Fix PaperBench code-only fallback for non-code rubrics - #164
Open
sylvesterkaczmarek wants to merge 1 commit into
Open
Fix PaperBench code-only fallback for non-code rubrics#164sylvesterkaczmarek wants to merge 1 commit into
sylvesterkaczmarek wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
code_only=Truefallback produce a valid single Code Development task when a rubric contains no Code Development leavesTaskNodestatesrun_judge()currently falls back with:when
task_tree.code_only()returnsNone.TaskNodevalidation forbids a task category on an internal node, so the first call raises beforeset_sub_tasks([])can run. Reversing the calls has the analogous problem because a leaf with no task category is also invalid.The fix performs the fallback atomically with
dataclasses.replace, creating the intended leaf without passing through an invalid intermediate tree.Regression coverage verifies both the no-code fallback and the existing path where a Code Development subtree is present.