From a80da65f8c56af7485cf9ee325d9e14966a8e1f6 Mon Sep 17 00:00:00 2001
From: yaojingang <kingboke@gmail.com>
Date: Tue, 16 Jun 2026 04:31:25 +0800
Subject: [PATCH] Lock benchmark evidence

---
 reports/benchmark_reproducibility.json | 25 +++++++++++--------------
 reports/benchmark_reproducibility.md   | 15 +++++++--------
 2 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index 7c45a7e..b45d4bb 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,19 +3,17 @@
   "ok": true,
   "generated_at": "2026-06-16",
   "skill_dir": ".",
-  "commit": "cd4c8036a978ae90e57ba303ddcdb2059acd8389",
+  "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82",
   "git_status": {
     "available": true,
-    "dirty": true,
-    "changed_file_count": 1,
-    "sample": [
-      " M reports/context_budget.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": 25,
     "missing_artifact_count": 0,
@@ -39,15 +37,14 @@
     "world_class_source_pass_count": 6,
     "world_class_source_blocked_count": 7,
     "public_claim_ready": false,
-    "public_claim_blocker_count": 5,
-    "working_tree_dirty": true,
-    "changed_file_count": 1
+    "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)",
@@ -56,10 +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": "cd4c8036a978ae90e57ba303ddcdb2059acd8389",
+    "ready": true,
+    "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82",
     "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 5050877..09edb1c 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,14 +1,14 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-06-16`
-Commit: `cd4c8036a978ae90e57ba303ddcdb2059acd8389`
-Working tree dirty at generation: `true`
+Commit: `5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82`
+Working tree dirty at generation: `false`
 Evidence bundle SHA256: `4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd`
 
 ## Summary
 
 - reproducibility ready: `true`
-- release lock ready: `false`
+- release lock ready: `true`
 - methodology complete: `true`
 - required artifacts: `25`
 - missing artifacts: `0`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa
 - world-class ready: `false`
 - world-class source checks: `6` pass / `13` total; `7` blocked
 - public claim ready: `false`
-- public claim blockers: `5`
-- changed files at generation: `1`
+- 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