{
  "schema_version": "1.0",
  "ok": true,
  "generated_at": "2026-06-17",
  "skill_dir": ".",
  "commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
  "git_status": {
    "available": true,
    "dirty": true,
    "changed_file_count": 31,
    "sample": [
      " M registry/index.json",
      " M registry/packages/yao-meta-skill.json",
      " M reports/adoption_drift_report.json",
      " M reports/architecture_maintainability.json",
      " M reports/architecture_maintainability.md",
      " M reports/compiled_targets.json",
      " M reports/context_budget.json",
      " M reports/context_budget_summary.json",
      " M reports/evidence_consistency.json",
      " M reports/install_simulation.json",
      " M reports/install_simulation.md",
      " M reports/output_execution_runs.json"
    ],
    "scope": "generation-time status before this report is written"
  },
  "summary": {
    "reproducibility_ready": true,
    "release_lock_ready": false,
    "methodology_complete": true,
    "required_artifact_count": 25,
    "missing_artifact_count": 0,
    "evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
    "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
    "archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
    "output_case_count": 5,
    "failure_disclosure_count": 3,
    "command_count": 23,
    "command_executed_count": 10,
    "timing_observed_count": 10,
    "model_executed_count": 0,
    "token_observed_count": 0,
    "human_review_complete": false,
    "provider_evidence_complete": false,
    "world_class_ready": false,
    "world_class_open_gap_count": 4,
    "world_class_task_count": 4,
    "world_class_ledger_pending_count": 4,
    "world_class_source_check_count": 13,
    "world_class_source_pass_count": 7,
    "world_class_source_blocked_count": 6,
    "public_claim_ready": false,
    "public_claim_blocker_count": 5,
    "working_tree_dirty": true,
    "changed_file_count": 31
  },
  "public_claim": {
    "ready": false,
    "scope": "public benchmark or world-class readiness claim",
    "blockers": [
      "release lock is not clean or commit is unavailable",
      "provider-backed model holdout evidence is incomplete",
      "human blind-review adjudication is incomplete",
      "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
      "world-class source checks are not all accepted (7/13 pass, 6 blocked)"
    ],
    "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
  },
  "release_lock": {
    "ready": false,
    "commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
    "status_scope": "generation-time status before this report is written",
    "reason": "working tree was dirty at generation time"
  },
  "evidence_bundle": {
    "algorithm": "sha256(path,label,exists,artifact_sha256)",
    "artifact_count": 25,
    "existing_count": 25,
    "missing_count": 0,
    "missing_paths": [],
    "sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e"
  },
  "methodology": {
    "path": "reports/benchmark_methodology.md",
    "exists": true,
    "sections": [
      {
        "heading": "## Benchmark Types",
        "exists": true
      },
      {
        "heading": "## Sample Sources",
        "exists": true
      },
      {
        "heading": "## Evaluation Dimensions",
        "exists": true
      },
      {
        "heading": "## Weighting Rule",
        "exists": true
      },
      {
        "heading": "## Failure Disclosure",
        "exists": true
      },
      {
        "heading": "## Reproduction",
        "exists": true
      }
    ],
    "missing_sections": []
  },
  "artifacts_checked": [
    {
      "label": "methodology",
      "path": "reports/benchmark_methodology.md",
      "exists": true,
      "bytes": 2715,
      "sha256": "57025e0123ce5d10401c5bff376d2eeeac7943c83897ae1ad3fb22cadf790f92"
    },
    {
      "label": "failure_disclosure",
      "path": "evals/failure-cases.md",
      "exists": true,
      "bytes": 889,
      "sha256": "28833c0d4a217d612879d193fb5de199880dd5b3093ab5757e4315600fa4fb08"
    },
    {
      "label": "output_cases",
      "path": "evals/output/cases.jsonl",
      "exists": true,
      "bytes": 6555,
      "sha256": "a6ae9685711620d7203b73ace4412194ae287689f945b5139ec8ad75b9eefe04"
    },
    {
      "label": "output_schema",
      "path": "evals/output/schema.json",
      "exists": true,
      "bytes": 2193,
      "sha256": "8ee340c95064260c5e952be614e19841ac676162c6bf01d21b107e38cb04e0b9"
    },
    {
      "label": "output_scorecard",
      "path": "reports/output_quality_scorecard.json",
