Sha** program repair space with existing patches and similar code
Automated program repair (APR) has great potential to reduce bug-fixing effort and many
approaches have been proposed in recent years. APRs are often treated as a search …
approaches have been proposed in recent years. APRs are often treated as a search …
Getafix: Learning to fix bugs automatically
Static analyzers help find bugs early by warning about recurring bug categories. While fixing
these bugs still remains a mostly manual task in practice, we observe that fixes for a specific …
these bugs still remains a mostly manual task in practice, we observe that fixes for a specific …
Fixminer: Mining relevant fix patterns for automated program repair
Patching is a common activity in software development. It is generally performed on a source
code base to address bugs or add new functionalities. In this context, given the recurrence of …
code base to address bugs or add new functionalities. In this context, given the recurrence of …
Repairing bugs in python assignments using large language models
Students often make mistakes on their introductory programming assignments as part of
their learning process. Unfortunately, providing custom repairs for these mistakes can …
their learning process. Unfortunately, providing custom repairs for these mistakes can …
Automatic inference of code transforms for patch generation
We present a new system, Genesis, that processes human patches to automatically infer
code transforms for automatic patch generation. We present results that characterize the …
code transforms for automatic patch generation. We present results that characterize the …
Leveraging syntax-related code for automated program repair
Q **n, SP Reiss - … 32nd IEEE/ACM International Conference on …, 2017 - ieeexplore.ieee.org
We present our automated program repair technique ssFix which leverages existing code
(from a code database) that is syntax-related to the context of a bug to produce patches for …
(from a code database) that is syntax-related to the context of a bug to produce patches for …
Babble: Learning better abstractions with e-graphs and anti-unification
Library learning compresses a given corpus of programs by extracting common structure
from the corpus into reusable library functions. Prior work on library learning suffers from two …
from the corpus into reusable library functions. Prior work on library learning suffers from two …