Files
yao-meta-skill/reports/benchmark_reproducibility.json
T
2026-06-14 14:27:15 +08:00

408 lines
14 KiB
JSON

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "fd5a790df90b2b6faad58b671c42171186504bac",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 12,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.md",
" M reports/registry_audit.json",
" M reports/registry_audit.md",
" M reports/security_trust_report.json",
" M reports/security_trust_report.md",
" M reports/upgrade_check.json",
" M reports/world_class_operator_runbook.html"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53",
"source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c",
"archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
"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": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 12
},
"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 (6/13 pass, 7 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": "fd5a790df90b2b6faad58b671c42171186504bac",
"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": 24,
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53"
},
"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": "d8028784464931bc1d44ce097feb95e531682ee5172f4e9680da7a11f93b2b98"
},
{
"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": 9495,
"sha256": "240485a721af49d5c75fe8049e9ef74b50546f685aa6346ab9e20713fb1105f4"
},
{
"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": 10313,
"sha256": "8251329e663dda51472f29b7721e73d72ccbec9760d96fda022f6218a5a6e347"
},
{
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 99433,
"sha256": "7fccfda339c51073eb1c8325ac7740e7c6f44f4067b4ba66cba1afd5f095ac25"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 20747,
"sha256": "ae16e17266e4e7fed08f4423f8abca7902b0d1cc0839b5692925c62463b72e58"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "f919e3f7834aee8891c5cc97a26ea9f8045b30b3c41e0bf6bbe9a1c13ee63d83"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "53af9d5a90682b65f190cd9b0cf99aaa1496cb3d16c7199df06d5bdfa0ded491"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "1ed7ce5266c2dd7ee8daf83a3a5c65cdb69ade1567a33b88b77b619d3f5afa16"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14309,
"sha256": "6bb2dcb0e1e590deacd04c28a86bc74769c82810ecca6a5f660d6615e8db7c18"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 19940,
"sha256": "164803bb1cea795c8b962ec82cb1b3a4a58bbc51e10a4edfce12de00d046905a"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 16763,
"sha256": "7b3d12cd30870cb361b7bb09e43d5ea88fd5bbe35a6d78f91303862a71489ff2"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 15552,
"sha256": "8f7f9db6f8999ba65078968f8e8383ad4a385000d60bc83ff822a3ca582cc6ce"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 12413,
"sha256": "a6d609911ed5d14a4e710233f3207a12750982eaa1f9d6d6ebc5d612b16e7ac4"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 20738,
"sha256": "443e0335d2703160a41bb6dbd077268f889c0e55e27ca15483d17a3b635213a2"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 12104,
"sha256": "4bd789775307e1b7730be09b0c46d35f678cdee67ef2c7ea29a81c97dd446e24"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 17616,
"sha256": "b94a0e9d92b6609eb6c06e608b52aa17174638bc1422e3b3d306521906bccb01"
},
{
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 8463,
"sha256": "250d616b028cf046e2033f9e2c5648c8d95c110d0d8990b35e4d481e14cfc558"
}
],
"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 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": "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"
}
}