frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
10114cc4082486e3dab14422678c14aa28a135f9
yao-meta-skill/reports/benchmark_reproducibility.json
T
yaojingang 10114cc408 Refresh Review Studio panel reports
2026-06-17 01:31:17 +08:00

415 lines
14 KiB
JSON
Raw Blame History

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 2,
"sample": [
" M reports/context_budget.json",
" M reports/context_budget_summary.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": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3",
"source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
"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": 2
},
"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": "bc74e896e0241c17d25d94e198f91a2e2e7136cf",
"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": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3"
},
"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": 7966,
"sha256": "c0a5988ee9aff029b8c56b0a090aa23fc4efe803bd960f722b5a9a9c15a5c78d"
},
{
"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": 132641,
"sha256": "e0e8b047f580e5c8ff33580c49a99d3221919f52f6c5e3849976ed840a8618d9"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 28940,
"sha256": "c3fb22a905196a6d5242bde27f0b33f5233accacb478a80d1fd7a0582243e2bc"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "01100afaf317ebcdef836070636905bb3e4d64412c8a8f14d8758db822eba33c"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "6dde3b877e00b3e8936d0ffe1e45c77926639f5b21b0a4f30e779e6b4ffd4f57"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "7177ae392187ac0af2ed071c31c758e6e3e4d63230bbbcbdfc1b35719d23b966"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "867273823e8244ac65d44e69edb8c3d6c628b0f28f8a3bfdee612b802592654a"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 20828,
"sha256": "af3c3f101ad992820bf36ddb14b02e7404ef16411567c483f86eed530ca45f62"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 22285,
"sha256": "74deeabfac9f488a35cd816fdf8cd74a52fe73a82958770cbd7b41191a218814"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 19319,
"sha256": "69afd0ff3d49ba9e1ea57248e41cfe62a0abfdf06fd0f997ed3008a5656c2566"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 41202,
"sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 13655,
"sha256": "17def7ba6982d834e13ce3896dd9093019eec3ee8d2fa5b283ef8d6b17b19be0"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 24835,
"sha256": "00bfa998b24a37cf3f0354d3956f1c722041d5cbada0f4357f27f7c2187d11f1"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 15424,
"sha256": "337fb764b98ad2707f5a0d7bba88b9c5401256d7be00f8f3dc478e89e3bcb6c2"
},
{
"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": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f"
}
],
"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"
}
}
Reference in New Issue View Git Blame Copy Permalink