{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:16:33Z","timestamp":1782958593150,"version":"3.54.5"},"reference-count":90,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T00:00:00Z","timestamp":1737158400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T00:00:00Z","timestamp":1737158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TED2021-130331B-I00"],"award-info":[{"award-number":["TED2021-130331B-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001866","name":"Fonds National de la Recherche Luxembourg","doi-asserted-by":"publisher","award":["16544475"],"award-info":[{"award-number":["16544475"]}],"id":[{"id":"10.13039\/501100001866","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10664-024-10608-8","type":"journal-article","created":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T08:30:05Z","timestamp":1737189005000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["On the suitability of hugging face hub for empirical studies"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5334-9041","authenticated-orcid":false,"given":"Adem","family":"Ait","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier Luis","family":"C\u00e1novas Izquierdo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi","family":"Cabot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,18]]},"reference":[{"key":"10608_CR1","doi-asserted-by":"crossref","unstructured":"Ait A, Izquierdo JLC, Cabot J (2022) An empirical study on the survival rate of github projects. In: Int. Conf. on Mining Software Repositories, pp 365\u2013375","DOI":"10.1145\/3524842.3527941"},{"key":"10608_CR2","first-page":"728","volume-title":"Int","author":"A Ait","year":"2023","unstructured":"Ait A, C\u00e1novas Izquierdo JL, Cabot J (2023) HFCommunity: a Tool to Analyze the Hugging Face Hub Community. Int. Conf. on Software Analysis, Evolution and Reengineering, pp 728\u2013732"},{"key":"10608_CR3","unstructured":"Ait A, Izquierdo JLC, Cabot J (2023b) On the suitability of hugging face hub for empirical studies. arXiv:2307.14841"},{"key":"10608_CR4","doi-asserted-by":"crossref","unstructured":"Akhtar M, Benjelloun O, Conforti C, Gijsbers P, Giner-Miguelez J, Jain N, Kuchnik M, Lhoest Q, Marcenac P, Maskey M, Mattson P, Oala L, Ruyssen P, Shinde R, Simperl E, Thomas G, Tykhonov S, Vanschoren J, van\u00a0der Velde J, Vogler S, Wu C (2024) Croissant: A metadata format for ml-ready datasets. In: Workshop on Data Management for End-to-End Machine Learning, pp 1\u20136","DOI":"10.1145\/3650203.3663326"},{"key":"10608_CR5","doi-asserted-by":"crossref","unstructured":"Al-Rubaye A, Sukthankar G (2023) Improving Code Review with GitHub Issue Tracking. In: Int. Conf. on advances in social networks analysis and mining, p 210-217","DOI":"10.1109\/ASONAM55673.2022.10068709"},{"issue":"4","key":"10608_CR6","doi-asserted-by":"publisher","first-page":"274","DOI":"10.17706\/jsw.12.4.274-291","volume":"12","author":"G Alamer","year":"2017","unstructured":"Alamer G, Alyahya S (2017) Open Source Software Hosting Platforms: A Collaborative Perspective\u2019s Review. J Softw 12(4):274\u2013291","journal-title":"J Softw"},{"key":"10608_CR7","doi-asserted-by":"crossref","unstructured":"Baltes S, Kiefer R, Diehl S (2017) Attribution Required: Stack Overflow Code Snippets in GitHub Projects. In: Int. conf. on software engineering Companion, pp 161\u2013163","DOI":"10.1109\/ICSE-C.2017.99"},{"key":"10608_CR8","doi-asserted-by":"crossref","unstructured":"Baltes S, Knack J, Anastasiou D, Tymann R, Diehl S (2018) (No) Influence