FixEval: Execution-based Evaluation of Program Fixes for Programming Problems
Authors:
- 1 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11-18
Abstract
The complexity of modern software has led to a drastic increase in the time and cost associated with detecting and rectifying software bugs. In response, researchers have explored various methods to automatically generate fixes for buggy code. However, due to the large combinatorial space of possible fixes for any given bug, few tools and datasets are available to evaluate model-generated fixes effectively. To address this issue, we introduce FIXEvAL, a benchmark comprising of buggy code submissions to competitive programming problems and their corresponding fixes. FixeValoffers an extensive collection of unit tests to evaluate the correctness of model-generated program fixes and assess further information regarding time, memory constraints, and acceptance based on a verdict. We consider two Transformer language models pretrained on programming languages as our baseline and compare them using match-based and execution-based evaluation metrics. Our experiments show that match-based metrics do not reflect model-generated program fixes accurately. At the same time, execution-based methods evaluate programs through all cases and scenarios designed explicitly for that solution. Therefore, we believe FixeValprovides a step towards real-world automatic bug fixing and model-generated code evaluation. The dataset and models are open-sourced. 1 1 https://github.com/FixEval/FixEval_officialKeywords
All Related Versions
This publication has 20 references indexed in Scilit:
- QuixBugs: a multi-lingual program repair benchmark set based on the quixey challenge2017
- The ManyBugs and IntroClass Benchmarks for Automated Repair of C ProgramsIEEE Transactions on Software Engineering, 2015
- Defects4J: a database of existing faults to enable controlled testing studies for Java programs2014
- Automatic repair of buggy if conditions and missing preconditions with SMT2014
- Programmers' build errors: a case study (at google)2014
- Automatic patch generation learned from human-written patches2013
- On the Complexity of Software SystemsComputer, 2012
- A systematic study of automated program repair: Fixing 55 out of 105 bugs for $8 each2012
- Evolving patches for software repair2011
- On the automation of fixing software bugs2008