{
  "adjudication": {
    "expected_cells": 120,
    "ledger_sha256": "e0b4e1c1fa255d5955dea2bf3e76d913e641e9324a821c55e85a36e0589e5dff",
    "pending_cells": 0,
    "result_version": "offline-v2",
    "reviewed_cells": 120,
    "status": "complete"
  },
  "claim_boundary": "Full benchmark-contract compliance under two operational profiles. This purposive task set does not estimate representative implementation reliability, and the profile difference does not identify documentation causality.",
  "claim_scope": {
    "causal_claim_supported": false,
    "claim_type": "benchmark-contract-compliance",
    "conditions": [
      "controlled",
      "confirmatory-official-cloudscape-docs-v1"
    ],
    "primary_outcome_label": "Full benchmark-contract compliance",
    "representative_reliability_supported": false,
    "resource_condition_id": "confirmatory-official-cloudscape-docs-v1"
  },
  "condition_reports": [
    {
      "completed_runs": 60,
      "condition_id": "controlled",
      "evidence_compliance": {
        "full_pass_rate": 0.6833333333333333,
        "full_passes": 41,
        "mean_locator_validity": 0.997295,
        "mean_required_region_coverage": 0.81667,
        "mean_required_source_coverage": 1.0,
        "runs": 60
      },
      "label": "Frozen evidence only",
      "measurement_kind_results": {
        "contract-transcription": {
          "pass_rate": 0.5555555555555556,
          "passes": 10,
          "runs": 18
        },
        "executable-software": {
          "pass_rate": 0.3055555555555556,
          "passes": 11,
          "runs": 36
        },
        "governance-procedure": {
          "pass_rate": 1.0,
          "passes": 3,
          "runs": 3
        },
        "semantic-selection": {
          "pass_rate": 0.0,
          "passes": 0,
          "runs": 3
        }
      },
      "path": "conditions/controlled.json",
      "report_fingerprint": "b554b37faa9b7cac20105b9dc8e7349ba2355dcec0cfcd5e5ff1cfce8a25689e",
      "successful_runs": 24,
      "task_success_rate": 0.4,
      "tool_exposure": {
        "runs_with_requests": 0,
        "total_requests": 0
      },
      "usage_totals": {
        "cache_creation_input_tokens": 1613155,
        "cache_read_input_tokens": 498427,
        "cost_usd": 15.537983100000002,
        "input_tokens": 2111668,
        "output_tokens": 311251,
        "uncached_input_tokens": 86
      }
    },
    {
      "completed_runs": 60,
      "condition_id": "confirmatory-official-cloudscape-docs-v1",
      "evidence_compliance": {
        "full_pass_rate": 0.6,
        "full_passes": 36,
        "mean_locator_validity": 0.9291666666666667,
        "mean_required_region_coverage": 0.71667,
        "mean_required_source_coverage": 0.925,
        "runs": 60
      },
      "label": "Optional official Cloudscape resources",
      "measurement_kind_results": {
        "contract-transcription": {
          "pass_rate": 0.5555555555555556,
          "passes": 10,
          "runs": 18
        },
        "executable-software": {
          "pass_rate": 0.2222222222222222,
          "passes": 8,
          "runs": 36
        },
        "governance-procedure": {
          "pass_rate": 1.0,
          "passes": 3,
          "runs": 3
        },
        "semantic-selection": {
          "pass_rate": 0.3333333333333333,
          "passes": 1,
          "runs": 3
        }
      },
      "path": "conditions/confirmatory-official-cloudscape-docs-v1.json",
      "report_fingerprint": "c7eb64cc7eb43be5f243eb84eb0f072e4eed50278a5ddaa7999c90b78157b084",
      "successful_runs": 22,
      "task_success_rate": 0.36666666666666664,
      "tool_exposure": {
        "runs_with_requests": 12,
        "total_requests": 21
      },
      "usage_totals": {
        "cache_creation_input_tokens": 2015519,
        "cache_read_input_tokens": 911172,
        "cost_usd": 18.267431599999995,
        "input_tokens": 2926799,
        "output_tokens": 323418,
        "uncached_input_tokens": 108
      }
    }
  ],
  "cost_scope": "The recorded confirmatory calls only; offline remediation made no actor calls.",
  "excluded_calls_disclosure": "Calibration, canary, debugging, and interrupted calls are outside the 120-cell review population.",
  "failure_findings": [],
  "official_tool_use": {
    "runs_with_requests": 12,
    "total_requests": 21
  },
  "paired_descriptive_counts": {
    "helped": 9,
    "hurt": 11,
    "same": 40
  },
  "publication_format": "ds-eval/agent-publication@2",
  "replay_manifest": {
    "sha256": "1ca3f605b9cc9a7fde3d4db404780cdea5b8732024dbe7130154c1713ea269f6"
  },
  "report_fingerprint": "b554b37faa9b7cac20105b9dc8e7349ba2355dcec0cfcd5e5ff1cfce8a25689e",
  "system": "cloudscape",
  "task_review": {
    "measurement_valid_tasks": 20,
    "mutation_matrix_complete": true,
    "sha256": "c68ff6f3da064d23d176e00339ddcdbf158df723556dbd6fb04bb551ae64cae7",
    "tasks": 20
  }
}
