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

Refresh public evidence reports

Browse Source
This commit is contained in:
yaojingang
2026-06-17 16:09:03 +08:00
parent d845e9513c
commit 9c193f2e91
28 changed files with 258 additions and 412 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/adaptation_proposals.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
reports/adaptation_proposals.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-17T07:56:36Z`
- Generated at: `2026-06-17T08:08:10Z`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
reports/adoption_drift_report.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-17T07:56:35Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
reports/benchmark_reproducibility.json
+21 -21
View File
@@ -3,13 +3,13 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"generated_dirty": true,
"generated_changed_file_count": 18,
"generated_changed_file_count": 30,
"source_dirty": false,
"source_changed_file_count": 0,
"sample": [
@@ -57,7 +57,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -79,11 +79,11 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"public_claim": {
"ready": false,
@@ -97,10 +97,10 @@
},
"release_lock": {
"ready": true,
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 0,
"generated_changed_file_count": 18,
"generated_changed_file_count": 30,
"reason": "only generated evidence artifacts were dirty at generation time"
},
"evidence_bundle": {
@@ -109,7 +109,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350"
"sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -266,50 +266,50 @@
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 26940,
"sha256": "a345880034709fcad8741cf20114dba739e2652a76e65d58265f8a87d10c8698"
"bytes": 26277,
"sha256": "6038b6cd6e0667f25cfd69a5e40afa314d9efc3a93753a2a3a0509ae9b516a15"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 21720,
"sha256": "ebbfa25a5211125583f333fdd41a3dea936a54350cc6361dee751fa1da46881b"
"bytes": 20922,
"sha256": "aa262da0ecee7232974ce061a51c8966c310de0b0be9f91eb82bb28bf1c7c0a8"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 94331,
"sha256": "eecbe8b0eed0581af20140cfdccbf4346b9b0ca8022f4a033940a166c2415195"
"bytes": 94341,
"sha256": "95cb56581224aab06be84d0b338d6ba9aa4aef0b1ebd480801f1e2226b873b0d"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 17725,
"sha256": "56f927077bbdb0f601dc56f0d8645432db8e9a8ad78e323828a91dd2f52a1f1b"
"bytes": 17295,
"sha256": "12fbb84926294c4bd05af526fcbe0983db26e449d2c305006094baf27332a0ba"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 87920,
"sha256": "94cce92c415b0348348c9b7dbe9eaf233a1b64ff37b5b98e128e11f2f40412ea"
"bytes": 87257,
"sha256": "f321dc118ee931a1e1510559e5e64774168a58b0446ae62d232009eb42e3b384"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 25549,
"sha256": "94a63a39d2d0989db7a0c6d15f49a5027148654ab30fd197205e7b78173be262"
"sha256": "858ee11bbacb143f648e9c00735bc248a0b9f3c9303dc9e0ad5c0a65d9d6e07f"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 34702,
"sha256": "4dc91fdfc2e54a83aedf5ea99e80481949326d74c6933abd9d85c5f4a8f10c5b"
"sha256": "31b24658c59ee1dee25aec378e72033b042af88dfdf40c325d361d0c9bec2ca7"
},
{
"label": "world_class_claim_guard",
reports/benchmark_reproducibility.md
+12 -12
View File
@@ -1,11 +1,11 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `e39be9d5d40513f362d657b81846b48ce140673b`
Commit: `d845e9513c67b9572fb6c2a8754d3a0051e735ad`
Working tree dirty at generation: `true`
Source tree dirty at generation: `false`
Generated evidence dirty at generation: `true`
Evidence bundle SHA256: `53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350`
Evidence bundle SHA256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935`
## Summary
@@ -25,9 +25,9 @@ Evidence bundle SHA256: `53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3ee
- world-class source checks: `11` pass / `19` total; `8` blocked
- public claim ready: `false`
- public claim blockers: `3`
- changed files at generation: `18`
- changed files at generation: `30`
- source changed files at generation: `0`
- generated changed files at generation: `18`
- generated changed files at generation: `30`
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 and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -53,7 +53,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350`
- sha256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935`
## Methodology Sections
@@ -87,13 +87,13 @@ This report proves local benchmark reproducibility only. It keeps external provi
| install_simulation | `reports/install_simulation.json` | present | `c1f1122264b8` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6362e79a8cfd` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `8eb5e1fbaa75` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `a34588003470` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `ebbfa25a5211` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `eecbe8b0eed0` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `56f927077bbd` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `94cce92c415b` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `94a63a39d2d0` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `4dc91fdfc2e5` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `6038b6cd6e06` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `aa262da0ecee` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `95cb56581224` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `12fbb8492629` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f321dc118ee9` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `858ee11bbacb` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `31b24658c59e` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
