From 220f68a066973a875c2b91f3c5f8aaacdf3bc90f Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 07:12:08 +0800 Subject: [PATCH] Refresh downstream reports for artifact roles --- reports/evidence_consistency.json | 28 +++++++++---------- reports/review-studio.html | 6 ++-- reports/review-studio.json | 46 +++++++++++-------------------- reports/review-viewer.json | 10 +++---- reports/skill-interpretation.json | 10 +++---- reports/skill-overview.json | 10 +++---- 6 files changed, 48 insertions(+), 62 deletions(-) diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index f7b2420..7dde5d6 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" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", - "actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "expected": "28c83c6976717daff13667d775bbbc1dbc377dc0", + "actual": "28c83c6976717daff13667d775bbbc1dbc377dc0", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,7 +261,7 @@ "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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c", @@ -271,10 +271,10 @@ "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": 25, "missing_artifact_count": 0, "source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c", @@ -284,7 +284,7 @@ "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", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", - "actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "expected": "28c83c6976717daff13667d775bbbc1dbc377dc0", + "actual": "28c83c6976717daff13667d775bbbc1dbc377dc0", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,7 +407,7 @@ "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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c", @@ -417,10 +417,10 @@ "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": 25, "missing_artifact_count": 0, "source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c", @@ -430,7 +430,7 @@ "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", diff --git a/reports/review-studio.html b/reports/review-studio.html index 10f3d0e..f93d883 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -711,7 +711,7 @@

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

Blueprint21/21

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

121 scripts scanned; secrets found

Py Compat0

193 files scanned for Python 3.11

Arch Debt0

899 largest lines; 9 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

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

646 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

Blueprint21/21

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

121 scripts scanned; secrets found

Py Compat0

193 files scanned for Python 3.11

Arch Debt0

899 largest lines; 9 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

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

646 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

@@ -848,8 +848,8 @@
-

公开声明

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

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 (6/13 pass, 7 blocked)
+

公开声明

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

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 (6/13 pass, 7 blocked)
diff --git a/reports/review-studio.json b/reports/review-studio.json index 852d1cb..e3ae3d3 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1812,7 +1812,7 @@ "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, @@ -1836,11 +1836,11 @@ "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": 22 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "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.", @@ -5446,30 +5446,17 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 22, - "sample": [ - " M evidence/world_class/README.md", - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", - " M reports/context_budget.json", - " M reports/context_budget.md", - " M reports/context_budget_summary.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/package_verification.json", - " M reports/package_verification.md" - ], + "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, @@ -5493,15 +5480,14 @@ "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": 22 + "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)", @@ -5510,10 +5496,10 @@ "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": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "ready": true, + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "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 57dde33..2a93f91 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -997,7 +997,7 @@ "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, @@ -1021,11 +1021,11 @@ "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": 22 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "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 ef4027b..1399d0f 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1001,7 +1001,7 @@ "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, @@ -1025,11 +1025,11 @@ "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": 22 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "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 d3ce9ed..59c5360 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.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": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 22 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b", + "commit": "28c83c6976717daff13667d775bbbc1dbc377dc0", "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.",