of Continuous Integration on the Commit Activity in GitHub Projects. In: ACM SIGSOFT Int. Workshop on Software Analytics, pp 1\u20137","DOI":"10.1145\/3278142.3278143"},{"issue":"6","key":"10608_CR9","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1109\/TSE.2019.2918536","volume":"47","author":"L Bao","year":"2021","unstructured":"Bao L, Xia X, Lo D, Murphy GC (2021) A Large Scale Study of Long-Time Contributor Prediction for GitHub Projects. IEEE Trans Software Eng 47(6):1277\u20131298","journal-title":"IEEE Trans Software Eng"},{"key":"10608_CR10","doi-asserted-by":"crossref","unstructured":"B\u00e4umer FS, Dollmann M, Geierhos M (2017) Studying Software Descriptions in SourceForge and App Stores for a Better Understanding of Real-Life Requirements. In: ACM SIGSOFT Int. Workshop on App Market Analytics, pp 19\u201325","DOI":"10.1145\/3121264.3121269"},{"key":"10608_CR11","doi-asserted-by":"crossref","unstructured":"Biazzini M, Baudry B (2014) \u201cMay the Fork Be with You\u201d: Novel Metrics to Analyze Collaboration on GitHub. In: Int. Workshop on Emerging Trends in Software Metrics, pp 37\u201343","DOI":"10.1145\/2593868.2593875"},{"key":"10608_CR12","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.jss.2018.09.016","volume":"146","author":"H Borges","year":"2018","unstructured":"Borges H, Tulio Valente M (2018) What\u2019s in a GitHub Star? Understanding Repository Starring Practices in a Social Coding Platform. J Syst Softw 146:112\u2013129","journal-title":"J Syst Softw"},{"key":"10608_CR13","first-page":"63","volume":"1","author":"X Cai","year":"2016","unstructured":"Cai X, Zhu J, Shen B, Chen Y (2016) GRETA: Graph-Based Tag Assignment for GitHub Repositories. Annual computer software and applications conference 1:63\u201372","journal-title":"Annual computer software and applications conference"},{"key":"10608_CR14","doi-asserted-by":"crossref","unstructured":"Casalnuovo C, Suchak Y, Ray B, Rubio-Gonz\u00e1lez C (2017) GitcProc: a tool for processing and classifying GitHub commits. In: ACM SIGSOFT Int. symposium on software testing and analysis, pp 396\u2013399","DOI":"10.1145\/3092703.3098230"},{"key":"10608_CR15","doi-asserted-by":"crossref","unstructured":"Casta\u00f1o J, Mart\u00ednez-Fern\u00e1ndez S, Franch X, Bogner J (2023a) Analyzing the evolution and maintenance of ML models on hugging face. arXiv:2311.13380","DOI":"10.1145\/3643991.3644898"},{"key":"10608_CR16","doi-asserted-by":"crossref","unstructured":"Casta\u00f1o J, Mart\u00ednez-Fern\u00e1ndez S, Franch X, Bogner J (2023b) Exploring the carbon footprint of hugging face\u2019s ML models: A repository mining study. In: Int. symposium on empirical software engineering and measurement, pp 1\u201312","DOI":"10.1109\/ESEM56168.2023.10304801"},{"key":"10608_CR17","doi-asserted-by":"crossref","unstructured":"Chen D, Stolee KT, Menzies T (2019) Replication Can Improve Prior Results: A GitHub Study of Pull Request Acceptance. In: Int. Conf. on Program Comprehension, pp 179\u2013190","DOI":"10.1109\/ICPC.2019.00037"},{"key":"10608_CR18","doi-asserted-by":"crossref","unstructured":"Cosentino V, C\u00e1novas\u00a0Izquierdo JL, Cabot J (2016) Findings from GitHub: Methods, Datasets and Limitations. In: Int. conf. on mining software repositories, pp 137\u2013141","DOI":"10.1145\/2901739.2901776"},{"key":"10608_CR19","doi-asserted-by":"publisher","first-page":"7173","DOI":"10.1109\/ACCESS.2017.2682323","volume":"5","author":"V Cosentino","year":"2017","unstructured":"Cosentino V, C\u00e1novas Izquierdo