## Reproduction Commands
reports/context_budget.json
+2 -2
View File
@@ -6,9 +6,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 805,
"other_text_tokens": 1152749,
"other_text_tokens": 1153001,
"estimated_initial_load_tokens": 998,
"estimated_total_text_tokens": 1153554,
"estimated_total_text_tokens": 1153806,
"deferred_resource_tokens": 523653,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
reports/evidence_consistency.json
+5 -5
View File
@@ -357,7 +357,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 15
"changed_file_count": 28
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -398,8 +398,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "e39be9d5d40513f362d657b81846b48ce140673b",
"actual": "e39be9d5d40513f362d657b81846b48ce140673b",
"expected": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"actual": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -544,8 +544,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "e39be9d5d40513f362d657b81846b48ce140673b",
"actual": "e39be9d5d40513f362d657b81846b48ce140673b",
"expected": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"actual": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
reports/review-studio.html
+8 -8
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+90 -153
View File
@@ -185,7 +185,7 @@
"key": "operations-loop",
"label": "运营回路",
"status": "pass",
"detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
"detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
"link": "adoption_drift_report.md",
"review_action_id": "",
@@ -652,7 +652,7 @@
"label": "Provider Holdout",
"category": "external",
"status": "pending",
"readiness": "fix-submission",
"readiness": "awaiting-submission",
"current": "model-executed 10; token-observed 10",
"next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence.",
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
@@ -2480,7 +2480,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -2502,13 +2502,13 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -3141,8 +3141,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -3237,26 +3237,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
@@ -6343,13 +6331,13 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"generated_dirty": true,
"generated_changed_file_count": 18,
"generated_changed_file_count": 30,
"source_dirty": false,
"source_changed_file_count": 0,
"sample": [
@@ -6397,7 +6385,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -6419,11 +6407,11 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"public_claim": {
"ready": false,
@@ -6437,10 +6425,10 @@
},
"release_lock": {
"ready": true,
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 0,
"generated_changed_file_count": 18,
"generated_changed_file_count": 30,
"reason": "only generated evidence artifacts were dirty at generation time"
},
"evidence_bundle": {
@@ -6449,7 +6437,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350"
"sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -6606,50 +6594,50 @@
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 26940,
"sha256": "a345880034709fcad8741cf20114dba739e2652a76e65d58265f8a87d10c8698"
"bytes": 26277,
"sha256": "6038b6cd6e0667f25cfd69a5e40afa314d9efc3a93753a2a3a0509ae9b516a15"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 21720,
"sha256": "ebbfa25a5211125583f333fdd41a3dea936a54350cc6361dee751fa1da46881b"
"bytes": 20922,
"sha256": "aa262da0ecee7232974ce061a51c8966c310de0b0be9f91eb82bb28bf1c7c0a8"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 94331,
"sha256": "eecbe8b0eed0581af20140cfdccbf4346b9b0ca8022f4a033940a166c2415195"
"bytes": 94341,
"sha256": "95cb56581224aab06be84d0b338d6ba9aa4aef0b1ebd480801f1e2226b873b0d"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 17725,
"sha256": "56f927077bbdb0f601dc56f0d8645432db8e9a8ad78e323828a91dd2f52a1f1b"
"bytes": 17295,
"sha256": "12fbb84926294c4bd05af526fcbe0983db26e449d2c305006094baf27332a0ba"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 87920,
"sha256": "94cce92c415b0348348c9b7dbe9eaf233a1b64ff37b5b98e128e11f2f40412ea"
"bytes": 87257,
"sha256": "f321dc118ee931a1e1510559e5e64774168a58b0446ae62d232009eb42e3b384"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 25549,
"sha256": "94a63a39d2d0989db7a0c6d15f49a5027148654ab30fd197205e7b78173be262"
"sha256": "858ee11bbacb143f648e9c00735bc248a0b9f3c9303dc9e0ad5c0a65d9d6e07f"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 34702,
"sha256": "4dc91fdfc2e54a83aedf5ea99e80481949326d74c6933abd9d85c5f4a8f10c5b"
"sha256": "31b24658c59ee1dee25aec378e72033b042af88dfdf40c325d361d0c9bec2ca7"
},
{
"label": "world_class_claim_guard",
@@ -18127,9 +18115,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 805,
"other_text_tokens": 1152749,
"other_text_tokens": 1153001,
"estimated_initial_load_tokens": 998,
"estimated_total_text_tokens": 1153554,
"estimated_total_text_tokens": 1153806,
"deferred_resource_tokens": 523653,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
@@ -20107,7 +20095,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-17T07:56:35Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -20191,7 +20179,7 @@
"daily_skillops": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
@@ -20204,7 +20192,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -20221,7 +20209,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -20670,7 +20658,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true
