SiblingRepair uses LLMs with semantic sibling detection and simultaneous/iterative repair strategies to outperform prior multi-hunk APR tools like Hercules on Defects4J and GHRB benchmarks.
Defects4j: a database of existing faults to enable controlled testing studies for java programs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3roles
dataset 2polarities
use dataset 2representative citing papers
Post-release defects concentrate in older, frequently modified high-churn components and require longer and more complex fixes than pre-release defects.
A learning-based test prioritization method using commit diffs, coverage, and history data outperforms baselines on cross-project validation with Defects4J.
citing papers explorer
-
SiblingRepair: Sibling-Based Multi-Hunk Repair with Large Language Models
SiblingRepair uses LLMs with semantic sibling detection and simultaneous/iterative repair strategies to outperform prior multi-hunk APR tools like Hercules on Defects4J and GHRB benchmarks.
-
What Makes Software Bugs Escape Testing? Evidence from a Large-Scale Empirical Study
Post-release defects concentrate in older, frequently modified high-churn components and require longer and more complex fixes than pre-release defects.
-
Commit-Aware Learning-Based Test Case Prioritization for Continuous Integration
A learning-based test prioritization method using commit diffs, coverage, and history data outperforms baselines on cross-project validation with Defects4J.