JL, Cabot J (2017) A Systematic Mapping Study of Software Development with GitHub. IEEE Access 5:7173\u20137192","journal-title":"IEEE Access"},{"issue":"1","key":"10608_CR20","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s10664-021-10054-w","volume":"27","author":"R Croft","year":"2022","unstructured":"Croft R, Xie Y, Zahedi M, Babar MA, Treude C (2022) An empirical study of developers\u2019 discussions about security challenges of different programming languages. Empir Softw Eng 27(1):27","journal-title":"Empir Softw Eng"},{"key":"10608_CR21","doi-asserted-by":"crossref","unstructured":"Dabbish LA, Stuart HC, Tsay J, Herbsleb JD (2012) Social coding in github: transparency and collaboration in an open software repository. In: Conf. on computer supported cooperative work, pp 1277\u20131286","DOI":"10.1145\/2145204.2145396"},{"key":"10608_CR22","first-page":"560","volume-title":"Int","author":"O Dabic","year":"2021","unstructured":"Dabic O, Aghajani E, Bavota G (2021) Sampling projects in github for MSR studies. Int. Conf. on mining software repositories, IEEE, pp 560\u2013564"},{"key":"10608_CR23","doi-asserted-by":"crossref","unstructured":"Decan A, Mens T, Claes M, Grosjean P (2016) When GitHub Meets CRAN: An Analysis of Inter-Repository Package Dependency Problems. In: Int. Conf. on Software Analysis, Evolution, and Reengineering, pp 493\u2013504","DOI":"10.1109\/SANER.2016.12"},{"key":"10608_CR24","doi-asserted-by":"crossref","unstructured":"Demeyer S, Murgia A, Wyckmans K, Lamkanfi A (2013) Happy Birthday! a Trend Analysis on Past Msr Papers. In: Int. working conf. on mining software repositories, pp 353\u2013362","DOI":"10.1109\/MSR.2013.6624049"},{"key":"10608_CR25","doi-asserted-by":"crossref","unstructured":"Destefanis G, Ortu M, Bowes D, Marchesi M, Tonelli R (2018) On Measuring Affects of Github Issues\u2019 Commenters. In: Int. workshop on emotion awareness in software engineering, pp 14\u201319","DOI":"10.1145\/3194932.3194936"},{"key":"10608_CR26","doi-asserted-by":"crossref","unstructured":"Dyer R, Nguyen HA, Rajan H, Nguyen TN (2015) Boa: Ultra-Large-Scale Software Repository and Source-Code Mining. ACM Trans Softw Eng Methodol 25(1)","DOI":"10.1145\/2803171"},{"key":"10608_CR27","doi-asserted-by":"crossref","unstructured":"Eibl G, Thurnay L (2023) The Promises and Perils of Open Source Software Release and Usage by Government - Evidence from GitHub and Literature. In: Int. conf. on digital government research, pp 180\u2013190","DOI":"10.1145\/3598469.3598489"},{"key":"10608_CR28","doi-asserted-by":"crossref","unstructured":"English R, Schweik CM (2007) Identifying Success and Tragedy of FLOSS Commons: A Preliminary Classification of Sourceforge.net Projects. In: Int. Workshop on emerging trends in floss research and development, pp 11\u201311","DOI":"10.1109\/FLOSS.2007.9"},{"key":"10608_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.110613","volume":"167","author":"S Eraslan","year":"2020","unstructured":"Eraslan S, Kopec-Harding K, Jay C, Embury SM, Haines R, Cort\u00e9s R\u00edos JC, Crowther P (2020) Integrating GitLab metrics into coursework consultation sessions in a software engineering course. J Syst Softw 167:110613","journal-title":"J Syst Softw"},{"key":"10608_CR30","first-page":"176","volume-title":"Int","author":"J Fairbanks","year":"2023","unstructured":"Fairbanks J, Tharigonda A, Eisty NU (2023) Analyzing the Effects of CI\/CD on Open Source Repositories in GitHub and GitLab. Int. Conf. on Software Engineering Research, Management