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.
InProceedings of the 38th IEEE/ACM International Confer- ence on Automated Software Engineering(Echternach, Luxembourg) (ASE ’23)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Hot fixes show urgency patterns with reduced collaboration and testing, differing from regular fixes, and human versus AI agents display over 10 distinct repair behaviors in large-scale GitHub data.
Quantum circuits show high average condition (97.56%) and decision (97.63%) coverage but lower path coverage (71.84%), with probabilistic versions adding confidence levels (averages 88.87%, 88.65%, 37.18%); mutation testing reveals weak or no correlation between structural coverage and fault finding
Technical heroes (commits, files, churn) and social heroes (issue comments) in Apache projects overlap only 10% with asymmetric activity, and bug fix/reopen rates show modest differences that vary by severity.
Emote enhances EvoSuite by allowing non-target setup calls in modular tests and refocusing the fitness function on the target call chain, delivering 15.15% higher target method coverage on an SF100 subset.
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.
-
Hot Fixing in the Wild
Hot fixes show urgency patterns with reduced collaboration and testing, differing from regular fixes, and human versus AI agents display over 10 distinct repair behaviors in large-scale GitHub data.
-
Probabilistic Condition, Decision and Path Coverage of Circuit-based Quantum Programs
Quantum circuits show high average condition (97.56%) and decision (97.63%) coverage but lower path coverage (71.84%), with probabilistic versions adding confidence levels (averages 88.87%, 88.65%, 37.18%); mutation testing reveals weak or no correlation between structural coverage and fault finding
-
Multifaceted Hero Developers and Bug-Fixing Outcomes Across Severity
Technical heroes (commits, files, churn) and social heroes (issue comments) in Apache projects overlap only 10% with asymmetric activity, and bug fix/reopen rates show modest differences that vary by severity.
-
On the Effectiveness of Modular Testing in EvoSuite
Emote enhances EvoSuite by allowing non-target setup calls in modular tests and refocusing the fitness function on the target call chain, delivering 15.15% higher target method coverage on an SF100 subset.