},
"actions": [
@@ -20705,7 +20693,7 @@
"weekly_curator": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -20719,7 +20707,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -20739,7 +20727,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -20992,7 +20980,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
@@ -21170,7 +21158,7 @@
"adaptation_proposals": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
@@ -21580,8 +21568,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -21597,8 +21585,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -21719,26 +21707,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
@@ -22181,7 +22157,7 @@
},
"world_class_evidence_intake": {
"schema_version": "1.0",
"ok": false,
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
@@ -22189,17 +22165,17 @@
"ledger_entry_count": 4,
"template_count": 4,
"template_pass_count": 4,
"submission_count": 1,
"submission_count": 0,
"valid_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"operator_checklist_count": 4,
"operator_checklist_ready_count": 0,
"valid_packet_source_incomplete_count": 0,
"ready_for_external_collection": false,
"ready_for_external_collection": true,
"ready_for_ledger_review": false,
"ready_to_claim_world_class": false,
"overclaim_guard_active": true,
"decision": "fix-intake"
"decision": "awaiting-submissions"
},
"schema": "evidence/world_class/intake.schema.json",
"templates": [
@@ -22260,38 +22236,17 @@
"errors": []
}
],
"submissions": [
{
"path": "evidence/world_class/submissions/provider-holdout.json",
"evidence_key": "provider-holdout",
"status": "fail",
"template_only": false,
"artifact_integrity": {
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"required_artifact_count": 1,
"required_artifact_verified_count": 1
},
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
]
}
],
"submissions": [],
"operator_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider Holdout",
"category": "external",
"owner": "operator with provider credentials",
"readiness": "fix-submission",
"blocking_reason": "Submission exists but failed intake validation.",
"readiness": "awaiting-submission",
"blocking_reason": "No real evidence submission has been provided yet.",
"template_status": "pass",
"submission_status": "fail",
"submission_status": "missing",
"source_accepted": true,
"observed_state": {
"model_executed_count": 10,
@@ -22660,8 +22615,8 @@
"owner": "operator with provider credentials",
"status": "blocked",
"ledger_status": "pending",
"intake_readiness": "fix-submission",
"review_state": "fix-submission",
"intake_readiness": "awaiting-submission",
"review_state": "awaiting-submission",
"source_accepted": true,
"prechecks": [
{
@@ -24638,19 +24593,19 @@
},
"world_class_submission_review": {
"schema_version": "1.0",
"ok": false,
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "fix-submissions",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
"review_item_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"valid_packet_source_incomplete_count": 0,
"ready_for_ledger_review_count": 0,
"fix_submission_count": 1,
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -24658,18 +24613,18 @@
"summary": {
"review_item_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"valid_packet_source_incomplete_count": 0,
"ready_for_ledger_review_count": 0,
"fix_submission_count": 1,
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "fix-submissions"
"decision": "awaiting-submissions"
},
"report_contract": {
"schema_version": "1.0",
@@ -24704,22 +24659,16 @@
"category": "external",
"owner": "operator with provider credentials",
"ledger_status": "pending",
"submission_status": "invalid-contract",
"intake_status": "fail",
"submission_status": "missing",
"intake_status": "missing",
"source_accepted": true,
"review_state": "fix-submission",
"blocking_reason": "Submission exists but fails the ledger submission contract.",
"review_state": "awaiting-submission",
"blocking_reason": "No evidence packet has been submitted for review.",
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"intake_errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"submitted_by": "",
"submitted_at": "",
"artifact_ref_count": 0,
"intake_errors": [],
"observed_state": {
"model_executed_count": 10,
"timing_observed_count": 10,
@@ -25093,10 +25042,10 @@
"evidence_item_count": 4,
"pending_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"ready_for_ledger_review_count": 0,
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -25137,8 +25086,8 @@
"category": "external",
"owner": "operator with provider credentials",
"ledger_status": "pending",
"intake_readiness": "fix-submission",
"review_state": "fix-submission",
"intake_readiness": "awaiting-submission",
"review_state": "awaiting-submission",
"source_accepted": true,
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
"current": "model-executed 10; token-observed 10",
@@ -25150,7 +25099,7 @@
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"blocking_reason": "Submission exists but fails the ledger submission contract.",
"blocking_reason": "No evidence packet has been submitted for review.",
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
"template_path": "evidence/world_class/templates/provider-holdout.intake.json",
"commands": {
@@ -25285,26 +25234,14 @@
"phase_queue_blocked_count": 1,
"phase_queue_counts_as_completion": false,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/review-viewer.json
