{
  "schema_version": 1,
  "drill": {
    "id": "drill-001",
    "title": "Recorded offline oversight drill",
    "recorded": true
  },
  "source": "recorded-offline-demo",
  "headline": "Injected 12 canaries across 62 items; caught 5. Median review time 15.2s on canaries vs 14.5s on real items.",
  "canaries": {
    "injected": 12,
    "caught": 5,
    "missed": 7,
    "catch_rate": 41.7,
    "executed": 0
  },
  "items": {
    "total": 62,
    "real": 50
  },
  "review_times": {
    "canary_seconds": 15.2,
    "real_seconds": 14.5,
    "complexity_correlation": 0.311
  },
  "mast_modes": [
    {
      "code": "1.1",
      "name": "Disobey Task Specification",
      "catch_rate": 0
    },
    {
      "code": "1.2",
      "name": "Disobey Role Specification",
      "catch_rate": 100
    },
    {
      "code": "2.5",
      "name": "Ignored Other Agent's Input",
      "catch_rate": 0
    },
    {
      "code": "2.6",
      "name": "Reasoning-Action Mismatch",
      "catch_rate": 50
    },
    {
      "code": "3.1",
      "name": "Premature Termination",
      "catch_rate": 100
    },
    {
      "code": "3.2",
      "name": "No or Incomplete Verification",
      "catch_rate": 50
    },
    {
      "code": "3.3",
      "name": "Incorrect Verification",
      "catch_rate": 50
    }
  ],
  "reviewers": [
    {
      "name": "avery",
      "decisions": 23,
      "catch_rate": 100,
      "median_canary_seconds": 35.5,
      "median_real_seconds": 31,
      "complexity_correlation": 1,
      "flat": false
    },
    {
      "name": "blake",
      "decisions": 20,
      "catch_rate": 0,
      "median_canary_seconds": 4,
      "median_real_seconds": 4.3,
      "complexity_correlation": 0.052,
      "flat": true
    },
    {
      "name": "casey",
      "decisions": 19,
      "catch_rate": 25,
      "median_canary_seconds": 15.2,
      "median_real_seconds": 14.5,
      "complexity_correlation": 1,
      "flat": true
    }
  ],
  "flags": [
    "Flatness flag for blake: median under 8s across at least 3 decisions, or CV under 0.25 with median under 15s across at least 5 decisions.",
    "Flatness flag for casey: median under 8s across at least 3 decisions, or CV under 0.25 with median under 15s across at least 5 decisions."
  ],
  "adaptations": [
    {
      "kind": "route_canary",
      "reviewer": "avery",
      "description": "Canary routed to avery (canary 1 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_high_risk",
      "reviewer": "blake",
      "description": "High-risk item routed to blake, the reviewer with the oldest last decision."
    },
    {
      "kind": "route_canary",
      "reviewer": "blake",
      "description": "Canary routed to blake (canary 1 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "flatness_explain_back",
      "reviewer": "blake",
      "description": "blake review times are flat (median 4.300s across 3 decisions). Explain-back is required before the next approval."
    },
    {
      "kind": "route_canary",
      "reviewer": "casey",
      "description": "Canary routed to casey (canary 1 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_medium",
      "reviewer": "avery",
      "description": "Medium-risk item routed to avery (medium 1 for that reviewer) by round-robin."
    },
    {
      "kind": "route_canary",
      "reviewer": "avery",
      "description": "Canary routed to avery (canary 2 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_medium",
      "reviewer": "blake",
      "description": "Medium-risk item routed to blake (medium 1 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "casey",
      "description": "Medium-risk item routed to casey (medium 1 for that reviewer) by round-robin."
    },
    {
      "kind": "route_high_risk",
      "reviewer": "avery",
      "description": "High-risk item routed to avery, the reviewer with the oldest last decision."
