evaluation/results.json

{
  "status": "QUALITY GO / PROOF-ADVISOR-ONLY",
  "all22": {
    "exact": 10,
    "n": 22,
    "parser": 22,
    "unsafe": 0,
    "ci95": [
      0.2438618659230165,
      0.6778952454468283
    ]
  },
  "holdout18": {
    "exact": 6,
    "n": 18,
    "ci95": [
      0.13342740250612353,
      0.5900747618279255
    ]
  },
  "canary4": {
    "exact": 4,
    "n": 4,
    "ci95": [
      0.3976353643835253,
      1.0
    ]
  },
  "audit_sha256": "f7bc7f2ed5bd09e36dfb67df122334d289269513abca20125b931bdc3202f740",
  "protocol_root": "6357188c7ecc3541d4b220aa19a5c826cbd81e448ed66cdd5a49b09d17d36c0e",
  "paired_stage2": {
    "all22_mcnemar_exact_two_sided_p": 1.0,
    "interpretation": "Difference not statistically significant."
  },
  "paired_clean_stage3": {
    "all22_mcnemar_exact_two_sided_p": 0.015625,
    "holdout18_p": 0.03125,
    "interpretation": "Stage4 improvement was significant."
  },
  "production_qualification": {
    "converted": "504/504",
    "canary": "12/12"
  },
  "jensen": {
    "status": "SEARCH_EXHAUSTED",
    "pass_at_6_lean_valid": 0,
    "rh_proved": false
  }
}