{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:00:57Z","timestamp":1785495657278,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3793302.3793369","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:42:54Z","timestamp":1785494574000},"page":"423-434","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Modeling Sampling Workflows for Code Repositories"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2019-1058","authenticated-orcid":false,"given":"Romain","family":"Lefeuvre","sequence":"first","affiliation":[{"name":"University of Rennes, Inria, CNRS, IRISA, Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8504-8139","authenticated-orcid":false,"given":"Ma\u00efwenn","family":"Le Goasteller","sequence":"additional","affiliation":[{"name":"University of Rennes, Inria, CNRS, IRISA, Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9868-1814","authenticated-orcid":false,"given":"Jessie","family":"Galasso","sequence":"additional","affiliation":[{"name":"McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7104-7848","authenticated-orcid":false,"given":"Benoit","family":"Combemale","sequence":"additional","affiliation":[{"name":"Inria, University of Rennes, CNRS, IRISA, Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4821","authenticated-orcid":false,"given":"Quentin","family":"Perez","sequence":"additional","affiliation":[{"name":"INSA Rennes, University of Rennes, Inria, CNRS, IRISA, Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6304-9926","authenticated-orcid":false,"given":"Houari","family":"Sahraoui","sequence":"additional","affiliation":[{"name":"DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"2022. The Galaxy platform for accessible reproducible and collaborative biomedical analyses: 2022 update. Nucleic acids research 50 W1 (2022) W345\u2013W351.","DOI":"10.1093\/nar\/gkac610"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Khairul Alam Banani Roy Chanchal\u00a0K Roy and Kartik Mittal. 2025. An empirical investigation on the challenges in scientific workflow systems development. Empirical Software Engineering 30 5 (2025) 151.","DOI":"10.1007\/s10664-025-10705-2"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Sebastian Baltes and Paul Ralph. 2022. Sampling in software engineering research: a critical review and guidelines. 27 4 (2022) 94. 10.1007\/s10664-021-10072-8","DOI":"10.1007\/s10664-021-10072-8"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78246-9_38"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Juan\u00a0Andr\u00e9s Carruthers Jorge\u00a0Andr\u00e9s Diaz-Pace and Emanuel Irraz\u00e1bal. 2024. A longitudinal study on the temporal validity of software samples. Information and Software Technology 168 (2024) 107404.","DOI":"10.1016\/j.infsof.2024.107404"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Alejandra Cervera Ville Rantanen Kristian Ovaska Marko Laakso Javier Nunez-Fontarnau Amjad Alkodsi Julia Casado Chiara Facciotto Antti H\u00e4kkinen Riku Louhimo et\u00a0al. 2019. Anduril 2: upgraded large-scale data integration framework. Bioinformatics 35 19 (2019) 3815\u20133817.","DOI":"10.1093\/bioinformatics\/btz133"},{"key":"e_1_3_3_2_8_2","volume-title":"Sampling Techniques","author":"Cochran William\u00a0G","year":"1977","unstructured":"William\u00a0G Cochran. 1977. Sampling Techniques. John Wiley & Sons, Nashville, TN."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"dblp Team. 2025. dblp computer science bibliography \u2013 Monthly Snapshot XML Release of July 2025. 10.4230\/dblp.xml.2025-07-02","DOI":"10.4230\/dblp.xml.2025-07-02"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Paolo Di\u00a0Tommaso Maria Chatzou Evan\u00a0W Floden Pablo\u00a0Prieto Barja Emilio Palumbo and Cedric Notredame. 2017. Nextflow enables reproducible computational workflows. Nature biotechnology 35 4 (2017) 316\u2013319.","DOI":"10.1038\/nbt.3820"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Robert Dyer Hoan\u00a0Anh Nguyen Hridesh Rajan and Tien\u00a0N. Nguyen. 2015. Boa: Ultra-Large-Scale Software Repository and Source-Code Mining. ACM Trans. Softw. Eng. Methodol. 25 1 (Dec. 2015) 34\u00a0pages. 10.1145\/2803171","DOI":"10.1145\/2803171"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/1809745"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3674805.3690747"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2597073.2597074"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Johannes K\u00f6ster and Sven Rahmann. 