Add threshold sweep tool for perturbation scoring#90
Draft
dangng2004 wants to merge 1 commit into
Draft
Conversation
threshold_sweep.py recomputes recall at a range of fuzzy-coverage thresholds by reusing already-completed reviewer outputs and an on-disk cache of LLM-judge decisions (which are threshold-independent). One judgment per (perturbation, comment) pair; sweeping is then a pure re-aggregation. Pairs with the --threshold / --substring-gate flags added in PR #87 to support picking an operating point from data rather than guessing.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
threshold_sweep.pyrecomputes detection recall at a range of fuzzy-coverage thresholds by reusing already-completed reviewer outputs--threshold/--substring-gateflags added in PR Fix substring-match scorer bug; add gate/threshold flags #87 so the operating point can be chosen from data rather than guessedTest plan
results/<run>/<reviewer-model>/tree and confirm it produces a CSV of recall-by-threshold🤖 Generated with Claude Code