fix(scoring): treat unary en/em dashes as minus signs - #475
Open
marktech0813 wants to merge 1 commit into
Open
Conversation
Models emit U+2013/U+2014 as minus; the extractor only accepted ASCII '-', so "–3" graded as unsigned 3. Fold only in unary position so year ranges stay intact (James-CUDA#473). Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
-, same sign-preserving intent as [bug] MATH grader: Unicode minus U+2212 is invisible — "−3" extracts as unsigned "3" (sign-flip false positive) and \boxed{−3} never matches -3 #460 for U+2212.1994–1995) are left alone so the last year stays unsigned.ruff<0.16and completes the [bug] DROP grader: leading-decimal answers lose their point — ".5" grades EQUAL to gold "5" (false positive) and UNEQUAL to gold "0.5" (false negative) #423 DROP leading-decimal edge-strip so CI stays green on main's regression tests.Test plan
pytest tests/test_reward_en_em_dash_minus.py tests/test_drop_leading_decimal_point.pyMade with Cursor