2026-09-20T06:52:43Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1157742026-06-16T18:55:26Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Martin C. Rinard. Long, Fan, Ph. D. Massachusetts Institute of Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-05-23T16:34:14Z 2018-05-23T16:34:14Z 2018 2018 http://hdl.handle.net/1721.1/115774 1036987605 Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. Cataloged from PDF version of thesis. Includes bibliographical references (pages 285-296). Automatic patch generation holds out the promise of automatically correcting software defects without the need for developers to manually diagnose, understand, and correct these defects. This dissertation presents two novel patch generation systems, Prophet and Genesis, which learn from past successful human patches to enhance the patch generation process. The core of Prophet and Genesis is a novel learning technique that extracts universal properties of correct code and a novel inference technique that generalizes universal patching strategies across different applications. The results show that the learning and inference techniques enable Prophet and Genesis to operate with rich and tractable search spaces that contain many useful patches and efficient search algorithms that prioritize correct patches. By collectively leveraging development efforts worldwide, Prophet and Genesis automatically generate correct patches for real-world defects in large open-source C and Java applications with up to millions lines of code. by Fan Long. Ph.D. 296 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Automatic patch generation via learning from successful human patches Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="50aceb81-ea0c-49f3-9b40-8c46b21afb8b"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Automatic patch generation via learning from successful human patches</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <Authors> <Author> <DisplayName>Long, Fan, Ph. D. Massachusetts Institute of Technology</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>Automatic patch generation holds out the promise of automatically correcting software defects without the need for developers to manually diagnose, understand, and correct these defects. This dissertation presents two novel patch generation systems, Prophet and Genesis, which learn from past successful human patches to enhance the patch generation process. The core of Prophet and Genesis is a novel learning technique that extracts universal properties of correct code and a novel inference technique that generalizes universal patching strategies across different applications. The results show that the learning and inference techniques enable Prophet and Genesis to operate with rich and tractable search spaces that contain many useful patches and efficient search algorithms that prioritize correct patches. By collectively leveraging development efforts worldwide, Prophet and Genesis automatically generate correct patches for real-world defects in large open-source C and Java applications with up to millions lines of code.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>