Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions
GitHub’s Copilot for Pull Requests (PRs) is a promising service aiming to automate various developer tasks related to PRs, such as generating summaries of changes or providing complete walkthroughs with links to the relevant code. As this innovative technology gains traction in the Open Source Software (OSS) community, it is crucial to examine its early adoption and its impact on the development process. Additionally, it offers a unique opportunity to observe how developers respond when they disagree with the generated content. In our study, we employ a mixed-methods approach, blending quantitative analysis with qualitative insights, to examine 18,256 PRs in which parts of the descriptions were crafted by generative AI. Our findings indicate that: (1) Copilot for PRs, though in its infancy, is seeing a marked uptick in adoption. (2) PRs enhanced by Copilot for PRs require less review time and have a higher likelihood of being merged. (3) Developers using Copilot for PRs often complement the automated descriptions with their manual input. These results offer valuable insights into the growing integration of generative AI in software development.
Fri 19 JulDisplayed time zone: Brasilia, Distrito Federal, Brazil change
10:30 - 11:00 | |||
10:30 30mPoster | Understanding the Impact of APIs Behavioral Breaking Changes on Client Applications Posters Dhanushka Jayasuriya University of Auckland, Valerio Terragni University of Auckland, Jens Dietrich Victoria University of Wellington, Kelly Blincoe University of Auckland | ||
10:30 30mPoster | Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-coded Credentials Posters Yizhan Huang The Chinese University of Hong Kong, Yichen LI The Chinese University of Hong Kong, Weibin Wu Sun Yat-sen University, Jianping Zhang The Chinese University of Hong Kong, Michael Lyu The Chinese University of Hong Kong | ||
10:30 30mPoster | Natural Is The Best: Model-Agnostic Code Simplification for Pre-trained Large Language Models Posters Yan Wang Central University of Finance and Economics, Xiaoning Li Central University of Finance and Economics, Tien N. Nguyen University of Texas at Dallas, Shaohua Wang Central University of Finance and Economics, Chao Ni School of Software Technology, Zhejiang University, Ling Ding Central University of Finance and Economics | ||
10:30 30mPoster | PyRadar: Towards Automatically Retrieving and Validating Source Code Repository Information for PyPI Packages Posters Kai Gao University of Science and Technology Beijing, Weiwei Xu Peking University, Wenhao Yang Peking University, Minghui Zhou Peking University | ||
10:30 30mPoster | "The Law Doesn’t Work Like a Computer": Exploring Software Licensing Issues Faced by Legal Practitioners Posters Nathan Wintersgill William & Mary, Trevor Stalnaker William & Mary, Laura A. Heymann William & Mary, Oscar Chaparro William & Mary, Denys Poshyvanyk William & Mary | ||
10:30 30mPoster | RavenBuild: Context, Relevance, and Dependency Aware Build Outcome Prediction Posters Gengyi Sun University of Waterloo, Sarra Habchi Ubisoft Montréal, Shane McIntosh University of Waterloo | ||
10:30 30mPoster | MirrorFair: Fixing Fairness Bugs in Machine Learning Software via Counterfactual Predictions Posters Ying Xiao King's College London / Southern University of Science and Technology, Jie M. Zhang King's College London, Yepang Liu Southern University of Science and Technology, Mohammad Reza Mousavi King's College London, Sicen Liu Southern University of Science and Technology, Dingyuan Xue Southern University of Science and Technology | ||
10:30 30mPoster | Do Code Generation Models Think Like Us? - A Study of Attention Alignment between Large Language Models and Human Programmers Posters Bonan Kou Purdue University, Shengmai Chen Purdue University, Zhijie Wang University of Alberta, Lei Ma The University of Tokyo & University of Alberta, Tianyi Zhang Purdue University | ||
10:30 30mPoster | Dependency-Induced Waste in Continuous Integration: An Empirical Study on NPM Dependencies Posters Nimmi Weeraddana University of Waterloo, Mahmoud Alfadel University of Waterloo, Shane McIntosh University of Waterloo | ||
10:30 30mPoster | A Miss Is as Good as A Mile: Metamorphic Testing for Deep Learning Operators Posters Jinyin Chen Zhejiang University of Technology, Chengyu Jia Zhejiang University of Technology, Yunjie Yan Zhejiang University of Technology, Jie Ge Zhejiang University of Technology, haibin zheng Zhejiang University of Technology, Yao Cheng TÜV SÜD Asia Pacific Pte. Ltd. | ||
10:30 30mPoster | Investigating Documented Privacy Changes in Android OS Posters Chuan Yan University of Queensland, Mark Huasong Meng National University of Singapore, Fuman Xie University of Queensland, Guangdong Bai University of Queensland | ||
10:30 30mPoster | Analyzing Quantum Programs with LintQ: A Static Analysis Framework for Qiskit Posters | ||
10:30 30mPoster | Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions Posters Tao Xiao Nara Institute of Science and Technology, Hideaki Hata Shinshu University, Christoph Treude Singapore Management University, Kenichi Matsumoto Nara Institute of Science and Technology | ||
10:30 30mPoster | Bloat beneath Python's Scales: A Fine-Grained Inter-Project Dependency Analysis Posters Georgios-Petros Drosos ETH Zurich, Thodoris Sotiropoulos ETH Zurich, Diomidis Spinellis Athens University of Economics and Business & Delft University of Technology, Dimitris Mitropoulos University of Athens | ||
This room is conjoined with the Foyer to provide additional space for the coffee break, and hold poster presentations throughout the event.