{
  "runtime": "merlin-v3-ungated-20261104",
  "weights_candidate": "merlin-v3-precision-20261007",
  "threshold": 0.5,
  "action_token_limit": 128,
  "action_agreement": true,
  "removed_gates": [
    "operation_allowlist",
    "lexical_request",
    "learned_request_intent"
  ],
  "AgentDojo": {
    "total": 1220,
    "assessed": 1159,
    "tp": 85,
    "fp": 20,
    "positives": 352,
    "negatives": 868
  },
  "private_historical_regression": {
    "total": 415,
    "assessed": 415,
    "skipped": 0,
    "alerts": 1,
    "source_pool_total": 610,
    "excluded_before_replay": 195,
    "exclusion_reason": "original context could not be reliably reconstructed"
  },
  "private_original_flagged_no_risk": {
    "saved": 539,
    "reconstructed_and_assessed": 409,
    "alerts": 1,
    "claude_code": {
      "saved": 133,
      "assessed": 128,
      "alerts": 0
    },
    "codex": {
      "saved": 406,
      "assessed": 281,
      "alerts": 1
    }
  },
  "private_recent_sample": {
    "total": 1207,
    "assessed": 600,
    "skipped": 607,
    "alerts": 4
  },
  "private_recent_alert_review": {
    "clear_false_alerts": 3,
    "uncertain_low_impact": 1,
    "confirmed_true_positive": 0
  },
  "limitations": [
    "Historical examples overlap model development; regression evidence, not unseen holdout.",
    "AgentDojo was repeatedly consulted during development.",
    "Recent sample is stratified and reconstructed from pre-call transcripts; not representative of every deployment.",
    "Unassessed examples are not safe predictions.",
    "No fresh ungated ASB or AgentHarm result is claimed."
  ],
  "private_examples_published": false
}