },
+  "affected_blind_ids": [
+    "P02",
+    "P04",
+    "P09",
+    "P18",
+    "P19",
+    "P20",
+    "P21",
+    "P22",
+    "P24",
+    "P27",
+    "P29",
+    "P30",
+    "P33",
+    "P36",
+    "P37",
+    "P38",
+    "P42",
+    "P43",
+    "P45",
+    "P47",
+    "P54",
+    "P59",
+    "P62"
+  ],
+  "successful_components_preserved": 88,
+  "resume_policy": "After owner confirms billing recovery, retry missing components only using the same run files, frozen labels, model, prompts and cumulative 400-request ceiling.",
+  "owner_instruction": "2026-10-28: complete fixes and the execution report now; resume paid calls later.",
+  "validation": {
+    "offline_unit_tests": 149,
+    "ruff": "passed",
+    "remote_runner_tag": "ubuntu24.04-x64-lean4.35",
+    "initial_remote_ci": "https://gitea.entroia.com/Zayden-Jung/lean-bench/actions/runs/427",
+    "initial_remote_ci_status": "success; image job skipped for PR",
+    "recovery_remote_ci": "https://gitea.entroia.com/Zayden-Jung/lean-bench/actions/runs/433",
+    "consolidated_pull_request": "https://gitea.entroia.com/Zayden-Jung/lean-bench/pulls/9"
+  }
+}