and Applications, pp 176\u2013181"},{"issue":"7","key":"10608_CR31","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/s10664-022-10200-y","volume":"27","author":"SW Flint","year":"2022","unstructured":"Flint SW, Chauhan J, Dyer R (2022) Pitfalls and Guidelines for Using Time-based Git Data. Empir Softw Eng 27(7):194","journal-title":"Empir Softw Eng"},{"key":"10608_CR32","doi-asserted-by":"crossref","unstructured":"Foushee B, Krein JL, Wu J, Buck R, Knutson CD, Pratt LJ, MacLean AC (2013) Reflexivity, Raymond, and the Success of Open Source Software Development: A SourceForge Empirical Study. In: Int. conf. on evaluation and assessment in software engineering, pp 246\u2013251","DOI":"10.1145\/2460999.2461036"},{"key":"10608_CR33","doi-asserted-by":"crossref","unstructured":"Gajanayake R, Hiras M, Gunathunga P, Janith\u00a0Supun EG, Karunasenna A, Bandara P (2020) Candidate Selection for the Interview using GitHub Profile and User Analysis for the Position of Software Engineer. In: Int. conf. on advancements in computing, pp 168\u2013173","DOI":"10.1109\/ICAC51239.2020.9357279"},{"key":"10608_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2023.103030","volume":"231","author":"J Giner-Miguelez","year":"2024","unstructured":"Giner-Miguelez J, G\u00f3mez A, Cabot J (2024) Describeml: A dataset description tool for machine learning. Sci Comput Program 231:103030","journal-title":"Sci Comput Program"},{"key":"10608_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.110911","volume":"175","author":"M Golzadeh","year":"2021","unstructured":"Golzadeh M, Decan A, Legay D, Mens T (2021) A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments. J Syst Softw 175:110911","journal-title":"J Syst Softw"},{"key":"10608_CR36","doi-asserted-by":"crossref","unstructured":"Gonzalez D, Zimmermann T, Nagappan N (2020) The State of the ML-universe: 10 Years of Artificial Intelligence & Machine Learning Software Development on GitHub. In: Int. conf. on mining software repositories, pp 431\u2013442","DOI":"10.1145\/3379597.3387473"},{"key":"10608_CR37","doi-asserted-by":"crossref","unstructured":"Gousios G, Spinellis D (2012) GHTorrent: Github\u2019s data from a firehose. In: Working conf. of mining software repositories, pp 12\u201321","DOI":"10.1109\/MSR.2012.6224294"},{"key":"10608_CR38","doi-asserted-by":"crossref","unstructured":"Gousios G, Pinzger M, van Deursen A (2014) An exploratory study of the pull-based software development model. In: Int. conf. on software engineering, pp 345\u2013355","DOI":"10.1145\/2568225.2568260"},{"key":"10608_CR39","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.dss.2010.12.010","volume":"51","author":"KL Gwebu","year":"2011","unstructured":"Gwebu KL, Wang J (2011) Adoption of Open Source Software: The role of social identification. Decis Support Syst 51:220\u2013229","journal-title":"Decis Support Syst"},{"key":"10608_CR40","doi-asserted-by":"crossref","unstructured":"Hauff C, Gousios G (2015) Matching GitHub developer profiles to job advertisements. In: Working conf. on mining software repositories, p 362-366","DOI":"10.1109\/MSR.2015.41"},{"issue":"8","key":"10608_CR41","doi-asserted-by":"publisher","first-page":"4004","DOI":"10.1109\/TSE.2023.3278129","volume":"49","author":"R He","year":"2023","unstructured":"He R, He H, Zhang Y, Zhou M (2023) Automating Dependency Updates in Practice: An Exploratory Study on GitHub Dependabot. IEEE Trans Softw Eng 49(8):4004\u20134022","journal-title":"IEEE Trans Softw