feat(eval): paired bootstrap + durable predictions in the Arabic harness - #107
Merged
Conversation
…valuate_der The windowed Arabic harness now emits final_preds.jsonl (src, teacher/student predictions) and a paired sentence-level bootstrap (delta, ci95, p_leq0) inside final_eval.json — a point delta without a CI is not evidence. Single decode pass; aggregate DER unchanged.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Extends PR #9's protocol to the windowed Sadeed harness: per-paragraph predictions are saved (final_preds.jsonl — also the provenance artifact), and every verdict carries delta/ci95/p_leq0 via a deterministic seeded bootstrap. Reruns of the headline specs give the papers their error bars; saved preds make any future pairing offline.