Prophet: Automatic Patch Generation via Learning from Successful Human Patches

We present Prophet, a novel patch generation system that learns a probabilistic model over candidate patches from a large code database that contains many past successful human patches. It defines the probabilistic model as the combination of a distribution over program points based on error localiz...

Full description

Bibliographic Details
Main Authors: Long, Fan, Rinard, Martin
Other Authors: Martin Rinard
Published: 2015
Online Access:http://hdl.handle.net/1721.1/97088

Similar Items