From ac327630910196a2e0b2a028879bc7dabfe13fbb Mon Sep 17 00:00:00 2001 From: yaojingang Date: Wed, 17 Jun 2026 00:24:10 +0800 Subject: [PATCH] Refresh clean stale-lock release reports --- reports/benchmark_reproducibility.json | 33 +++++++------------- reports/benchmark_reproducibility.md | 15 +++++---- reports/evidence_consistency.json | 30 +++++++++--------- reports/review-studio.html | 6 ++-- reports/review-studio.json | 43 ++++++++++---------------- reports/review-viewer.json | 10 +++--- reports/skill-interpretation.json | 10 +++--- reports/skill-overview.json | 10 +++--- 8 files changed, 67 insertions(+), 90 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index c5a32d6a..c0c5880a 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,27 +3,17 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 9, - "sample": [ - " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md", - " M reports/evidence_consistency.json", - " M reports/evidence_consistency.md", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json", - " M reports/skill-overview.html", - " M reports/skill-overview.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, @@ -47,15 +37,14 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "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)", @@ -64,10 +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": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "ready": true, + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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 c9e742c3..4cfbf271 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,14 +1,14 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `7476c7ccbfaa094932809d405accf3aca9bc16ea` -Working tree dirty at generation: `true` +Commit: `b6ded57f9cc65b1dd7dbbac9c394647dadc131d7` +Working tree dirty at generation: `false` Evidence bundle SHA256: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f` ## 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: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc10 - world-class ready: `false` - world-class source checks: `7` pass / `13` total; `6` blocked - public claim ready: `false` -- public claim blockers: `5` -- changed files at generation: `9` +- 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 05c8b483..2c30071e 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -207,8 +207,8 @@ "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" ], @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 10 + "changed_file_count": 7 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "7476c7ccbfaa094932809d405accf3aca9bc16ea", - "actual": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -276,7 +276,7 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", @@ -286,10 +286,10 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "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": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", @@ -299,7 +299,7 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "7476c7ccbfaa094932809d405accf3aca9bc16ea", - "actual": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -422,7 +422,7 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", @@ -432,10 +432,10 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "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": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", @@ -445,7 +445,7 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", diff --git a/reports/review-studio.html b/reports/review-studio.html index 9893aed6..438e1d7c 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,7 +740,7 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint20/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint20/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

@@ -882,8 +882,8 @@
-

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (7/13 pass, 6 blocked)
+

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (7/13 pass, 6 blocked)
diff --git a/reports/review-studio.json b/reports/review-studio.json index 00a8a2db..0911cf8a 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1959,7 +1959,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, @@ -1983,11 +1983,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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.", @@ -5650,27 +5650,17 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 9, - "sample": [ - " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md", - " M reports/evidence_consistency.json", - " M reports/evidence_consistency.md", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json", - " M reports/skill-overview.html", - " M reports/skill-overview.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, @@ -5694,15 +5684,14 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "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)", @@ -5711,10 +5700,10 @@ "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": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "ready": true, + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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/review-viewer.json b/reports/review-viewer.json index d1afed9b..583b73e3 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -996,7 +996,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, @@ -1020,11 +1020,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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.json b/reports/skill-interpretation.json index 921ed3f3..d22b8fbe 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1000,7 +1000,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, @@ -1024,11 +1024,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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-overview.json b/reports/skill-overview.json index 70ad6166..2360c489 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -995,7 +995,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, @@ -1019,11 +1019,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 9 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "7476c7ccbfaa094932809d405accf3aca9bc16ea", + "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", "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.",