yaojingang
390 lines
13 KiB
JSON
390 lines
13 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-14",
|
|
"skill_dir": ".",
|
|
"commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4",
|
|
"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": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de",
|
|
"source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
|
|
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
|
|
"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": "7cbbf58078b146fdb6f2e7678934f057e961bdf4",
|
|
"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": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de"
|
|
},
|
|
"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": "2c230fbc6455657eec1738b43c33cf31219a6e70b8e5d846bada11e1051c3168"
|
|
},
|
|
{
|
|
"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": "3c69120778acb66ad88743c62d26d119a23abab81926e2f8f0ed9cfbc483318c"
|
|
},
|
|
{
|
|
"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": "9387060b0ca239dde97a2f80fc0917cce44ff343ee99893af8f5443d7ebf75bc"
|
|
},
|
|
{
|
|
"label": "package_verification",
|
|
"path": "reports/package_verification.json",
|
|
"exists": true,
|
|
"bytes": 19325,
|
|
"sha256": "007d65fe23663d4377861b2e44612629eb3a90e0b1f400e763132bf5e6495f0a"
|
|
},
|
|
{
|
|
"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": "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": 11613,
|
|
"sha256": "0bff14542475657a1261c1afcd87ffabc5d5c5e75bcd20afcfeacc44b16b7c14"
|
|
},
|
|
{
|
|
"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": 7263,
|
|
"sha256": "4f03edb2ef28d9dfd27a393f8058d6e27d2b10fa8cbfe35f473e003556b9ffe0"
|
|
},
|
|
{
|
|
"label": "world_class_operator_runbook",
|
|
"path": "reports/world_class_operator_runbook.json",
|
|
"exists": true,
|
|
"bytes": 15206,
|
|
"sha256": "43492b169ade7202f4fcd5db989e314c3b04cb96d6178ec6854bb90788d7e586"
|
|
},
|
|
{
|
|
"label": "world_class_operator_runbook_markdown",
|
|
"path": "reports/world_class_operator_runbook.md",
|
|
"exists": true,
|
|
"bytes": 9445,
|
|
"sha256": "cb05eec07f1ed0939fecbfc46b9101029498be6b8ebc03bb536fa3223e5846af"
|
|
},
|
|
{
|
|
"label": "world_class_operator_runbook_html",
|
|
"path": "reports/world_class_operator_runbook.html",
|
|
"exists": true,
|
|
"bytes": 13430,
|
|
"sha256": "68b45d5f6f88df6eb22ad23643846e60207ab41af11d9c85cb20d5fe3e0e7182"
|
|
},
|
|
{
|
|
"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"
|
|
}
|
|
}
|