    },
    {
      "kind": "route_canary",
      "reviewer": "blake",
      "description": "Canary routed to blake (canary 2 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_canary",
      "reviewer": "casey",
      "description": "Canary routed to casey (canary 2 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "flatness_explain_back",
      "reviewer": "casey",
      "description": "casey review times are flat (median 14.500s across 5 decisions). Explain-back is required before the next approval."
    },
    {
      "kind": "route_medium",
      "reviewer": "avery",
      "description": "Medium-risk item routed to avery (medium 2 for that reviewer) by round-robin."
    },
    {
      "kind": "route_canary",
      "reviewer": "avery",
      "description": "Canary routed to avery (canary 3 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "blake",
      "description": "Medium-risk item routed to blake (medium 2 for that reviewer) by round-robin."
    },
    {
      "kind": "route_canary",
      "reviewer": "blake",
      "description": "Canary routed to blake (canary 3 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_medium",
      "reviewer": "casey",
      "description": "Medium-risk item routed to casey (medium 2 for that reviewer) by round-robin."
    },
    {
      "kind": "route_high_risk",
      "reviewer": "avery",
      "description": "High-risk item routed to avery, the reviewer with the oldest last decision."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "avery",
      "description": "Medium-risk item routed to avery (medium 3 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "blake",
      "description": "Medium-risk item routed to blake (medium 3 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "casey",
      "description": "Medium-risk item routed to casey (medium 3 for that reviewer) by round-robin."
    },
    {
      "kind": "route_high_risk",
      "reviewer": "avery",
      "description": "High-risk item routed to avery, the reviewer with the oldest last decision."
    },
    {
      "kind": "route_canary",
      "reviewer": "casey",
      "description": "Canary routed to casey (canary 3 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 3 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_canary",
      "reviewer": "avery",
      "description": "Canary routed to avery (canary 4 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_canary",
      "reviewer": "blake",
      "description": "Canary routed to blake (canary 4 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_medium",
      "reviewer": "avery",
      "description": "Medium-risk item routed to avery (medium 4 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "blake",
      "description": "Medium-risk item routed to blake (medium 4 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "casey",
      "description": "Medium-risk item routed to casey (medium 4 for that reviewer) by round-robin."
    },
    {
      "kind": "route_high_risk",
      "reviewer": "avery",
      "description": "High-risk item routed to avery, the reviewer with the oldest last decision."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_canary",
      "reviewer": "casey",
      "description": "Canary routed to casey (canary 4 for that reviewer). Ties go to the careful reviewer."
    },
    {
      "kind": "route_medium",
      "reviewer": "avery",
      "description": "Medium-risk item routed to avery (medium 5 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "blake",
      "description": "Medium-risk item routed to blake (medium 5 for that reviewer) by round-robin."
    },
    {
      "kind": "batch_low_risk",
      "reviewer": "room",
      "description": "Batched 2 low-risk items so reviewers see them together."
    },
    {
      "kind": "route_medium",
      "reviewer": "casey",
      "description": "Medium-risk item routed to casey (medium 5 for that reviewer) by round-robin."
    }
  ],
  "adaptation_counts": [
    {
      "kind": "route_medium",
      "count": 15
    },
    {
      "kind": "route_canary",
      "count": 12
    },
    {
      "kind": "batch_low_risk",
      "count": 11
    },
    {
      "kind": "route_high_risk",
      "count": 5
    },
    {
      "kind": "flatness_explain_back",
      "count": 2
    }
  ],
  "recommendation": "Require blake to explain the diff in one sentence before every approval until the flatness rule clears: median at least 8 seconds, and, once they have 5 or more decisions, either a coefficient of variation of at least 0.25 or a median of at least 15 seconds.",
  "limits": "Limits: small sample; demonstrates the method, not statistical significance. Three simulated or live reviewers and one repository are enough to show the measurement, and they are not enough to estimate a population rate.",
  "safety": {
    "consent_first": true,
    "canaries_execute": false,
    "private_misses": true,
    "aggregate_export_only": true
  }
}