Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs?
Cedric Richter, Jan Haltermann, Marie-Christine Jakobs, Felix Pauck, Stefan Schott, Heike Wehrheim
2022年份
2被引次数
摘要
Debugging, that is, identifying and fixing bugs in software, is a central part of software development. Developers are therefore often confronted with the task of deciding whether a given code snippet contains a bug, and if yes, where. Recently, data-driven methods have been employed to learn this task of bug detection, resulting (amongst others) in so called neural bug detectors. Neural bug detectors are trained on millions of buggy and correct code snippets.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- How to Train Your Neural Bug Detector: Artificial vs Real BugsCedric Richter, Heike WehrheimASE 2023 · 被引用 5 次
- Self-Supervised Bug Detection and RepairMiltiadis Allamanis, Henry Jackson-Flux, Marc BrockschmidtNeurIPS 2021 · 被引用 145 次
- Hoppity: Learning Graph Transformations to Detect and Fix Bugs in ProgramsElizabeth Dinella, Hanjun Dai, Ziyang Li, Mayur Naik 等ICLR 2020 · 被引用 212 次
- DeepFD: Automated Fault Diagnosis and Localization for Deep Learning ProgramsJialun Cao, Meiziniu Li, Xiao Chen, Ming Wen 等ICSE 2022 · 被引用 42 次
- DeepLocalize: Fault Localization for Deep Neural NetworksMohammad Wardat, Wei Le, Hridesh RajanICSE 2021 · 被引用 93 次
