Write a Blog >>

We present Prophet, a novel patch generation system that learns a probabilistic model over candidate patches from a database of past successful patches. Prophet defines the probabilistic model as the combination of a distribution over program points based on error localization algorithms and a parameterized log-linear distribution over modification operations. It then learns the model parameters via maximum log-likelihood, which identifies important characteristics of the previous successful patches. For a new defect, Prophet generates a search space that contains many candidate patches, applies the learned model to prioritize those potentially correct patches that are consistent with the identified successful patch characteristics, and then validates the candidate patches with a user supplied test suite. The experimental results indicate that these techniques enable Prophet to generate correct patches for 15 out of 69 real-world errors in open source projects. The previous state of the art generate and validate system, which uses a set of hand-code heuristics to prioritize the search, generates correct patches for 11 of these same 69 errors.

Thu 21 Jan

Displayed time zone: Guadalajara, Mexico City, Monterrey change

10:30 - 12:10
Track 2: Probabilistic and statistical analysisResearch Papers at Grand Bay South
Chair(s): Aditya Nori Microsoft Research, UK
10:30
25m
Talk
Prophet: Automatic Patch Generation via Learning from Successful Patches
Research Papers
Fan Long MIT CSAIL, Martin C. Rinard Massachusetts Institute of Technology, USA
Media Attached
10:55
25m
Talk
Estimating types in binaries using predictive modeling
Research Papers
Omer Katz Technion, Israel Institute of Technology, Ran El-Yaniv Technion, Israel Institute of Technology, Eran Yahav Technion
Media Attached File Attached
11:20
25m
Talk
Algorithmic Analysis of Qualitative and Quantitative Termination Problems for Affine Probabilistic Programs
Research Papers
Krishnendu Chatterjee IST Austria, Hongfei Fu IST Austria, Rouzbeh Hasheminezhad Sharif University, Petr Novotný IST Austria
Media Attached
11:45
25m
Talk
Transforming Spreadsheet Data Types using Examples
Research Papers
Rishabh Singh Microsoft Research, Sumit Gulwani Microsoft Research
Media Attached