From c1505fa6f156cf07ad09d9ddf5ea1c0ae57678d7 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Mon, 15 Jun 2026 22:09:48 +0800 Subject: [PATCH] Refresh clean portability evidence --- reports/benchmark_reproducibility.json | 36 ++----- reports/benchmark_reproducibility.md | 15 ++- reports/evidence_consistency.json | 134 ++++++++++++------------- reports/skill-interpretation.json | 10 +- reports/skill-overview.json | 10 +- 5 files changed, 94 insertions(+), 111 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index ee42e40..2b66fff 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,30 +3,17 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "84b761abce9f0a361ddea7d446d0454666de0885", + "commit": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 47, - "sample": [ - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " 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" - ], + "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, @@ -50,15 +37,14 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 47 + "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": "84b761abce9f0a361ddea7d446d0454666de0885", + "ready": true, + "commit": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "status_scope": "generation-time status before this report is written", - "reason": "working tree was dirty at generation time" + "reason": "clean generation-time HEAD" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 395d485..f84225f 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,14 +1,14 @@ # Benchmark Reproducibility Generated at: `2026-06-15` -Commit: `84b761abce9f0a361ddea7d446d0454666de0885` -Working tree dirty at generation: `true` +Commit: `ad40ed8693324c51dec88d3b1f60d804f18b0462` +Working tree dirty at generation: `false` Evidence bundle SHA256: `27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4` ## 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: `27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b1 - world-class ready: `false` - world-class source checks: `7` pass / `13` total; `6` blocked - public claim ready: `false` -- public claim blockers: `5` -- changed files at generation: `47` +- 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) | @@ -43,8 +42,8 @@ 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 diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 3fa99dc..c8ab8fc 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -37,8 +37,8 @@ "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" ], @@ -48,8 +48,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "84b761abce9f0a361ddea7d446d0454666de0885", - "actual": "84b761abce9f0a361ddea7d446d0454666de0885", + "expected": "ad40ed8693324c51dec88d3b1f60d804f18b0462", + "actual": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -61,30 +61,30 @@ "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": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "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": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -98,13 +98,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -112,13 +112,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -141,8 +141,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -153,8 +153,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -174,7 +174,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 6 + "source_pass_count": 7 }, "actual": { "ready": false, @@ -182,7 +182,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 6 + "source_pass_count": 7 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -194,8 +194,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "84b761abce9f0a361ddea7d446d0454666de0885", - "actual": "84b761abce9f0a361ddea7d446d0454666de0885", + "expected": "ad40ed8693324c51dec88d3b1f60d804f18b0462", + "actual": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -207,30 +207,30 @@ "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": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "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": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -244,13 +244,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -258,13 +258,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -287,8 +287,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -299,8 +299,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -320,7 +320,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 6 + "source_pass_count": 7 }, "actual": { "ready": false, @@ -328,7 +328,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 6 + "source_pass_count": 7 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -1127,7 +1127,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 6, + "source_pass_count": 7, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1186,8 +1186,7 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events", - "Adoption sample" + "External events" ] } ] @@ -1201,7 +1200,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 6, + "source_pass_count": 7, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1260,8 +1259,7 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events", - "Adoption sample" + "External events" ] } ] @@ -1611,15 +1609,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "public_claim_ready": false }, "paths": [ diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 3cb4bda..1bebca0 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -999,7 +999,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -1023,11 +1023,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 47 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "84b761abce9f0a361ddea7d446d0454666de0885", + "commit": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 1a1a0bd..b5a5e7f 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -994,7 +994,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -1018,11 +1018,11 @@ "world_class_source_pass_count": 7, "world_class_source_blocked_count": 6, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 47 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "84b761abce9f0a361ddea7d446d0454666de0885", + "commit": "ad40ed8693324c51dec88d3b1f60d804f18b0462", "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.",