yaojingang
411 lines
14 KiB
JSON
411 lines
14 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-16",
|
|
"skill_dir": ".",
|
|
"commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
|
|
"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": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
|
|
"source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
|
|
"archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
|
|
"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": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
|
|
"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": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1"
|
|
},
|
|
"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": "ab66dfd1a1f2fca481752aa164271a8c4f419cab9653f45dd63d1c73011713bb"
|
|
},
|
|
{
|
|
"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": 118486,
|
|
"sha256": "ca53fbf5fa66f574d34603b160c3c3a264b015ba2722deb930b5accb94b52af8"
|
|
},
|
|
{
|
|
"label": "python_compatibility",
|
|
"path": "reports/python_compatibility.json",
|
|
"exists": true,
|
|
"bytes": 25199,
|
|
"sha256": "18c8a142c8108071bc453367c1fd3589b3368c098d5fc27f4b1d11c19f0bfb92"
|
|
},
|
|
{
|
|
"label": "registry_audit",
|
|
"path": "reports/registry_audit.json",
|
|
"exists": true,
|
|
"bytes": 3183,
|
|
"sha256": "7f980caf507c7d094401a18194eeeb7480de3a924326b6d0c97e07b33e3fb64f"
|
|
},
|
|
{
|
|
"label": "package_verification",
|
|
"path": "reports/package_verification.json",
|
|
"exists": true,
|
|
"bytes": 19338,
|
|
"sha256": "bbe73152879cad38600925a9a6d9847f9b3ee279d9197dadf867dadca259bb29"
|
|
},
|
|
{
|
|
"label": "install_simulation",
|
|
"path": "reports/install_simulation.json",
|
|
"exists": true,
|
|
"bytes": 8604,
|
|
"sha256": "aa45be12d2a94664dce95884668839d58808eaad70de90cfb1e96939e9e3a3c0"
|
|
},
|
|
{
|
|
"label": "skill_os2_audit",
|
|
"path": "reports/skill_os2_audit.json",
|
|
"exists": true,
|
|
"bytes": 14310,
|
|
"sha256": "a4dfc4e3af1167e3d6ced9444c41bc6cd2133bb67942fedba94c046814bf7866"
|
|
},
|
|
{
|
|
"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": 41071,
|
|
"sha256": "37fd4b91f92ceda3a5873431d5629b33c7909c10fbdc465eaad546e45562328f"
|
|
},
|
|
{
|
|
"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"
|
|
}
|
|
}
|