Eng"},{"key":"10608_CR42","doi-asserted-by":"crossref","unstructured":"Hove SE, Anda B (2005) Experiences from Conducting Semi-structured Interviews in Empirical Software Engineering Research. In: Int. Symposium on Software Metrics, p\u00a023","DOI":"10.1109\/METRICS.2005.24"},{"key":"10608_CR43","doi-asserted-by":"crossref","unstructured":"Howison J, Crowston K (2004) The Perils and Pitfalls of Mining Sourceforge. In: Int. Workshop on Mining Software Repositories, pp 7\u201311","DOI":"10.1049\/ic:20040467"},{"key":"10608_CR44","doi-asserted-by":"crossref","unstructured":"Imtiaz N, Middleton J, Chakraborty J, Robson N, Bai GR, Murphy-Hill ER (2019) Investigating the effects of gender bias on GitHub. In: Int. Conf. on Software Engineering, pp 700\u2013711","DOI":"10.1109\/ICSE.2019.00079"},{"issue":"1","key":"10608_CR45","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s10664-021-10061-x","volume":"27","author":"JLC Izquierdo","year":"2022","unstructured":"Izquierdo JLC, Cabot J (2022) On the analysis of non-coding roles in open source development. Empir Softw Eng 27(1):18","journal-title":"Empir Softw Eng"},{"key":"10608_CR46","unstructured":"Jiang W, Cheung C, Thiruvathukal GK, Davis JC (2023a) Exploring Naming Conventions (and Defects) of Pre-trained Deep Learning Models in Hugging Face and Other Model Hubs. arXiv:2310.01642"},{"key":"10608_CR47","doi-asserted-by":"crossref","unstructured":"Jiang W, Synovic N, Hyatt M, Schorlemmer TR, Sethi R, Lu YH, Thiruvathukal GK, Davis JC (2023b) An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry. In: Int. conf. on software engineering, pp 2463\u20132475","DOI":"10.1109\/ICSE48619.2023.00206"},{"issue":"4","key":"10608_CR48","doi-asserted-by":"publisher","first-page":"396","DOI":"10.9734\/BJAST\/2015\/14975","volume":"7","author":"A Joshi","year":"2015","unstructured":"Joshi A, Kale S, Chandel S, Pal DK (2015) Likert scale: Explored and explained. British J Appl Sci Technol 7(4):396\u2013403","journal-title":"British J Appl Sci Technol"},{"key":"10608_CR49","doi-asserted-by":"crossref","unstructured":"Joshi SD, Chimalakonda S (2019) RapidRelease: A Dataset of Projects and Issues on Github with Rapid Releases. In: Int. conf. on mining software repositories, p 587-591","DOI":"10.1109\/MSR.2019.00088"},{"key":"10608_CR50","doi-asserted-by":"crossref","unstructured":"Kaide K, Tamada H (2022) Argo: Projects\u2019 Time-Series Data Fetching and Visualizing Tool for GitHub. In: Int. summer virtual conf. on software engineering, artificial intelligence, networking and parallel\/distributed computing, pp 141\u2013147","DOI":"10.1109\/SNPD-Summer57817.2022.00032"},{"key":"10608_CR51","doi-asserted-by":"crossref","unstructured":"Kalliamvakou E, Gousios G, Blincoe K, Singer L, Germ\u00e1n DM, Damian DE (2014) The Promises and Perils of Mining GitHub. In: Int. working conf. on mining software repositories, pp 92\u2013101","DOI":"10.1145\/2597073.2597074"},{"issue":"5","key":"10608_CR52","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1007\/s10664-015-9393-5","volume":"21","author":"E Kalliamvakou","year":"2016","unstructured":"Kalliamvakou E, Gousios G, Blincoe K, Singer L, Germ\u00e1n DM, Damian DE (2016) An In-depth Study of the Promises and Perils of Mining GitHub. Empir Softw Eng 21(5):2035\u20132071","journal-title":"Empir Softw Eng"},{"key":"10608_CR53","doi-asserted-by":"crossref","unstructured":"Kathikar A, Nair A, Lazarine B, Sachdeva A, Samtani S (2023) Assessing the vulnerabilities of the open-source artificial intelligence (AI) landscape: A large-scale