diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 5850282..3529563 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,30 +3,17 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "effbf3f74c4ce959c7444d873d0586d884a43202", + "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 65, - "sample": [ - " M Makefile", - " M README.md", - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " M reports/adoption_drift_report.json", - " M reports/adoption_drift_report.md", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", - " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md", - " M reports/compiled_targets.json", - " M reports/context_budget.json" - ], + "dirty": false, + "changed_file_count": 0, + "sample": [], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -50,15 +37,14 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 65 + "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": [ - "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)", @@ -67,10 +53,10 @@ "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": "effbf3f74c4ce959c7444d873d0586d884a43202", + "ready": true, + "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", "status_scope": "generation-time status before this report is written", - "reason": "working tree was dirty at generation time" + "reason": "clean generation-time HEAD" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 2e0b0c6..a13a7f7 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,14 +1,14 @@ # Benchmark Reproducibility Generated at: `2026-06-15` -Commit: `effbf3f74c4ce959c7444d873d0586d884a43202` -Working tree dirty at generation: `true` +Commit: `a5dab4779d48b51ea8ace316527d38dd559e6b01` +Working tree dirty at generation: `false` Evidence bundle SHA256: `c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49` ## Summary - reproducibility ready: `true` -- release lock ready: `false` +- release lock ready: `true` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a6 - world-class ready: `false` - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `5` -- changed files at generation: `65` +- public claim blockers: `4` +- changed files at generation: `0` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,7 +35,6 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | -| 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) | @@ -43,8 +42,8 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `false` -- reason: working tree was dirty at generation time +- ready: `true` +- reason: clean generation-time HEAD - status scope: generation-time status before this report is written ## Evidence Bundle diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 2e62acd..a6d9d69 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -37,8 +37,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": false, - "actual": false, + "expected": true, + "actual": true, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -48,8 +48,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "effbf3f74c4ce959c7444d873d0586d884a43202", - "actual": "effbf3f74c4ce959c7444d873d0586d884a43202", + "expected": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "actual": "a5dab4779d48b51ea8ace316527d38dd559e6b01", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -61,7 +61,7 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -71,10 +71,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -84,7 +84,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -194,8 +194,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "effbf3f74c4ce959c7444d873d0586d884a43202", - "actual": "effbf3f74c4ce959c7444d873d0586d884a43202", + "expected": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "actual": "a5dab4779d48b51ea8ace316527d38dd559e6b01", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -207,7 +207,7 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -217,10 +217,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -230,7 +230,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -1324,10 +1324,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 215 + "file_count": 132 } ], - "file_count": 389, + "file_count": 306, "folder_count": 4, "distribution": [ { @@ -1360,7 +1360,7 @@ }, { "label": "reports", - "value": 215 + "value": 132 } ] }, @@ -1412,10 +1412,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 215 + "file_count": 132 } ], - "file_count": 389, + "file_count": 306, "folder_count": 4, "distribution": [ { @@ -1448,7 +1448,7 @@ }, { "label": "reports", - "value": 215 + "value": 132 } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 90ac880..54f832c 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -525,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 215 + "file_count": 132 } ], - "file_count": 389, + "file_count": 306, "folder_count": 4, "distribution": [ { @@ -561,7 +561,7 @@ }, { "label": "reports", - "value": 215 + "value": 132 } ] }, @@ -695,7 +695,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 215 + "file_count": 132 } ], "strengths": [ @@ -996,7 +996,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -1020,11 +1020,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 65 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "effbf3f74c4ce959c7444d873d0586d884a43202", + "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 6e8bccf..057d43e 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -930,7 +930,7 @@
让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.
| 路径Path | 作用Role | 类型Type |
|---|---|---|
| SKILL.md | Skill 入口文件Skill entrypoint | 文件file |
| README.md | 人类可读使用说明Human-readable usage guide | 文件file |
| agents/interface.yaml | 跨平台接口元数据Neutral interface metadata | 文件file |
| manifest.json | 生命周期与打包元数据Lifecycle and portability metadata | 文件file |
| references | 扩展指导与复用资料Extended guidance and reusable notes | 目录folder |
| scripts | 确定性脚本或本地工具Deterministic helpers or local tooling | 目录folder |
| evals | 触发与质量检查Trigger and quality checks | 目录folder |
| reports | 生成的证据与总结报告Generated evidence and overview artifacts | 目录folder |
| 路径Path | 作用Role | 类型Type |
|---|---|---|
| SKILL.md | Skill 入口文件Skill entrypoint | 文件file |
| README.md | 人类可读使用说明Human-readable usage guide | 文件file |
| agents/interface.yaml | 跨平台接口元数据Neutral interface metadata | 文件file |
| manifest.json | 生命周期与打包元数据Lifecycle and portability metadata | 文件file |
| references | 扩展指导与复用资料Extended guidance and reusable notes | 目录folder |
| scripts | 确定性脚本或本地工具Deterministic helpers or local tooling | 目录folder |
| evals | 触发与质量检查Trigger and quality checks | 目录folder |
| reports | 生成的证据与总结报告Generated evidence and overview artifacts | 目录folder |