FIX: krippendorff_alpha NaN for unpairable identical ratings - #2844
Merged
Roman Lutz (romanlutz) merged 2 commits intoSep 26, 2026
Conversation
…ntical ratings The num_categories == 1 early return reported perfect agreement before the total_n == 0 degenerate check, so data where every item is rated by a single rater (no pairable coincidences) produced alpha = 1.0 whenever all ratings happened to be identical. The statistic is undefined in that case; the docstring already promises NaN for undefined input. Move the single-category early return after the coincidence construction so unpairable data reaches the existing total_n == 0 NaN path while pairable identical ratings still return 1.0.
Roman Lutz (romanlutz)
approved these changes
Sep 26, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #2843.
reordered the early returns so the no-pairable-ratings check runs before the single-category perfect-agreement exit, making any dataset without pairable ratings return NaN consistently with the docstring and with the existing differing-ratings behavior.
verified with a 1000-case differential fuzz against an independent reference implementation (0 mismatches), a regression test that fails on main, the full krippendorff suite (47 green) and the 2693-test scorer-evaluation suite. ruff clean.