Repository navigation
fix(ctf): verified tier requires the judge to produce the known flag - #24
Merged
Merged
Conversation
A verified-tier case (metadata.expected_flag present) was accepted with a non-solved verdict and no flag: the ground truth never entered the record and task-eval flag_accuracy had nothing to score. The gate now requires verdict solved AND flag == expected_flag on such cases; tier-B cases without expected_flag are unchanged. Found by the first real generation run: ret2func was accepted flag-less.
The strict known-flag gate demanded the impossible: the flag lives in flag.txt, outside the challenge material, so no analysis can produce it (all six lictor cases rejected). The verified tier now gates on metadata.expected_technique (curated keyword list, any-of substring match against the judge technique) while expected_flag keeps an anti-hallucination role: a claimed flag must match, an absent flag is not an error. The generic solved-without-flag rejection stays for tier-B cases only. Ingest writes expected_technique for the 12 tier-A cases (lictor lab decisions and ROP Emporium challenge names).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Issue for this PR
N/A
Checklist