      "exists": true,
      "bytes": 25530,
      "sha256": "0806258a8e084b27e112537faff0de64a8519ca90cfdc78b57c0e4c08a514cca"
    },
    {
      "label": "output_execution",
      "path": "reports/output_execution_runs.json",
      "exists": true,
      "bytes": 7965,
      "sha256": "6a1d18e9ff6f3e2461fec034c4fe371d9e9c82ac57c32342d12849fed61ddc4d"
    },
    {
      "label": "blind_review",
      "path": "reports/output_blind_review_pack.json",
      "exists": true,
      "bytes": 7804,
      "sha256": "bbe2db8ec2776fe289cd7d6bb78d48c2b8baa106ad37f79c15e43669b10c9390"
    },
    {
      "label": "review_adjudication",
      "path": "reports/output_review_adjudication.json",
      "exists": true,
      "bytes": 10135,
      "sha256": "bb8c72a9291e329c83890884af9b73535a6cb86fa435afe2d6ba2ff07d88a02c"
    },
    {
      "label": "trigger_scorecard",
      "path": "reports/route_scorecard.json",
      "exists": true,
      "bytes": 16961,
      "sha256": "c164e83e36d0af276b6af2de2a5e026d7f0711b83eef2b5dcd0e760bd8bb28fc"
    },
    {
      "label": "runtime_conformance",
      "path": "reports/conformance_matrix.json",
      "exists": true,
      "bytes": 10342,
      "sha256": "97f9ba949c23a60b00e9ba2ff279ca03ba517845cc7c62aa8a42645d58006c7e"
    },
    {
      "label": "trust_report",
      "path": "reports/security_trust_report.json",
      "exists": true,
      "bytes": 133860,
      "sha256": "d865e5cc97a3b92e1332366c5c780354afb46038ba1c6ef152a61cc8407a19bc"
    },
    {
      "label": "python_compatibility",
      "path": "reports/python_compatibility.json",
      "exists": true,
      "bytes": 29196,
      "sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2"
    },
    {
      "label": "registry_audit",
      "path": "reports/registry_audit.json",
      "exists": true,
      "bytes": 3183,
      "sha256": "0412ab0eff34056858b8078f363f6cba2cc46ac294f0a165bfdab388287904f2"
    },
    {
      "label": "package_verification",
      "path": "reports/package_verification.json",
      "exists": true,
      "bytes": 19338,
      "sha256": "52f419800aa43fc1c5f0abd465da2ca67640d4f26efb06659534bf73f1480d2c"
    },
    {
      "label": "install_simulation",
      "path": "reports/install_simulation.json",
      "exists": true,
      "bytes": 8758,
      "sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7"
    },
    {
      "label": "skill_os2_audit",
      "path": "reports/skill_os2_audit.json",
      "exists": true,
      "bytes": 14310,
      "sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e"
    },
    {
      "label": "world_class_evidence_plan",
      "path": "reports/world_class_evidence_plan.json",
      "exists": true,
      "bytes": 20828,
      "sha256": "9b74155fb9bfe44ba838d64b1a31768b83978b154bdd8eaa606f494c816f189f"
    },
    {
      "label": "world_class_evidence_ledger",
      "path": "reports/world_class_evidence_ledger.json",
      "exists": true,
      "bytes": 22285,
      "sha256": "f6e1a69b0359c28c88e9e9e69ff66763c721ac8a112a43a673ce98cd9d3bce41"
    },
    {
      "label": "world_class_evidence_intake",
      "path": "reports/world_class_evidence_intake.json",
      "exists": true,
      "bytes": 19319,
      "sha256": "46f801051ec075725059e4e2682ef2162fd892b5e7255c8d5121d7b24dcc7f2c"
    },
    {
      "label": "world_class_evidence_preflight",
      "path": "reports/world_class_evidence_preflight.json",
      "exists": true,
      "bytes": 41202,
      "sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454"
    },
    {
      "label": "world_class_submission_review",
      "path": "reports/world_class_submission_review.json",
      "exists": true,
      "bytes": 13655,
      "sha256": "9fbd4cd437986fca9a043cbab24aec7d575aaf166a8d9365c79c56f093cab5b8"
    },
    {
      "label": "world_class_operator_runbook",
      "path": "reports/world_class_operator_runbook.json",
      "exists": true,
      "bytes": 24835,
      "sha256": "2d32a2e917b7215afe7a7a93ca8bacffa540a245953aa39e2ee47eea1b169d17"
    },
    {
      "label": "world_class_operator_runbook_markdown",
      "path": "reports/world_class_operator_runbook.md",
      "exists": true,
      "bytes": 15424,
      "sha256": "00d8ebabb91e14a06cacdb212f448668aa1e47b72587448e30681fc53acaad9a"
    },
    {
      "label": "world_class_operator_runbook_html",
      "path": "reports/world_class_operator_runbook.html",
      "exists": true,
      "bytes": 21348,
      "sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49"
    },
    {
      "label": "world_class_claim_guard",
      "path": "reports/world_class_claim_guard.json",
