frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
39e9cecc340e4bb2af918b44d5e609436474b5fa
yao-meta-skill/reports/benchmark_reproducibility.json
T
yaojingang 39e9cecc34 Refresh clean benchmark for review studio cards
2026-06-16 07:02:24 +08:00

411 lines
14 KiB
JSON
Raw Blame History

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
"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": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"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": true,
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
"artifact_count": 25,
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b"
},
"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": "dc896e2929e25d8f517ded4024f2bce12030f4be14f885f76255be887117766c"
},
{
"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": 117850,
"sha256": "8a6f0eb0c627b1b8a7ffb45fd431b678827a91590028021e145d6b60d2fc4c2e"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 25061,
"sha256": "364e9bbc8dd4d163114fb758eb75126d9005412b1d1a2c5f7c229df2b77435a6"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "bd4b1f1cd5b21d0bda736ea14db4e6839e3729f66c787ef3be97619e8d069267"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "3fe267c06ebba290d312575d3042fc8a1125ebe7c07c1c555eae2948dbf845d0"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "0a127a000c337bf9d180b30ac7ff4fefd6a3392aa7c4c4b822f6b3727fbcfd50"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "de180d2b67b017d5654e10e34d58d56ab0e4861968e282f34777f3677522027e"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 20554,
"sha256": "38e95161404d2dc9a1c7bf3c1ee213a051ced5444deb01b0a01e557a4321021d"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 21587,
"sha256": "d08019f31a7811ee747392f24a11902f173201054894c0338d80b45543c88d18"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 19178,
"sha256": "4a9119aba62b7cbc9f6b434c33f58a73d2fd623e1f4ed67c3ca994f23025a317"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 36073,
"sha256": "5576411ceb4aeb9d0c2fd1ecbcd78d08f49c62149615c20cc77d4ab5db1736cc"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 13658,
"sha256": "6aaf868374ba134afbb4d4bf9c0339604ab41b7439379241359b83c279e9207f"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 24330,
"sha256": "40d1796964450e55bbaea98e46b0aa3433693e0b532c89b77ce5279c020570ff"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 15360,
"sha256": "ebfa3a4b528044bdf40f8931a246b54eb7cf37afe55bc02cad95f6e04ea4efa0"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 21284,
"sha256": "eb6c4506b0f25f01eef077c7c65bfe3f3230d3991b0db3befa8798768254373f"
},
{
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 18406,
"sha256": "704aba252d55e9b9f546392ce7f51b91f3b74d3384501d7f80a74e14c5b50acd"
}
],
"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