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
2022Year
2Citations
Abstract
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.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 5bc469ba-308f-4048-abde-3dfb7ca9f028Related papers
- How to Train Your Neural Bug Detector: Artificial vs Real BugsCedric Richter, Heike WehrheimASE 2023 · 5 citations
- Self-Supervised Bug Detection and RepairMiltiadis Allamanis, Henry Jackson-Flux, Marc BrockschmidtNeurIPS 2021 · 145 citations
- Hoppity: Learning Graph Transformations to Detect and Fix Bugs in ProgramsElizabeth Dinella, Hanjun Dai, Ziyang Li, Mayur Naik et al.ICLR 2020 · 212 citations
- DeepFD: Automated Fault Diagnosis and Localization for Deep Learning ProgramsJialun Cao, Meiziniu Li, Xiao Chen, Ming Wen et al.ICSE 2022 · 42 citations
- DeepLocalize: Fault Localization for Deep Neural NetworksMohammad Wardat, Wei Le, Hridesh RajanICSE 2021 · 93 citations
