frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
fbaa3c821296303ee9b1fc892de970f2a74b475a
yao-meta-skill/reports/benchmark_reproducibility.json
T
yaojingang a25be312bc docs: refresh review studio waiver page
2026-06-14 11:34:38 +08:00

390 lines
13 KiB
JSON
Raw Blame History

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "78f94e47fd7ab999fdfc6d18ffb9917cf8848dba",
"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": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "d1e46322a670ebd2d3977fd716c13b3d00bc37816e83343fc21978eba96d40bb",
"source_contract_sha256": "e38d34ebe54c377f47f6010c06716f8f972406cf1019a27e6ebc057371dd260f",
"archive_sha256": "0e4ba92cd88c099965383daf5c3d6319b917d7c83d5ef29917f1cd932c1bd6f8",
"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,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"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)"
],
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, and accepted world-class evidence."
},
"release_lock": {
"ready": true,
"commit": "78f94e47fd7ab999fdfc6d18ffb9917cf8848dba",
"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": 24,
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "d1e46322a670ebd2d3977fd716c13b3d00bc37816e83343fc21978eba96d40bb"
},
"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": 7964,
"sha256": "c90136a4365e2db855de37883bff7266b581bb132717770e041f05e4b01c282e"
},
{
"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": 98830,
"sha256": "cec71ebc7eec3de04ff3d9e52169717937cb69ff95deae41d5996c88611c73c4"
},
{
"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": "7deef4fe2b76eaf4dd42fb35d6d61bf0afecfae64367c5cbf603de80aac14ad5"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "0b7b5be95961826b0ab64e77564205690349470effa3c79285649cc66f961136"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "8f987e805c92bf4178e3f246356ab268e59f62e9b6948be09f5c53054e7780ec"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14309,
"sha256": "3e2b95bc7fbd36d298cb1912c4a938d6239910ba522c208867b797f8ae6f73e8"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 19532,
"sha256": "941beb1a554a9367ba9fba6f7d6d1a73f873460b90c20c6714914f99a125056a"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 11613,
"sha256": "66f142054d90ce2f688ce875ddec3b06aa93cae27ea62877d14e3b8d2ebda6bc"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 13743,
"sha256": "9f382cb3717160cff3eccf63312e20fc670183139e2ce86ce5096a59cc1b9110"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 7263,
"sha256": "185a8cab25e7155ebd80cb66049c0965e4dc2d7cc38991f17464946f87fd26f2"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 15002,
"sha256": "3d643dc8170b50a37f91ffb190f69ad1e0d32f64914ebe2d731226728ac28cdc"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 9241,
"sha256": "302cfaa160ab7b50afda58a9e330e1219f47786b39b1e14d81ccc09c0ba10319"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 13226,
"sha256": "699da59fb4c5646a253e9688a35f24c692c9875083128220305d1d93a317f208"
},
{
"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 .",
"evidence": "reports/world_class_evidence_ledger.json"
},
{
"label": "world-class evidence intake",
"command": "python3 scripts/yao.py world-class-intake .",
"evidence": "reports/world_class_evidence_intake.json"
},
{
"label": "world-class submission review",
"command": "python3 scripts/yao.py world-class-submission-review .",
"evidence": "reports/world_class_submission_review.json"
},
{
"label": "world-class operator runbook",
"command": "python3 scripts/yao.py world-class-runbook .",
"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"
}
}
Reference in New Issue View Git Blame Copy Permalink