analysis of the hugging face platform. In: Int. conf. on intelligence and security informatics, pp 1\u20136","DOI":"10.1109\/ISI58743.2023.10297271"},{"key":"10608_CR54","doi-asserted-by":"crossref","unstructured":"Kleinbaum DG, Klein M (2005) Survival Analysis: A Self-Learning Text. Springer Science and Business Media, LLC","DOI":"10.1007\/0-387-29150-4"},{"key":"10608_CR55","doi-asserted-by":"crossref","unstructured":"Kritikos A, Chatziasimidis F (2011) SFparser: A Tool for Selectively Parsing SourceForge. In: Panhellenic conf. on informatics, pp 161\u2013165","DOI":"10.1109\/PCI.2011.42"},{"key":"10608_CR56","doi-asserted-by":"crossref","unstructured":"Lazarine B, Zhang Z, Sachdeva A, Samtani S, Zhu H (2022) Exploring the Propagation of Vulnerabilities from GitHub Repositories Hosted by Major Technology Organizations. In: Workshop on cyber security experimentation and test, pp 145\u2013150","DOI":"10.1145\/3546096.3546114"},{"issue":"2","key":"10608_CR57","doi-asserted-by":"publisher","first-page":"144","DOI":"10.3390\/sym11020144","volume":"11","author":"Z Liao","year":"2019","unstructured":"Liao Z, Yi M, Wang Y, Liu S, Liu H, Zhang Y, Zhou Y (2019) Healthy or not: A way to predict ecosystem health in github. Symmetry 11(2):144","journal-title":"Symmetry"},{"key":"10608_CR58","doi-asserted-by":"crossref","unstructured":"Malan DJ (2022) Standardizing Students\u2019 Programming Environments with Docker Containers: Using Visual Studio Code in the Cloud with GitHub Codespaces. In: ACM Conf. on innovation and technology in computer science education, pp 599\u2013600","DOI":"10.1145\/3502717.3532164"},{"key":"10608_CR59","doi-asserted-by":"crossref","unstructured":"Mitchell M, Wu S, Zaldivar A, Barnes P, Vasserman L, Hutchinson B, Spitzer E, Raji ID, Gebru T (2019) Model cards for model reporting. In: Conf. on fairness, accountability, and transparency, pp 220\u2013229","DOI":"10.1145\/3287560.3287596"},{"key":"10608_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2020.106485","volume":"131","author":"JE Montandon","year":"2021","unstructured":"Montandon JE, Valente MT, Silva LL (2021) Mining the Technical Roles of GitHub Users. Inf Softw Technol 131:106485","journal-title":"Inf Softw Technol"},{"issue":"9","key":"10608_CR61","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1108\/IMDS-03-2019-0136","volume":"119","author":"W Mu","year":"2019","unstructured":"Mu W, Bian Y, Zhao JL (2019) The role of online leadership in open collaborative innovation. Ind Manag Data Syst 119(9):1969\u20131987","journal-title":"Ind Manag Data Syst"},{"key":"10608_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2023.101499","volume":"23","author":"Y \u00d6z\u00e7evik","year":"2023","unstructured":"\u00d6z\u00e7evik Y, Altay O (2023) MetricHunter: A software metric dataset generator utilizing SourceMonitor upon public GitHub repositories. SoftwareX 23:101499","journal-title":"SoftwareX"},{"key":"10608_CR63","doi-asserted-by":"crossref","unstructured":"Pina D, Goldman A, Seaman C (2022) Sonarlizer xplorer: a tool to mine github projects and identify technical debt items using SonarQube. In: Int. Conf. on Technical Debt, p 71-75","DOI":"10.1145\/3524843.3528098"},{"key":"10608_CR64","doi-asserted-by":"crossref","unstructured":"Qiu HS, Nolte A, Brown A, Serebrenik A, Vasilescu B (2019) Going farther together: the impact of social capital on sustained participation in open source. In: Int. conf. on software engineering, pp 688\u2013699","DOI":"10.1109\/ICSE.2019.00078"},{"key":"10608_CR65","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. In: