@proceedings {1902, title = {Assessing Code Authorship: The Case of the Linux Kernel}, volume = {496}, year = {2017}, month = {05/2017}, pages = {151-163}, publisher = {Springer}, abstract = {Code authorship is a key information in large-scale open-source systems. Among others, it allows maintainers to assess division of work and identify key collaborators. Interestingly, open-source communities lack guidelines on how to manage authorship. This could be mitigated by setting to build an empirical body of knowledge on how authorship-related measures evolve in successful open-source communities. Towards that direction, we perform a case study on the Linux kernel. Our results show that: (a) only a small portion of developers (26\%) makes significant contributions to the code base; (b) the distribution of the number of files per author is highly skewed{\textemdash}a small group of top-authors (3\%) is responsible for hundreds of files, while most authors (75\%) are responsible for at most 11 files; (c) most authors (62\%) have a specialist profile; (d) authors with a high number of co-authorship connections tend to collaborate with others with less connections.}, keywords = {code authorship, developer network, linux kernel}, doi = {10.1007/978-3-319-57735-7_15}, url = {https://link.springer.com/chapter/10.1007/978-3-319-57735-7_15}, author = {Guilherme Avelino and Passos, Leonardo and Andre Hora and Marco Tulio Valente} } @conference {Passos:2014:DFA:2597073.2597124, title = {A Dataset of Feature Additions and Feature Removals from the Linux Kernel}, booktitle = {Proceedings of the 11th Working Conference on Mining Software Repositories}, series = {MSR 2014}, year = {2014}, pages = {376{\textendash}379}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {This paper describes a dataset of feature additions and removals in the Linux kernel evolution history, spanning over seven years of kernel development. Features, in this context, denote configurable system options that users select when creating customized kernel images. The provided dataset is the largest corpus we are aware of capturing feature additions and removals, allowing researchers to assess the kernel evolution from a feature-oriented point-of-view. Furthermore, the dataset can be used to better understand how features evolve over time, and how different artifacts change as a result. One particular use of the dataset is to provide a real-world case to assess existing support for feature traceability and evolution. In this paper, we detail the dataset extraction process, the underlying database schema, and example queries. The dataset is directly available at our Bitbucket repository: https://bitbucket.org/lpassos/kconfigdb }, keywords = {evolution, linux, msr data showcase, Traceability, Version Control History}, isbn = {978-1-4503-2863-0}, doi = {10.1145/2597073.2597124}, url = {http://doi.acm.org/10.1145/2597073.2597124}, attachments = {https://flosshub.org/sites/flosshub.org/files/kernel.pdf}, author = {Passos, Leonardo and Czarnecki, Krzysztof} }