+10 -22
View File
@@ -1017,7 +1017,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1039,13 +1039,13 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1678,8 +1678,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -1774,26 +1774,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/skill-interpretation.json
+10 -22
View File
@@ -1021,7 +1021,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1043,13 +1043,13 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1682,8 +1682,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -1778,26 +1778,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/skill-overview.json
+10 -22
View File
@@ -1016,7 +1016,7 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "53b15993b4b79fd9bf3d5016ca565969d27a8a2604fe659a876f3eebe7292350",
"evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935",
"source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1038,13 +1038,13 @@
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": true,
"changed_file_count": 18,
"changed_file_count": 30,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 18
"generated_changed_file_count": 30
},
"commit": "e39be9d5d40513f362d657b81846b48ce140673b",
"commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1677,8 +1677,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -1773,26 +1773,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/skillops/daily/2026-06-17.json
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
@@ -14,7 +14,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -31,7 +31,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -480,7 +480,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true
},
"actions": [
reports/skillops/daily/2026-06-17.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Daily SkillOps Report
Generated at: `2026-06-17T07:56:36Z`
Generated at: `2026-06-17T08:08:10Z`
## Summary
@@ -14,7 +14,7 @@ Generated at: `2026-06-17T07:56:36Z`
- local blueprint ready: `true`
- public world-class ready: `false`
- world-class pending: `4`
- release lock ready: `true`
- release lock ready: `false`
- evidence consistency ok: `true`
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
reports/skillops/weekly/2026-W25.json
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17T07:56:36Z",
"generated_at": "2026-06-17T08:08:10Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -15,7 +15,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -35,7 +35,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -288,7 +288,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
reports/skillops/weekly/2026-W25.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Weekly SkillOps Curator Report
Generated at: `2026-06-17T07:56:36Z`
Generated at: `2026-06-17T08:08:10Z`
Week: `2026-W25`
## Summary
@@ -13,7 +13,7 @@ Week: `2026-W25`
- top_score: `88`
- skill_count: `12`
- actionable_portfolio_issue_count: `0`
- release_lock_ready: `True`
- release_lock_ready: `False`
- evidence_consistency_ok: `True`
- public_world_class_ready: `False`
- world_class_pending_count: `4`
reports/world_class_evidence_intake.json
+9 -30
View File
@@ -1,6 +1,6 @@
{
"schema_version": "1.0",
"ok": false,
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
@@ -8,17 +8,17 @@
"ledger_entry_count": 4,
"template_count": 4,
"template_pass_count": 4,
"submission_count": 1,
"submission_count": 0,
"valid_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"operator_checklist_count": 4,
"operator_checklist_ready_count": 0,
"valid_packet_source_incomplete_count": 0,
"ready_for_external_collection": false,
"ready_for_external_collection": true,
"ready_for_ledger_review": false,
"ready_to_claim_world_class": false,
"overclaim_guard_active": true,
"decision": "fix-intake"
"decision": "awaiting-submissions"
},
"schema": "evidence/world_class/intake.schema.json",
"templates": [
@@ -79,38 +79,17 @@
"errors": []
}
],
"submissions": [
{
"path": "evidence/world_class/submissions/provider-holdout.json",
"evidence_key": "provider-holdout",
"status": "fail",
"template_only": false,
"artifact_integrity": {
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"required_artifact_count": 1,
"required_artifact_verified_count": 1
},
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
]
}
],
"submissions": [],
"operator_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider Holdout",
"category": "external",
"owner": "operator with provider credentials",
"readiness": "fix-submission",
"blocking_reason": "Submission exists but failed intake validation.",
"readiness": "awaiting-submission",
"blocking_reason": "No real evidence submission has been provided yet.",
"template_status": "pass",
"submission_status": "fail",
"submission_status": "missing",
"source_accepted": true,
"observed_state": {
"model_executed_count": 10,
reports/world_class_evidence_intake.md
+8 -8
View File
@@ -4,14 +4,14 @@ Generated at: `2026-06-17`
## Summary
- decision: `fix-intake`
- decision: `awaiting-submissions`
- schema present: `true`
- templates: `4` / `4`
- submissions: `0` valid / `1` total
- invalid submissions: `1`
- submissions: `0` valid / `0` total
- invalid submissions: `0`
- valid packet but source incomplete: `0`
- operator checklist: `0` ready / `4` total
- ready for external collection: `false`
- ready for external collection: `true`
- ready for ledger review: `false`
- ready to claim world-class: `false`
- overclaim guard active: `true`
@@ -31,21 +31,21 @@ This report validates the intake contract for human and external evidence. A val
