Add spec-guided RepairAgent extension with full analysis#22
Open
DinoZ-p wants to merge 1 commit into
Open
Conversation
Pipeline additions: - spec_generator.py: Javadoc-driven spec generation via GPT-4o - spec_verifier.py: Second-pass spec quality verification - defects4j.py: Auto DELETE+INSERT for low-similarity modifications - base.py: Spec injection into agent prompt at init - prompt_settings.yaml: Anti-overfitting guideline Research artifacts (researchAnalysis/): - 24 per-bug analyses of E34 plausible patches - Root cause taxonomy of 66 unfixed bugs with evidence - E39 detailed evaluation of 5 design improvements - Charts and presentation slides - Master report and mentor status report Results on 98 bugs the original RepairAgent could not fix: - E17 (first spec design): 16 plausible, 7 correct - E34 (refined spec): 24 plausible, 13 correct - Union: 15 unique correct fixes See HANDOFF.md for setup, current state, and experiment plan.
Author
|
1 |
4 similar comments
Author
|
1 |
Author
|
1 |
Author
|
1 |
Author
|
1 |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pipeline additions:
Research artifacts (researchAnalysis/):
Results on 98 bugs the original RepairAgent could not fix:
See HANDOFF.md for setup, current state, and experiment plan.