{
  "iter_id": "bench-harness-recalibration.1",
  "date": "2026-05-20",
  "mode": "standard",
  "outcome": "DONE",
  "tasks_total": 4,
  "tasks_completed": 4,
  "reloops_per_task": {
    "1": 0,
    "2": 0,
    "3": 0,
    "4": 0
  },
  "review_loops_spec": 0,
  "review_loops_quality": 0,
  "blocked_reason": null,
  "bench_results": {
    "check_py_exit_task3_replay": 0,
    "check_py_summary_task3": "57 metrics; 0 regressed, 0 improved beyond tolerance, 57 stable",
    "check_py_exit_task4_injection": 1,
    "check_py_injection_row": "throughput.bench_list_sum.bump_s 0.026 0.053 +99.57% 10.0% REGRESSION",
    "check_py_exit_task4_restored": 0,
    "check_py_summary_task4_restored": "57 metrics; 0 regressed, 2 improved beyond tolerance, 55 stable"
  },
  "notes": [
    "Task 3 same-HEAD replay passed on first try (no re-run needed for single-run noise mitigation).",
    "Task 4 restored replay shows 2 improvements on latency.explicit_at_rc.p99_us / p99_over_median (-33%) — improvements never gate per bench/check.py header; this is exactly the tail-distribution jitter that motivated dropping max_us / p99_9_us.",
    "All four tasks land as a single working-tree diff on bench/baseline.json (single-artefact iter)."
  ]
}