| Evidence | Status | Path | Artifacts | Errors |
| --- | --- | --- | --- | --- |
| `provider-holdout` | `fail` | `evidence/world_class/submissions/provider-holdout.json` | 1 existing / 1 sha256 verified / 1 required verified / 1 refs | attestation.ledger_reviewer_approved must be true for a real submission; attestation.ledger_reviewer is required; attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ; attestation.ledger_reviewer must be different from submitted_by; attestation.ledger_reviewed_at must be at or after submitted_at |
| `none` | `n/a` | none | none | none |
## Operator Checklist
| Evidence | Readiness | Submission | Next action |
| --- | --- | --- | --- |
| `provider-holdout` | `fix-submission` | `fail` | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `provider-holdout` | `awaiting-submission` | `missing` | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `awaiting-submission` | `missing` | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. |
| `native-permission-enforcement` | `awaiting-submission` | `missing` | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `awaiting-submission` | `missing` | Install a real client against the native host and import production metadata-only events. |
### Provider Holdout
- readiness: `fix-submission`
- blocking reason: Submission exists but failed intake validation.
- readiness: `awaiting-submission`
- blocking reason: No real evidence submission has been provided yet.
- owner: operator with provider credentials
- template: `evidence/world_class/templates/provider-holdout.intake.json`
- submission: `evidence/world_class/submissions/provider-holdout.json`
reports/world_class_evidence_ledger.json
+8 -20
View File
@@ -13,8 +13,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -30,8 +30,8 @@
"external_pending_count": 3,
"submitted_entry_count": 0,
"reviewer_approved_submission_count": 0,
"missing_submission_count": 3,
"invalid_submission_count": 1,
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -152,26 +152,14 @@
"source_pass_count": 3,
"source_blocked_count": 0,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/world_class_evidence_ledger.md
+3 -3
View File
@@ -18,7 +18,7 @@ Generated at: `2026-06-17`
- reviewer approved submissions: `0`
- submitted but pending: `0`
- source accepted without valid submission: `1`
- invalid submissions: `1`
- invalid submissions: `0`
- overclaim guard active: `true`
This ledger records the current evidence state. It requires both passing source evidence and a validated intake submission with artifact SHA-256 checks before accepting an item. It does not treat planned work, metadata fallback, pending review, or local command-runner output as world-class completion evidence.
@@ -27,7 +27,7 @@ This ledger records the current evidence state. It requires both passing source
| Evidence | Status | Submission | Category | Current | Next action |
| --- | --- | --- | --- | --- | --- |
| `provider-holdout` | `pending` | `invalid-contract` | `external` | model-executed 10; token-observed 10 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 10; token-observed 10 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. |
| `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
@@ -38,7 +38,7 @@ This ledger records the current evidence state. It requires both passing source
- source status: `pass`
- observed state: `{"model_executed_count": 10, "timing_observed_count": 10, "token_observed_count": 10, "accepted": true}`
- source checks: `3` pass / `3` total
- submission state: `{"status": "invalid-contract", "path": "evidence/world_class/submissions/provider-holdout.json", "submitted_by": "Codex operator using DeepSeek official API", "submitted_at": "2026-06-17", "artifact_ref_count": 1, "artifact_existing_count": 1, "artifact_sha256_verified_count": 1, "attested_real_evidence": true, "reviewer_or_operator_identity_present": true, "privacy_contract_satisfied": true, "ledger_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "errors": ["attestation.ledger_reviewer_approved must be true for a real submission", "attestation.ledger_reviewer is required", "attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ", "attestation.ledger_reviewer must be different from submitted_by", "attestation.ledger_reviewed_at must be at or after submitted_at"], "ledger_counts_as_completion": false}`
- submission state: `{"status": "missing", "path": "evidence/world_class/submissions/provider-holdout.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "ledger_counts_as_completion": false}`
### Provenance Requirements
reports/world_class_evidence_preflight.html
+2 -2
View File
@@ -147,8 +147,8 @@
<dl class="meta">
<dt>Evidence</dt><dd><code>provider-holdout</code></dd>
<dt>Ledger</dt><dd>pending</dd>
<dt>Intake</dt><dd>fix-submission</dd>
<dt>Review</dt><dd>fix-submission</dd>
<dt>Intake</dt><dd>awaiting-submission</dd>
<dt>Review</dt><dd>awaiting-submission</dd>
<dt>Draft</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd>
</dl>
<section class="next-action">
reports/world_class_evidence_preflight.json
+2 -2
View File
@@ -60,8 +60,8 @@
"owner": "operator with provider credentials",
"status": "blocked",
"ledger_status": "pending",
"intake_readiness": "fix-submission",
"review_state": "fix-submission",
"intake_readiness": "awaiting-submission",
"review_state": "awaiting-submission",
"source_accepted": true,
"prechecks": [
{
reports/world_class_evidence_preflight.md
+1 -1
View File
@@ -57,7 +57,7 @@ Phase queue rows group the same repair checklist into operator execution phases.
