Refresh complete release evidence lock
This commit is contained in:
yaojingang
@@ -3,34 +3,21 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 22,
|
||||
"sample": [
|
||||
" M AGENTS.md",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/evidence_consistency.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/review-studio.html"
|
||||
],
|
||||
"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,
|
||||
"evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"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": 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)",
|
||||
@@ -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": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"ready": true,
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a"
|
||||
"sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -194,7 +180,7 @@
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 23022,
|
||||
"sha256": "e53158aa045e19f51cbf61f4cb8b299c9ac2babeaacd5441ecb911eb99d8089d"
|
||||
"sha256": "c3a04d0b6b58425bc6446cd882413136b4c22916a0e345861443308d3724a5cc"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-16`
|
||||
Commit: `bc999b9508da329c8ce09f98cffa6f02aae5bb2b`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a`
|
||||
Commit: `ef36a74204623da7210e0bef56995e5a726224a3`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41`
|
||||
|
||||
## 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: `60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc6
|
||||
- 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: `22`
|
||||
- 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: `24` / `24`
|
||||
- sha256: `60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a`
|
||||
- sha256: `7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -79,7 +78,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `a3a6d4e6809e` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `e53158aa045e` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `c3a04d0b6b58` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `5d720a3d1a51` |
|
||||
| package_verification | `reports/package_verification.json` | present | `cd65875d5b97` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `3e27a6f7678e` |
|
||||
|
||||
@@ -47,8 +47,8 @@
|
||||
"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"
|
||||
],
|
||||
@@ -58,8 +58,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"actual": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"expected": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"actual": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -71,30 +71,30 @@
|
||||
"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": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"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": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"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",
|
||||
@@ -204,8 +204,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"actual": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"expected": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"actual": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -217,30 +217,30 @@
|
||||
"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": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"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": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"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",
|
||||
|
||||
@@ -676,7 +676,7 @@
|
||||
|
||||
<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>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; 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>111 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>177 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 8 watchlist; 64 CLI handlers; 18 in entrypoint</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>173 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>618 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>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; 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>111 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>177 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 8 watchlist; 64 CLI handlers; 18 in entrypoint</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>173 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>618 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>
|
||||
@@ -806,8 +806,8 @@
|
||||
</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>5</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><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</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>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>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><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+27
-31
@@ -1676,13 +1676,13 @@
|
||||
"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,
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -1700,11 +1700,11 @@
|
||||
"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": 2
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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.",
|
||||
@@ -5299,26 +5299,23 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 2,
|
||||
"sample": [
|
||||
" M AGENTS.md",
|
||||
" M tests/verify_evidence_consistency.py"
|
||||
],
|
||||
"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,
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -5336,15 +5333,14 @@
|
||||
"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": 2
|
||||
"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)",
|
||||
@@ -5353,10 +5349,10 @@
|
||||
"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": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"ready": true,
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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)",
|
||||
@@ -5364,7 +5360,7 @@
|
||||
"existing_count": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8"
|
||||
"sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -5437,8 +5433,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7967,
|
||||
"sha256": "56430f01ba194dc6dc793eb505f92fec7a8c46e1be4b71976a3d641c9b98c7ec"
|
||||
"bytes": 7966,
|
||||
"sha256": "bdec10142028387b48df78668ee9b2d51a83f6582f82640ad74751c51f7866c5"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -5480,21 +5476,21 @@
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 23022,
|
||||
"sha256": "e53158aa045e19f51cbf61f4cb8b299c9ac2babeaacd5441ecb911eb99d8089d"
|
||||
"sha256": "c3a04d0b6b58425bc6446cd882413136b4c22916a0e345861443308d3724a5cc"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "d6b523cc5cbb2d69c35989913e7e68dd4dc2bb04d3bcff88bbcb56fbe8be5084"
|
||||
"sha256": "5d720a3d1a51c6ba512aa9504fb215b157b5e3132abc416e893aa2cda30b8a4c"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "ae8ac3872be3299b3d2dc18a29128346a3ecbb579987b1b08156e305237b5119"
|
||||
"sha256": "cd65875d5b972e75a36d96c13f8f9ff7681c4a0f769add4d7802c609da73f08d"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
@@ -14156,7 +14152,7 @@
|
||||
"python_compatibility": {
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"generated_at": "2026-06-13",
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
|
||||
@@ -996,13 +996,13 @@
|
||||
"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,
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -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": 2
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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.",
|
||||
|
||||
@@ -1000,11 +1000,11 @@
|
||||
"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,
|
||||
"evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"output_case_count": 5,
|
||||
@@ -1024,11 +1024,11 @@
|
||||
"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": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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.",
|
||||
|
||||
@@ -995,11 +995,11 @@
|
||||
"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,
|
||||
"evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a",
|
||||
"evidence_bundle_sha256": "7c1743a74403aa2571ba9aec85f3ae0ca6e50bd2e125dde70e22c6d9f82b0f41",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9",
|
||||
"output_case_count": 5,
|
||||
@@ -1019,11 +1019,11 @@
|
||||
"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": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b",
|
||||
"commit": "ef36a74204623da7210e0bef56995e5a726224a3",
|
||||
"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