feat(review): moderate-explanation style in findings prompt - #527
Merged
Conversation
Empirical study (n=34, arXiv:2607.24601): full explanations maximize perceived trust but NOT agreement — moderate explanations achieve the highest developer agreement (89.22%). Instruct the reviewer to keep each finding at severity + short reason (1-3 sentences) + code evidence, avoiding long reasoning chains. Refs #525
2 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Add an EXPLANATION STYLE section to the review system prompt instructing findings at moderate depth: severity + short reason (1-3 sentences) + specific code evidence. Explicitly discourages long reasoning chains and exhaustive justifications.
Why
Refs #525 (first checklist item). Empirical evidence (arXiv:2607.24601, n=34): full explanations yield highest perceived trust (3.99/5) but NOT highest agreement; moderate explanations achieve highest developer agreement (89.22%). No explanation scores lowest on both. Applying the moderate-explanation principle to cora's findings format.
The second checklist item (exemplar-guided reformulation from accept/dismiss history) is a larger, data-dependent feature — tracked for a future PR.
Testing