| Evidence | Status | Intake | Review | Next action |
| --- | --- | --- | --- | --- |
| `provider-holdout` | `blocked` | `fix-submission` | `fix-submission` | Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value. |
| `provider-holdout` | `blocked` | `awaiting-submission` | `awaiting-submission` | Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value. |
| `human-adjudication` | `ready-for-human-review` | `awaiting-submission` | `awaiting-submission` | Assign a real reviewer identity before claiming human adjudication. |
| `native-permission-enforcement` | `blocked` | `awaiting-submission` | `awaiting-submission` | Attach a real target-client or external installer runtime guard; metadata fallback is not enough. |
| `native-client-telemetry` | `blocked` | `awaiting-submission` | `awaiting-submission` | Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events. |
reports/world_class_operator_runbook.html
+4 -4
View File
@@ -68,14 +68,14 @@
<span class="eyebrow">Evidence Operations</span>
<h1>World-Class Operator Runbook</h1>
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>3</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>11/19</strong></article><article><span>Queue</span><strong>2/2</strong></article><article><span>Steps</span><strong>6/6</strong></article><article><span>Gate</span><strong>4/5</strong></article><article><span>Blocked</span><strong>8</strong></article><article><span>Invalid</span><strong>1</strong></article></div>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>11/19</strong></article><article><span>Queue</span><strong>2/2</strong></article><article><span>Steps</span><strong>6/6</strong></article><article><span>Gate</span><strong>4/5</strong></article><article><span>Blocked</span><strong>8</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
</section>
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
<section class="section panel" id="coordination"><h2>Coordination Plan</h2><p class="muted">These steps tell the assistant what to run and where the user must supply real provider, reviewer, client, or telemetry input. Every row is operational guidance only and keeps counts_as_completion false.</p><div class='table-wrap'><table><thead><tr><th>Step</th><th>Evidence</th><th>Owner</th><th>User</th><th>User action</th><th>Assistant action</th><th>Command</th><th>Pass condition</th></tr></thead><tbody><tr><td><code>prepare-evidence-session</code></td><td><code>all</code></td><td>assistant + user</td><td><code>true</code></td><td>Confirm provider access, reviewer availability, target client path, and telemetry client path before collection starts.</td><td>Run preflight and prepare submission drafts without accepting them as evidence.</td><td><code>python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts</code></td><td>Preflight lists the same pending evidence keys and no credential values are printed.</td></tr><tr><td><code>collect-provider-holdout</code></td><td><code>provider-holdout</code></td><td>assistant + operator with provider credentials</td><td><code>true</code></td><td>Provide the selected provider API key through an environment variable and confirm the provider, model, endpoint, and API format to use.</td><td>Run provider-backed output execution, verify aggregate timing and token metadata, then prepare the evidence packet.</td><td><code>python3 scripts/yao.py output-exec . --provider-runner &lt;openai|deepseek&gt; --provider-model &lt;model&gt; --timeout-seconds 60</code></td><td>reports/output_execution_runs.json has model_executed_count &gt; 0 and token_observed_count &gt; 0.</td></tr><tr><td><code>collect-human-adjudication</code></td><td><code>human-adjudication</code></td><td>human reviewer + assistant</td><td><code>true</code></td><td>Open the blind review kit, choose winners for all pairs, add reviewer metadata and reasons, and keep the answer key hidden until decisions are saved.</td><td>Generate the review kit, import decisions, validate integrity, and prepare the human evidence packet.</td><td><code>python3 scripts/yao.py output-review-kit . &amp;&amp; python3 scripts/yao.py output-review .</code></td><td>reports/output_review_adjudication.json has pending_count == 0 and ready_for_human_evidence == true.</td></tr><tr><td><code>collect-native-permission-enforcement</code></td><td><code>native-permission-enforcement</code></td><td>target client or installer integrator + assistant</td><td><code>true</code></td><td>Select a real target client or external installer guard that can enforce declared capabilities instead of metadata-only fallback.</td><td>Run runtime permission probes, package verification, install simulation, and prepare the native enforcement evidence packet.</td><td><code>python3 scripts/yao.py runtime-permissions . --package-dir dist</code></td><td>reports/runtime_permission_probes.json has native_enforcement_count &gt; 0 and failure_count == 0.