From 39e9cecc340e4bb2af918b44d5e609436474b5fa Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 07:02:24 +0800 Subject: [PATCH] Refresh clean benchmark for review studio cards --- reports/benchmark_reproducibility.json | 44 +++++++++----------------- reports/benchmark_reproducibility.md | 21 ++++++------ 2 files changed, 25 insertions(+), 40 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 916697ae..24b4e592 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,34 +3,21 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "5338a770167da589a140c71ff0cd589ee5a3e8f4", + "commit": "30451d41f615562dfd0380414cc8447d4dad5e38", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 52, - "sample": [ - " M AGENTS.md", - " M references/review-studio-method.md", - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " 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", - " M reports/context_budget.md", - " M reports/context_budget_summary.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": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "a6a800e88be9348c69020f14560db3a902a8e24bbafc79b5d31200f42d3a6191", + "evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b", "source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60", "archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca", "output_case_count": 5, @@ -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": 52 + "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": "5338a770167da589a140c71ff0cd589ee5a3e8f4", + "ready": true, + "commit": "30451d41f615562dfd0380414cc8447d4dad5e38", "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)", @@ -78,7 +64,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "a6a800e88be9348c69020f14560db3a902a8e24bbafc79b5d31200f42d3a6191" + "sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -249,8 +235,8 @@ "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 36067, - "sha256": "1e6c66fc5e3ceec580313f3dbdc7e26d3526832c591c2c4281f52779d2f6242d" + "bytes": 36073, + "sha256": "5576411ceb4aeb9d0c2fd1ecbcd78d08f49c62149615c20cc77d4ab5db1736cc" }, { "label": "world_class_submission_review", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index efda5b1c..11ce79f1 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,14 +1,14 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `5338a770167da589a140c71ff0cd589ee5a3e8f4` -Working tree dirty at generation: `true` -Evidence bundle SHA256: `a6a800e88be9348c69020f14560db3a902a8e24bbafc79b5d31200f42d3a6191` +Commit: `30451d41f615562dfd0380414cc8447d4dad5e38` +Working tree dirty at generation: `false` +Evidence bundle SHA256: `f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b` ## Summary - reproducibility ready: `true` -- release lock ready: `false` +- release lock ready: `true` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `a6a800e88be9348c69020f14560db3a902a8e24bbafc79b5d31200f - 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: `52` +- 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) | @@ -43,15 +42,15 @@ 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 - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `a6a800e88be9348c69020f14560db3a902a8e24bbafc79b5d31200f42d3a6191` +- sha256: `f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b` ## Methodology Sections @@ -87,7 +86,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `38e95161404d` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `d08019f31a78` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `4a9119aba62b` | -| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `1e6c66fc5e3c` | +| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `5576411ceb4a` | | world_class_submission_review | `reports/world_class_submission_review.json` | present | `6aaf868374ba` | | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `40d179696445` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `ebfa3a4b5280` |