{
 "interrupted_stage_calls_before_resume": {
  "test.coord.evidence": 0,
  "test.coord.evidence_answer": 0,
  "test.coord.synthesis": 0
 },
 "largest_gaps_between_model_calls_s": [
  {
   "from_utc": 1794777652.159,
   "gap_s": 94.0,
   "to_utc": 1794777746.155
  },
  {
   "from_utc": 1794777290.867,
   "gap_s": 97.5,
   "to_utc": 1794777388.387
  },
  {
   "from_utc": 1794778308.909,
   "gap_s": 1910.0,
   "to_utc": 1794780218.924
  }
 ],
 "notes": [
  "Run 3 was started by the original implementation session at 2026-11-15T20:31:59Z. That process ended without writing run_state.json. Its last model call was at 2026-11-15T21:31:48Z, after the 'worker1' coordination stage completed and before the 'evidence' stage made any call. The cause was not recorded (the session that owned it ended).",
  "A takeover session resumed the same run at 2026-11-15T22:01:44Z with the unchanged command. The runner is resumable: completed stage files were reused, the frozen routing policy hash was re-checked, the task splits were re-checked against disk (TASK_SET_DRIFT guard), and only the unfinished coordination stages were executed.",
  "run_state.json therefore describes the resumed process only (pid and wall time). Total inference time is the summed latency in collective_benchmark.json, not that wall time.",
  "No stage was executed twice: the three stages run after the resume had zero model calls before it, so no test task was sampled a second time. The gate audit hash chain continues across both processes.",
  "The replication split ran afterwards in its own process, as designed."
 ],
 "resumed_utc": "2026-11-15T22:01:44Z",
 "run": 3,
 "run_state_pid_is_the_resumed_process": 163832,
 "run_state_wall_s_is_the_resumed_process_only": 468.0,
 "schema": "cain2027.e80.run_lineage.v1",
 "stages_executed_after_resume": [
  "test.coord.evidence",
  "test.coord.evidence_answer",
  "test.coord.synthesis"
 ],
 "started_utc": "2026-11-15T20:31:59Z"
}