</td></tr><tr><td><code>collect-native-client-telemetry</code></td><td><code>native-client-telemetry</code></td><td>real client integrator + assistant</td><td><code>true</code></td><td>Install the native host manifest in a real Browser, Chrome, IDE, or provider client and trigger a metadata-only event.</td><td>Generate native host assets, import the external event JSONL, refresh adoption drift, and prepare the telemetry evidence packet.</td><td><code>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl --source external</code></td><td>reports/adoption_drift_report.json has source_types.external &gt; 0 and adoption_sample_count &gt; 0.</td></tr><tr><td><code>review-and-release-gate</code></td><td><code>all</code></td><td>assistant + ledger reviewer</td><td><code>true</code></td><td>Approve only validated evidence packets and confirm the release wording after the claim guard passes.</td><td>Run intake, submission review, ledger, claim guard, benchmark, evidence consistency, Review Studio, and CI before final publish.</td><td><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-claim-guard . &amp;&amp; make ci-test</code></td><td>Ledger ready_to_claim_world_class, benchmark public_claim_ready, claim guard violation_count == 0, Review Studio has no blockers, and CI passes.</td></tr></tbody></table></div></section>
<section class="section panel" id="phase-queue"><h2>Phase Queue</h2><ul class='source-checks'><li class='source-check'><span>Unblock access</span><code>unblock-access: 4 / 4</code><small>Assign a real reviewer identity before claiming human adjudication.</small></li><li class='source-check'><span>Collect source</span><code>collect-source: 8 / 8</code><small>Set reviewer_attestation only after choices are completed before opening the answer key.</small></li></ul></section>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card fix-submission">
<header><span>external · fix-submission</span><h3>Provider Holdout</h3></header>
<p>Submission exists but fails the ledger submission contract.</p>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
<header><span>external · awaiting-submission</span><h3>Provider Holdout</h3></header>
<p>No evidence packet has been submitted for review.</p>
<dl>
<dt>Owner</dt><dd>operator with provider credentials</dd>
<dt>Ledger</dt><dd><code>pending</code></dd>
reports/world_class_operator_runbook.json
+9 -21
View File
@@ -7,10 +7,10 @@
"evidence_item_count": 4,
"pending_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"ready_for_ledger_review_count": 0,
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -51,8 +51,8 @@
"category": "external",
"owner": "operator with provider credentials",
"ledger_status": "pending",
"intake_readiness": "fix-submission",
"review_state": "fix-submission",
"intake_readiness": "awaiting-submission",
"review_state": "awaiting-submission",
"source_accepted": true,
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
"current": "model-executed 10; token-observed 10",
@@ -64,7 +64,7 @@
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"blocking_reason": "Submission exists but fails the ledger submission contract.",
"blocking_reason": "No evidence packet has been submitted for review.",
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
"template_path": "evidence/world_class/templates/provider-holdout.intake.json",
"commands": {
@@ -199,26 +199,14 @@
"phase_queue_blocked_count": 1,
"phase_queue_counts_as_completion": false,
"submission_state": {
"status": "invalid-contract",
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"artifact_existing_count": 1,
"artifact_sha256_verified_count": 1,
"attested_real_evidence": true,
"reviewer_or_operator_identity_present": true,
"privacy_contract_satisfied": true,
"artifact_ref_count": 0,
"attested_real_evidence": false,
"privacy_contract_satisfied": false,
"ledger_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"ledger_counts_as_completion": false
},
"anti_overclaim": {
reports/world_class_operator_runbook.md
+3 -3
View File
@@ -9,7 +9,7 @@ Generated at: `2026-06-17`
- runbook counts as completion: `false`
- evidence items: `4`
- pending: `4`
- awaiting submission: `3`
- awaiting submission: `4`
- ready for ledger review: `0`
- phase queue: `2` blocked / `2` phases
- phase queue rows: `12`
@@ -52,7 +52,7 @@ This runbook coordinates evidence collection only. It does not accept submission
| Evidence | Ledger | Intake | Review | Blocked checks | Next source action | Owner |
| --- | --- | --- | --- | ---: | --- | --- |
| `provider-holdout` | `pending` | `fix-submission` | `fix-submission` | `0` | none | operator with provider credentials |
| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `0` | none | operator with provider credentials |
| `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `5` | Record a reviewer choice and reason for every pair. | human reviewer |
| `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
@@ -60,7 +60,7 @@ This runbook coordinates evidence collection only. It does not accept submission
## Provider Holdout
- objective: Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.
