Automatic patch generation by learning correct code
Published in ACM SIGPLAN Notices • Jan 11, 2016
NobleIDNI7P75W95R93S88
Authors:,
Fan Long
Martin Rinard
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 candid...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!