Files
yao-meta-skill/reports/benchmark_reproducibility.json
T
2026-06-17 04:01:58 +08:00

425 lines
14 KiB
JSON

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 38,
"sample": [
" M assets/review-studio.css",
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/evidence_consistency.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": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"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": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 38
},
"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 (9/19 pass, 10 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": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"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": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49"
},
"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": 7967,
"sha256": "4ea56f4558ee371f71a7908f55a1fbcd2d3f3f18a517a6642a5ed7df6a204b59"
},
{
"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": 14084,
"sha256": "91fd88dd9b0f8876f68027a87893d1852dac59772613345bbbfabba658c9227e"
},
{
"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": 134467,
"sha256": "525f9766700afd55e2b5113b5f30a1ca4826ebab0902228a702f7927bffb6019"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29464,
"sha256": "f53cce322cc33af4f7cbc7e22587ac3e0c0359dfa1889a03f38c93472abf319d"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "995ded23370adb49997ef5bdd37e32c59b6aad31ed7813c7520e7e7b40d6e546"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "afb99167c57179ff0435c678e7e5638ceaed07042fa9177568ca21d6dc1bef3d"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "08d96de4662c8e047e351f4241ff3a4f98c521907fc4cd703faadff861bee63a"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14466,
"sha256": "7fc0b099204ca5045de2db9eb19c5cf599f9c87bed1cd7f39c1f5f50704b3fb2"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 22784,
"sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 26019,
"sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 20646,
"sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 58119,
"sha256": "10671b699295453b130ef8afe6488d2a4ac3220a901df2f86a69ee5eb896c36e"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 17302,
"sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 28935,
"sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 17576,
"sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 24019,
"sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7"
},
{
"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"
}
}