Automatic patch generation by learning correct code
Abstract
We present Prophet, a novel patch generation system that works with a set of successful human patches obtained from open- source software repositories to learn a probabilistic, application-independent model of correct code. It generates a space of candidate patches, uses the model to rank the candidate patches in order of likely correctness, and validates the ranked patches against a suite of test cases to find correct patches. Experimental results show that, on a benchmark set of 69 real-world defects drawn from eight open-source projects, Prophet significantly outperforms the previous state-of-the-art patch generation system.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 11, 2016
- Source ID
- 10.1145/2914770.2837617
Entities
People
- Fan Long
- Martin Rinard
Organizations
- Defense Advanced Research Projects Agency
- Massachusetts Institute of Technology