vance/codex-mmo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

😏

Browse Source
This commit is contained in:
vance
2026-08-24 08:11:59 -07:00
commit 53df0eed10
275 changed files with 133056 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
evals/debugging-confidence/README.md
+3
View File
@@ -0,0 +1,3 @@
# Debugging confidence evaluation
Designed for `high-confidence-debugging`. The fixture contains a state-dependent cache bug and a misleading obvious hypothesis. Success requires a failing reproduction, a minimal fix, regression tests, and explicit acceptance or rejection of verifier results.