      "exists": true,
      "bytes": 18596,
      "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
    }
  ],
  "missing_artifacts": [],
  "reproduction_commands": [
    {
      "label": "source commit",
      "command": "git rev-parse HEAD",
      "evidence": "git commit hash"
    },
    {
      "label": "trigger eval",
      "command": "make eval-suite",
      "evidence": "reports/eval_suite.json"
    },
    {
      "label": "output eval",
      "command": "python3 scripts/yao.py output-eval",
      "evidence": "reports/output_quality_scorecard.json"
    },
    {
      "label": "output execution",
      "command": "python3 scripts/yao.py output-exec --runner-command '[\"python3\",\"scripts/local_output_eval_runner.py\"]'",
      "evidence": "reports/output_execution_runs.json"
    },
    {
      "label": "blind review adjudication",
      "command": "python3 scripts/yao.py output-review",
      "evidence": "reports/output_review_adjudication.json"
    },
    {
      "label": "skill ir",
      "command": "python3 scripts/yao.py skill-ir . --output-json skill-ir/examples/yao-meta-skill.json",
      "evidence": "skill-ir/examples/yao-meta-skill.json"
    },
    {
      "label": "runtime conformance",
      "command": "python3 scripts/yao.py conformance .",
      "evidence": "reports/conformance_matrix.json"
    },
    {
      "label": "trust report",
      "command": "python3 scripts/yao.py trust .",
      "evidence": "reports/security_trust_report.json"
    },
    {
      "label": "python compatibility",
      "command": "python3 scripts/yao.py python-compat .",
      "evidence": "reports/python_compatibility.json"
    },
    {
      "label": "package",
      "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --expectations evals/packaging_expectations.json --output-dir dist --zip",
      "evidence": "dist/yao-meta-skill.zip"
    },
    {
      "label": "package verify",
      "command": "python3 scripts/yao.py package-verify . --package-dir dist --require-zip",
      "evidence": "reports/package_verification.json"
    },
    {
      "label": "install simulate",
      "command": "python3 scripts/yao.py install-simulate . --package-dir dist",
      "evidence": "reports/install_simulation.json"
    },
    {
      "label": "registry audit",
      "command": "python3 scripts/yao.py registry-audit .",
      "evidence": "reports/registry_audit.json"
    },
    {
      "label": "skill os audit",
      "command": "python3 scripts/yao.py skill-os2-audit .",
      "evidence": "reports/skill_os2_audit.json"
    },
    {
      "label": "world-class evidence plan",
      "command": "python3 scripts/yao.py world-class-evidence .",
      "evidence": "reports/world_class_evidence_plan.json"
    },
    {
      "label": "world-class evidence ledger",
      "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_evidence_ledger.json"
    },
    {
      "label": "world-class evidence intake",
      "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_evidence_intake.json"
    },
    {
      "label": "world-class evidence preflight",
      "command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_evidence_preflight.json"
    },
    {
      "label": "world-class submission review",
      "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_submission_review.json"
    },
    {
      "label": "world-class operator runbook",
      "command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_operator_runbook.json"
    },
    {
      "label": "world-class claim guard",
      "command": "python3 scripts/yao.py world-class-claim-guard .",
      "evidence": "reports/world_class_claim_guard.json"
    },
    {
      "label": "evidence consistency",
      "command": "python3 scripts/yao.py evidence-consistency .",
      "evidence": "reports/evidence_consistency.json"
    },
    {
      "label": "full ci",
      "command": "make ci-test",
      "evidence": "CI target output"
    }
  ],
  "failure_disclosure": {
    "path": "evals/failure-cases.md",
    "case_count": 3,
    "policy": "Keep representative failures visible and tied to regression checks."
  },
  "limitations": [
    "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
    "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
    "Pending blind-review decisions are visible but do not count as human adjudication.",
    "World-class readiness remains false until external and human evidence gaps close."
  ],
  "artifacts": {
    "json": "reports/benchmark_reproducibility.json",
    "markdown": "reports/benchmark_reproducibility.md"
  }
}