Conf. on empirical methods in natural language processing, pp 3980\u20133990","DOI":"10.18653\/v1\/D19-1410"},{"key":"10608_CR66","doi-asserted-by":"crossref","unstructured":"Ren L, Zhou S, K\u00e4stner C (2018) Forks Insight: Providing an Overview of GitHub Forks. In: Int. conf. on software engineering: companion proceeedings, pp 179\u2013180","DOI":"10.1145\/3183440.3195085"},{"key":"10608_CR67","unstructured":"Rigney D (2010) The Matthew effect: How advantage begets further advantage. Columbia University Press"},{"key":"10608_CR68","doi-asserted-by":"crossref","unstructured":"Robles G (2010) Replicating MSR: a Study of the Potential Replicability of Papers Published in the Mining Software Repositories Proceedings. In: Int. working conf. on mining software repositories, pp 171\u2013180","DOI":"10.1109\/MSR.2010.5463348"},{"key":"10608_CR69","doi-asserted-by":"crossref","unstructured":"Robles G, Ho-Quang T, Hebig R, Chaudron MRV, Fernandez MA (2017) An Extensive Dataset of UML Models in GitHub. In: Int. conf. on mining software repositories, pp 519\u2013522","DOI":"10.1109\/MSR.2017.48"},{"key":"10608_CR70","doi-asserted-by":"crossref","unstructured":"Romano S, Caulo M, Buompastore M, Guerra L, Mounsif A, Telesca M, Baldassarre MT, Scanniello G (2021) G-Repo: a Tool to Support MSR Studies on GitHub. In: Int. Conf. on software analysis, evolution and reengineering, pp 551\u2013555","DOI":"10.1109\/SANER50967.2021.00064"},{"key":"10608_CR71","doi-asserted-by":"crossref","unstructured":"Safari H, Sabri N, Shahsavan F, Bahrak B (2020) An Analysis of GitLab\u2019s Users and Projects Networks. In: Int. Symposium onTelecommunications, pp 194\u2013200","DOI":"10.1109\/IST50524.2020.9345844"},{"key":"10608_CR72","doi-asserted-by":"crossref","unstructured":"Sanh V, Wolf T, Ruder S (2019) A Hierarchical Multi-Task Approach for Learning Embeddings from Semantic Tasks. In: Conf. on artificial intelligence, pp 6949\u20136956","DOI":"10.1609\/aaai.v33i01.33016949"},{"key":"10608_CR73","doi-asserted-by":"crossref","unstructured":"Souza I, Campello L, Rodrigues E, Guedes G, Bernardino M (2021) An Analysis of Automated Code Inspection Tools for Php Available on GitHub Marketplace. In: Symp. on systematic and automated software, pp 10\u201317","DOI":"10.1145\/3482909.3482912"},{"key":"10608_CR74","doi-asserted-by":"crossref","unstructured":"Spinellis D, Kotti Z, Mockus A (2020) A Dataset for GitHub Repository Deduplication. In: Int. conf. on mining software repositories, pp 523\u2013527","DOI":"10.1145\/3379597.3387496"},{"key":"10608_CR75","doi-asserted-by":"crossref","unstructured":"Squire M (2017) The Lives and Deaths of Open Source Code Forges. In: Int. symposium on open collaboration, opensym, pp 15:1\u201315:8","DOI":"10.1145\/3125433.3125468"},{"key":"10608_CR76","doi-asserted-by":"crossref","unstructured":"Tsay J, Dabbish L, Herbsleb J (2014) Let\u2019s Talk about It: Evaluating Contributions through Discussion in GitHub. In: ACM SIGSOFT Int. symposium on foundations of software engineering, pp 144\u2013154","DOI":"10.1145\/2635868.2635882"},{"key":"10608_CR77","doi-asserted-by":"crossref","unstructured":"Valenzuela-Toledo P, Bergel A, Kehrer T, Nierstrasz O (2023) EGAD: A moldable tool for GitHub Action analysis. In: Int. conf. on mining software repositories, pp 260\u2013264","DOI":"10.1109\/MSR59073.2023.00044"},{"key":"10608_CR78","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2022.121478","volume":"176","author":"J