Open_Ultra_SAST/benchmarks/measurements/2026-10-12-valid-benchmark-pilot/metrics_a_interim_163.json

{
  "exploit_verified": {
    "count": 0,
    "flagged_positive_pushes": 0,
    "flagged_positives": 0,
    "n": 0,
    "not_yet_proved": [],
    "rate": null,
    "status": "measured",
    "wilson95": [
      null,
      null
    ]
  },
  "false_alarms_per_100_pushes": {
    "cluster95": [
      0.0,
      2.027027027027027
    ],
    "count": 1,
    "icc": -0.004445973772031825,
    "n": 149,
    "rate": 0.6711409395973155,
    "wilson95": [
      0.11856820977550406,
      3.703427895996746
    ]
  },
  "headline": "On unseen app repos: recall 0.0% (Wilson 0.0-24.3), false alarms 0.7 per 100 pushes, precision 0.0%; exploit-verified 0 of 0.",
  "precision": {
    "count": 0,
    "n": 1,
    "rate": 0.0,
    "wilson95": [
      0,
      0.7934567085261071
    ]
  },
  "recall": {
    "cluster95": [
      0.0,
      0.0
    ],
    "count": 0,
    "n": 12,
    "rate": 0.0,
    "wilson95": [
      0,
      0.2425007574992425
    ]
  }
}