Prophet swMATH ID: 17448 Software Authors: Long, Fan; Rinard, Martin Description: Automatic patch generation by learning correct code. 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. Homepage: http://dl.acm.org/citation.cfm?doid=2837614.2837617 Keywords: code correctness model; learning correct code; program repair Related Software: SemFix; Angelix; GZoltar; Nopol; ASTOR; GenProg; DLFix; DeepFix; QuixBugs; Codeflaws; Qlose; JFIX; Defects4J; jGenProg; ARJA; jMetal; SQLizer; RobustFill; aplore3; Python Cited in: 4 Documents all top 5 Cited by 17 Authors 1 Cubuktepe, Murat 1 Forrest, Stephanie 1 Jansen, Nils 1 Junges, Sebastian 1 Kapur, Deepak 1 Katoen, Joost-Pieter 1 Khaireddine, Besma 1 Krasanakis, Emmanouil 1 Martinez, Matias 1 Mili, Ali 1 Nguyen, Thanhvu H. 1 Papusha, Ivan 1 Poonawala, Hasan A. 1 Symeonidis, Andreas L. 1 Topcu, Ufuk 1 Weimer, Westley 1 Zakharchenko, Aleksandr Cited in 2 Serials 1 Acta Informatica 1 Journal of Logical and Algebraic Methods in Programming Cited in 2 Fields 4 Computer science (68-XX) 1 Operations research, mathematical programming (90-XX) Citations by Year