2012. Snakemake\u2014a scalable bioinformatics workflow engine. Bioinformatics 28 19 (2012) 2520\u20132522.","DOI":"10.1093\/bioinformatics\/bts480"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"William Kruskal and Frederick Mosteller. 1979. Representative sampling I: Non-scientific literature. International Statistical Review\/Revue Internationale de Statistique (1979) 13\u201324. 10.2307\/1403202","DOI":"10.2307\/1403202"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"William Kruskal and Frederick Mosteller. 1979. Representative sampling II: Scientific literature excluding statistics. International Statistical Review\/Revue Internationale de Statistique (1979) 111\u2013127. 10.2307\/1402564","DOI":"10.2307\/1402564"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"William Kruskal and Frederick Mosteller. 1979. Representative Sampling III: The Current Statistical Literature. International Statistical Review \/ Revue Internationale de Statistique 47 3 (1979) 245\u2013265. 10.2307\/1402647","DOI":"10.2307\/1402647"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589806.3600043"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Yuxing Ma Tapajit Dey Chris Bogart Sadika Amreen Marat Valiev Adam Tutko David Kennard Russell Zaretzki and Audris Mockus. 2021. World of code: enabling a research workflow for mining and analyzing the universe of open source VCS data. Empirical Softw. Engg. 26 2 (March 2021) 42\u00a0pages. 10.1007\/s10664-020-09905-9","DOI":"10.1007\/s10664-020-09905-9"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196446"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.ECOOP.2024.27"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Frank\u00a0J Massey\u00a0Jr. 1951. The Kolmogorov-Smirnov test for goodness of fit. Journal of the American statistical Association 46 253 (1951) 68\u201378.","DOI":"10.1080\/01621459.1951.10500769"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Felix M\u00f6lder Kim\u00a0Philipp Jablonski Brice Letcher Michael\u00a0B. Hall Christopher Tomkins-Tinch Vanessa\u00a0V. Sochat Jan Forster Soohyun Lee Sven Twardziok Alexander Kanitz Andreas Wilm Manuel Holtgrewe Sven Rahmann Sven Nahnsen and Johannes K\u00f6ster. 2021. Sustainable data analysis with Snakemake. F1000Research 10 (2021) 33. 10.12688\/F1000RESEARCH.29032.1","DOI":"10.12688\/F1000RESEARCH.29032.1"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Marcus\u00a0R Munaf\u00f2 Brian\u00a0A Nosek Dorothy\u00a0VM Bishop Katherine\u00a0S Button Christopher\u00a0D Chambers Nathalie Percie\u00a0du Sert Uri Simonsohn Eric-Jan Wagenmakers Jennifer\u00a0J Ware and John\u00a0PA Ioannidis. 2017. A manifesto for reproducible science. Nature human behaviour 1 1 (2017) 0021.","DOI":"10.1038\/s41562-016-0021"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2491411.2491415"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_2"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387442"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00030"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Per Runeson and Martin H\u00f6st. 2009. Guidelines for conducting and reporting case study research in software engineering. Empirical Softw. Engg. 14 2 (April 2009) 131\u2013164. 10.1007\/s10664-008-9102-8","DOI":"10.1007\/s10664-008-9102-8"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-1404-4_5"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"M. Vidoni. 2022. A systematic process for Mining Software Repositories: Results from a systematic literature review. 144 (2022) 106791. 10.1016\/j.infsof.2021.106791","DOI":"10.1016\/j.infsof.2021.106791"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Yanming Yang Xin Xia David Lo Tingting Bi John Grundy and Xiaohu Yang. 2022. Predictive Models in Software Engineering: Challenges and Opportunities. ACM Trans. Softw. Eng. Methodol. 31 3 (apr 2022) 72\u00a0pages. 10.1145\/3503509","DOI":"10.1145\/3503509"}],"event":{"name":"MSR '26: 23rd International Conference on Mining Software Repositories","location":"Rio de Janeiro Brazil","acronym":"MSR '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 23rd International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793302.3793369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:43:11Z","timestamp":1785494591000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793302.3793369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":32,"alternative-id":["10.1145\/3793302.3793369","10.1145\/3793302"],"URL":"https:\/\/doi.org\/10.1145\/3793302.3793369","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}