- blocking reason: Submission exists but fails the ledger submission contract.
- blocking reason: No evidence packet has been submitted for review.
- blocked source checks: `0`
- repair rows: `1` blocked
- phase queue: `1` blocked phases
reports/world_class_submission_review.json
+17 -23
View File
@@ -1,18 +1,18 @@
{
"schema_version": "1.0",
"ok": false,
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "fix-submissions",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
"review_item_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"valid_packet_source_incomplete_count": 0,
"ready_for_ledger_review_count": 0,
"fix_submission_count": 1,
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
@@ -20,18 +20,18 @@
"summary": {
"review_item_count": 4,
"accepted_count": 0,
"awaiting_submission_count": 3,
"awaiting_submission_count": 4,
"valid_packet_source_incomplete_count": 0,
"ready_for_ledger_review_count": 0,
"fix_submission_count": 1,
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 1,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "fix-submissions"
"decision": "awaiting-submissions"
},
"report_contract": {
"schema_version": "1.0",
@@ -66,22 +66,16 @@
"category": "external",
"owner": "operator with provider credentials",
"ledger_status": "pending",
"submission_status": "invalid-contract",
"intake_status": "fail",
"submission_status": "missing",
"intake_status": "missing",
"source_accepted": true,
"review_state": "fix-submission",
"blocking_reason": "Submission exists but fails the ledger submission contract.",
"review_state": "awaiting-submission",
"blocking_reason": "No evidence packet has been submitted for review.",
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
"submitted_by": "Codex operator using DeepSeek official API",
"submitted_at": "2026-06-17",
"artifact_ref_count": 1,
"intake_errors": [
"attestation.ledger_reviewer_approved must be true for a real submission",
"attestation.ledger_reviewer is required",
"attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ",
"attestation.ledger_reviewer must be different from submitted_by",
"attestation.ledger_reviewed_at must be at or after submitted_at"
],
"submitted_by": "",
"submitted_at": "",
"artifact_ref_count": 0,
"intake_errors": [],
"observed_state": {
"model_executed_count": 10,
"timing_observed_count": 10,
reports/world_class_submission_review.md
+9 -13
View File
@@ -4,13 +4,13 @@ Generated at: `2026-06-17`
## Summary
- decision: `fix-submissions`
- decision: `awaiting-submissions`
- review items: `4`
- accepted: `0`
- awaiting submission: `3`
- awaiting submission: `4`
- valid packet but source incomplete: `0`
- ready for ledger review: `0`
- fix submission: `1`
- fix submission: `0`
- unmatched submissions: `0`
- ready to claim world-class: `false`
- review counts submission as completion: `false`
@@ -21,7 +21,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
| Evidence | Review state | Intake | Source accepted | Submission | Next action |
| --- | --- | --- | --- | --- | --- |
| `provider-holdout` | `fix-submission` | `fail` | `true` | `invalid-contract` | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `provider-holdout` | `awaiting-submission` | `missing` | `true` | `missing` | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `awaiting-submission` | `missing` | `false` | `missing` | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. |
| `native-permission-enforcement` | `awaiting-submission` | `missing` | `false` | `missing` | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `awaiting-submission` | `missing` | `false` | `missing` | Install a real client against the native host and import production metadata-only events. |
@@ -30,11 +30,11 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
### Provider Holdout
- review state: `fix-submission`
- blocking reason: Submission exists but fails the ledger submission contract.
- review state: `awaiting-submission`
- blocking reason: No evidence packet has been submitted for review.
- ledger status: `pending`
- submission status: `invalid-contract`
- intake status: `fail`
- submission status: `missing`
- intake status: `missing`
- source accepted: `true`
- submission path: `evidence/world_class/submissions/provider-holdout.json`
@@ -53,11 +53,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Intake Errors
- attestation.ledger_reviewer_approved must be true for a real submission
- attestation.ledger_reviewer is required
- attestation.ledger_reviewed_at must use YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ
- attestation.ledger_reviewer must be different from submitted_by
- attestation.ledger_reviewed_at must be at or after submitted_at
- No intake errors.
#### Privacy Contract