@inproceedings{16902b99914e43708f9d22bdb683879b,
title = "A Dataset for GitHub Repository Deduplication",
abstract = "GitHub projects can be easily replicated through the site's fork process or through a Git clone-push sequence. This is a problem for empirical software engineering, because it can lead to skewed results or mistrained machine learning models. We provide a dataset of 10.6 million GitHub projects that are copies of others, and link each record with the project's ultimate parent. The ultimate parents were derived from a ranking along six metrics. The related projects were calculated as the connected components of an 18.2 million node and 12 million edge denoised graph created by directing edges to ultimate parents. The graph was created by filtering out more than 30 hand-picked and 2.3 million pattern-matched clumping projects. Projects that introduced unwanted clumping were identified by repeatedly visualizing shortest path distances between unrelated important projects. Our dataset identified 30 thousand duplicate projects in an existing popular reference dataset of 1.8 million projects. An evaluation of our dataset against another created independently with different methods found a significant overlap, but also differences attributed to the operational definition of what projects are considered as related. ",
keywords = "dataset, Deduplication, fork, GitHub, project clone",
author = "Diomidis Spinellis and Zoe Kotti and Audris Mockus",
year = "2020",
month = jun,
day = "29",
doi = "10.1145/3379597.3387496",
language = "English",
series = "Proceedings - 2020 IEEE/ACM 17th International Conference on Mining Software Repositories, MSR 2020",
publisher = "Association for Computing Machinery (ACM)",
pages = "523--527",
booktitle = "Proceedings - 2020 IEEE/ACM 17th International Conference on Mining Software Repositories, MSR 2020",
address = "United States",
note = "17th IEEE/ACM International Conference on Mining Software Repositories, MSR 2020, co-located with the 42nd International Conference on Software Engineering. ICSE 2020 ; Conference date: 29-06-2020 Through 30-06-2020",
}