BigIssue: A Realistic Bug Localization Benchmark

TL;DR

BigIssue is a new benchmark designed to evaluate bug localization techniques on realistic Java bugs, aiming to improve machine learning models' ability to identify bugs in real-world code repositories.

Contribution

The paper introduces BigIssue, a comprehensive benchmark dataset for realistic bug localization, encouraging development of models that consider full repository context.

Findings

Provides diverse real and synthetic Java bugs for evaluation

Highlights the importance of full repository context in bug localization

Aims to enhance bug localization and automatic program repair performance

Abstract

As machine learning tools progress, the inevitable question arises: How can machine learning help us write better code? With significant progress being achieved in natural language processing with models like GPT-3 and Bert, the applications of natural language processing techniques to code are starting to be explored. Most of the research has been focused on automatic program repair (APR), and while the results on synthetic or highly filtered datasets are promising, such models are hard to apply in real-world scenarios because of inadequate bug localization. We propose BigIssue: a benchmark for realistic bug localization. The goal of the benchmark is two-fold. We provide (1) a general benchmark with a diversity of real and synthetic Java bugs and (2) a motivation to improve bug localization capabilities of models through attention to the full repository context. With the introduction of BigIssue, we hope to advance the state of the art in bug localization, in turn improving APR performance and increasing its applicability to the modern development cycle.