frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Refresh clean archive identity evidence

Browse Source
This commit is contained in:
yaojingang
2026-06-15 22:16:15 +08:00
parent 27a5c12008
commit 6e2dfd48d0
5 changed files with 42 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/benchmark_reproducibility.json
+11 -25
View File
@@ -3,30 +3,17 @@
"ok": true, "ok": true,
"generated_at": "2026-06-15", "generated_at": "2026-06-15",
"skill_dir": ".", "skill_dir": ".",
"commit": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "commit": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"git_status": { "git_status": {
"available": true, "available": true,
"dirty": true, "dirty": false,
"changed_file_count": 38, "changed_file_count": 0,
"sample": [ "sample": [],
" M reports/adoption_drift_report.json",
" M reports/adoption_drift_report.md",
" 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",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md"
],
"scope": "generation-time status before this report is written" "scope": "generation-time status before this report is written"
}, },
"summary": { "summary": {
"reproducibility_ready": true, "reproducibility_ready": true,
"release_lock_ready": false, "release_lock_ready": true,
"methodology_complete": true, "methodology_complete": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
@@ -50,15 +37,14 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5, "public_claim_blocker_count": 4,
"working_tree_dirty": true, "working_tree_dirty": false,
"changed_file_count": 38 "changed_file_count": 0
}, },
"public_claim": { "public_claim": {
"ready": false, "ready": false,
"scope": "public benchmark or world-class readiness claim", "scope": "public benchmark or world-class readiness claim",
"blockers": [ "blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete", "provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete", "human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", "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." "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": { "release_lock": {
"ready": false, "ready": true,
"commit": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "commit": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"status_scope": "generation-time status before this report is written", "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": { "evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)", "algorithm": "sha256(path,label,exists,artifact_sha256)",
reports/benchmark_reproducibility.md
+7 -8
View File
@@ -1,14 +1,14 @@
# Benchmark Reproducibility # Benchmark Reproducibility
Generated at: `2026-06-15` Generated at: `2026-06-15`
Commit: `db1b24cbda5eb00f71b35846dff0f178625aa31d` Commit: `27a5c120081fe8f2518de60c6a2278f41762e9b6`
Working tree dirty at generation: `true` Working tree dirty at generation: `false`
Evidence bundle SHA256: `0d1c762a722d1bbc83339a0365efcfcdf027849fc83c7079da92a524b905f5ab` Evidence bundle SHA256: `0d1c762a722d1bbc83339a0365efcfcdf027849fc83c7079da92a524b905f5ab`
## Summary ## Summary
- reproducibility ready: `true` - reproducibility ready: `true`
- release lock ready: `false` - release lock ready: `true`
- methodology complete: `true` - methodology complete: `true`
- required artifacts: `24` - required artifacts: `24`
- missing artifacts: `0` - missing artifacts: `0`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `0d1c762a722d1bbc83339a0365efcfcdf027849fc83c7079da92a52
- world-class ready: `false` - world-class ready: `false`
- world-class source checks: `6` pass / `13` total; `7` blocked - world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false` - public claim ready: `false`
- public claim blockers: `5` - public claim blockers: `4`
- changed files at generation: `38` - 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. 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 | | Blocker |
| --- | | --- |
| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete | | provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete | | human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | | 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 ## Release Lock
- ready: `false` - ready: `true`
- reason: working tree was dirty at generation time - reason: clean generation-time HEAD
- status scope: generation-time status before this report is written - status scope: generation-time status before this report is written
## Evidence Bundle ## Evidence Bundle
reports/evidence_consistency.json
+14 -14
View File
@@ -37,8 +37,8 @@
"key": "benchmark-release-lock-self-consistency", "key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches git dirty state", "label": "Benchmark release lock matches git dirty state",
"status": "pass", "status": "pass",
"expected": false, "expected": true,
"actual": false, "actual": true,
"paths": [ "paths": [
"reports/benchmark_reproducibility.json" "reports/benchmark_reproducibility.json"
], ],
@@ -48,8 +48,8 @@
"key": "overview-benchmark-commit", "key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit", "label": "overview embeds the benchmark commit",
"status": "pass", "status": "pass",
"expected": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "expected": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"actual": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "actual": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"paths": [ "paths": [
"reports/benchmark_reproducibility.json", "reports/benchmark_reproducibility.json",
"reports/skill-overview.json" "reports/skill-overview.json"
@@ -61,7 +61,7 @@
"label": "overview embeds benchmark summary fields", "label": "overview embeds benchmark summary fields",
"status": "pass", "status": "pass",
"expected": { "expected": {
"release_lock_ready": false, "release_lock_ready": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
@@ -71,10 +71,10 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5 "public_claim_blocker_count": 4
}, },
"actual": { "actual": {
"release_lock_ready": false, "release_lock_ready": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
@@ -84,7 +84,7 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5 "public_claim_blocker_count": 4
}, },
"paths": [ "paths": [
"reports/benchmark_reproducibility.json", "reports/benchmark_reproducibility.json",
@@ -194,8 +194,8 @@
"key": "interpretation-benchmark-commit", "key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit", "label": "interpretation embeds the benchmark commit",
"status": "pass", "status": "pass",
"expected": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "expected": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"actual": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "actual": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"paths": [ "paths": [
"reports/benchmark_reproducibility.json", "reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json" "reports/skill-interpretation.json"
@@ -207,7 +207,7 @@
"label": "interpretation embeds benchmark summary fields", "label": "interpretation embeds benchmark summary fields",
"status": "pass", "status": "pass",
"expected": { "expected": {
"release_lock_ready": false, "release_lock_ready": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
@@ -217,10 +217,10 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5 "public_claim_blocker_count": 4
}, },
"actual": { "actual": {
"release_lock_ready": false, "release_lock_ready": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
@@ -230,7 +230,7 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5 "public_claim_blocker_count": 4
}, },
"paths": [ "paths": [
"reports/benchmark_reproducibility.json", "reports/benchmark_reproducibility.json",
reports/skill-interpretation.json
+5 -5
View File
@@ -1000,7 +1000,7 @@
"ok": true, "ok": true,
"summary": { "summary": {
"reproducibility_ready": true, "reproducibility_ready": true,
"release_lock_ready": false, "release_lock_ready": true,
"methodology_complete": true, "methodology_complete": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
@@ -1024,11 +1024,11 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5, "public_claim_blocker_count": 4,
"working_tree_dirty": true, "working_tree_dirty": false,
"changed_file_count": 38 "changed_file_count": 0
}, },
"commit": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "commit": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"missing_artifacts": [], "missing_artifacts": [],
"limitations": [ "limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
reports/skill-overview.json
+5 -5
View File
@@ -995,7 +995,7 @@
"ok": true, "ok": true,
"summary": { "summary": {
"reproducibility_ready": true, "reproducibility_ready": true,
"release_lock_ready": false, "release_lock_ready": true,
"methodology_complete": true, "methodology_complete": true,
"required_artifact_count": 24, "required_artifact_count": 24,
"missing_artifact_count": 0, "missing_artifact_count": 0,
@@ -1019,11 +1019,11 @@
"world_class_source_pass_count": 6, "world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7, "world_class_source_blocked_count": 7,
"public_claim_ready": false, "public_claim_ready": false,
"public_claim_blocker_count": 5, "public_claim_blocker_count": 4,
"working_tree_dirty": true, "working_tree_dirty": false,
"changed_file_count": 38 "changed_file_count": 0
}, },
"commit": "db1b24cbda5eb00f71b35846dff0f178625aa31d", "commit": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
"missing_artifacts": [], "missing_artifacts": [],
"limitations": [ "limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",