Bug fixing
18 papers with code • 1 benchmarks • 1 datasets
SWE-bench
Most implemented papers
FixEval: Execution-based Evaluation of Program Fixes for Programming Problems
To address this issue, we introduce FixEval, a benchmark comprising of buggy code submissions to competitive programming problems and their corresponding fixes.
CoditT5: Pretraining for Source Code and Natural Language Editing
Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits.
ADPTriage: Approximate Dynamic Programming for Bug Triage
In this study, we develop a Markov decision process (MDP) model for an online bug triage task.
Using Developer Discussions to Guide Fixing Bugs in Software
Automatically fixing software bugs is a challenging task.
Automating Code-Related Tasks Through Transformers: The Impact of Pre-training
Then, we pre-train 32 transformers using both (i) generic pre-training objectives usually adopted in SE; and (ii) pre-training objectives tailored to specific code-related tasks subject of our experimentation, namely bug-fixing, code summarization, and code completion.
Bug Characterization in Machine Learning-based Systems
ml-bugs-2022/replication-package
•
•
Based on our results, fixing ML bugs are more costly and ML components are more error-prone, compared to non-ML bugs and non-ML components respectively.
AutoCodeRover: Autonomous Program Improvement
Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding.
Unraveling Code Clone Dynamics in Deep Learning Frameworks
We empirically analyze code clones in nine popular DL frameworks, i. e., TensorFlow, Paddle, PyTorch, Aesara, Ray, MXNet, Keras, Jax and BentoML, to investigate (1) the characteristics of the long-term code cloning evolution over releases in each framework, (2) the short-term, i. e., within-release, code cloning patterns and their influence on the long-term trends, and (3) the file-level code clones within the DL frameworks.
