chore: refresh top-level source maturity clean-lock evidence
This commit is contained in:
yaojingang
@@ -3,29 +3,17 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-14",
|
||||
"skill_dir": ".",
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 11,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/package_verification.json",
|
||||
" M reports/package_verification.md",
|
||||
" M reports/registry_audit.json",
|
||||
" M reports/registry_audit.md",
|
||||
" M reports/security_trust_report.json",
|
||||
" M reports/security_trust_report.md",
|
||||
" M reports/upgrade_check.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,
|
||||
@@ -49,15 +37,14 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 11
|
||||
"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": [
|
||||
"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)"
|
||||
@@ -65,10 +52,10 @@
|
||||
"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": false,
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"ready": true,
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"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)",
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-14`
|
||||
Commit: `88cec0e51e828c289294bd50041409262e60a40f`
|
||||
Working tree dirty at generation: `true`
|
||||
Commit: `c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160`
|
||||
|
||||
## 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: `4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d4
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `11`
|
||||
- public claim blockers: `3`
|
||||
- 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.
|
||||
|
||||
@@ -35,15 +35,14 @@ 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) |
|
||||
|
||||
## 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
|
||||
|
||||
@@ -543,7 +543,7 @@
|
||||
|
||||
<section>
|
||||
<h2>核心指标</h2>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>3 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
@@ -673,8 +673,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>3</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+16
-29
@@ -1332,7 +1332,7 @@
|
||||
"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,
|
||||
@@ -1356,11 +1356,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 11
|
||||
"public_claim_blocker_count": 3,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"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.",
|
||||
@@ -4920,29 +4920,17 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-14",
|
||||
"skill_dir": ".",
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 11,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/package_verification.json",
|
||||
" M reports/package_verification.md",
|
||||
" M reports/registry_audit.json",
|
||||
" M reports/registry_audit.md",
|
||||
" M reports/security_trust_report.json",
|
||||
" M reports/security_trust_report.md",
|
||||
" M reports/upgrade_check.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,
|
||||
@@ -4966,15 +4954,14 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 11
|
||||
"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": [
|
||||
"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)"
|
||||
@@ -4982,10 +4969,10 @@
|
||||
"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": false,
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"ready": true,
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"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)",
|
||||
|
||||
@@ -919,7 +919,7 @@
|
||||
"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,
|
||||
@@ -943,11 +943,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 11
|
||||
"public_claim_blocker_count": 3,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"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.",
|
||||
|
||||
@@ -918,7 +918,7 @@
|
||||
"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,
|
||||
@@ -942,11 +942,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 11
|
||||
"public_claim_blocker_count": 3,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
|
||||
"commit": "c2f5672b2c9eb2e57fde9ce71feb8b89c4d65f4d",
|
||||
"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.",
|
||||
|
||||
Reference in New Issue
Block a user