Wachs","year":"2022","unstructured":"Wachs J, Nitecki M, Schueller W, Polleres A (2022) The Geography of Open Source Software: Evidence from GitHub. Technological Forecasting Social Change 176:121478","journal-title":"Technological Forecasting Social Change"},{"key":"10608_CR79","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2022.106845","volume":"145","author":"J Wang","year":"2022","unstructured":"Wang J, Zhang X, Chen L, Xie X (2022) Personalizing label prediction for GitHub issues. Inf Soft Technol 145:106845","journal-title":"Inf Soft Technol"},{"key":"10608_CR80","doi-asserted-by":"crossref","unstructured":"Wessel M, Serebrenik A, Wiese I, Steinmacher I, Gerosa MA (2020) What to Expect from Code Review Bots on GitHub? A Survey with OSS Maintainers. In: Brazilian symposium on software engineering, pp 457\u2013462","DOI":"10.1145\/3422392.3422459"},{"key":"10608_CR81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29044-2","volume-title":"Experimentation in Software Engineering","author":"C Wohlin","year":"2012","unstructured":"Wohlin C, Runeson P, H\u00f6st M, Ohlsson MC, Regnell B (2012) Experimentation in Software Engineering. Springer"},{"key":"10608_CR82","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, Davison J, Shleifer S, von Platen P, Ma C, Jernite Y, Plu J, Xu C, Scao TL, Gugger S, Drame M, Lhoest Q, Rush AM (2020) Transformers: State-of-the-Art Natural Language Processing. In: Conf. on empirical methods in natural language processing, pp 38\u201345","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"10608_CR83","doi-asserted-by":"crossref","unstructured":"Wolter T, Barcomb A, Riehle D, Harutyunyan N (2023) Open Source License Inconsistencies on GitHub. ACM Trans Softw Eng Methodol 32(5)","DOI":"10.1145\/3571852"},{"key":"10608_CR84","doi-asserted-by":"crossref","unstructured":"Wu J, He H, Xiao W, Gao K, Zhou M (2022) Demystifying Software Release Note Issues on GitHub. In: Int. conf. on program comprehension, pp 602\u2013613","DOI":"10.1145\/3524610.3527919"},{"key":"10608_CR85","unstructured":"Yang X, Liang W, Zou J (2024) Navigating dataset documentations in AI: A large-scale analysis of dataset cards on hugging face. arXiv:2401.13822"},{"key":"10608_CR86","unstructured":"You K, Liu Y, Zhang Z, Wang J, Jordan MI, Long M (2022) Ranking and tuning pre-trained models: A new paradigm for exploiting model hubs. J Mach Learn Res 23:209:1\u2013209:47"},{"key":"10608_CR87","doi-asserted-by":"crossref","unstructured":"Yu Y, Yin G, Wang H, Wang T (2014) Exploring the patterns of social behavior in GitHub. In: Int. workshop on crowd-based software development methods and technologies, pp 31\u201336","DOI":"10.1145\/2666539.2666571"},{"key":"10608_CR88","doi-asserted-by":"crossref","unstructured":"Yu Y, Wang H, Filkov V, Devanbu P, Vasilescu B (2015) Wait for It: Determinants of Pull Request Evaluation Latency on GitHub. In: Working conf. on mining software repositories, pp 367\u2013371","DOI":"10.1109\/MSR.2015.42"},{"key":"10608_CR89","doi-asserted-by":"crossref","unstructured":"Yu Y, Li Z, Yin G, Wang T, Wang H (2018) A Dataset of Duplicate Pull-Requests in Github. In: Int. Conf. on Mining Software Repositories, p 22-25","DOI":"10.1145\/3196398.3196455"},{"key":"10608_CR90","doi-asserted-by":"crossref","unstructured":"Zou W, Zhang W, Xia X, Holmes R, Chen Z (2019) Branch Use in Practice: A Large-Scale Empirical Study of 2,923 Projects on GitHub. In: Int. conf. on software quality, reliability and security, pp 306\u2013317","DOI":"10.1109\/QRS.2019.00047"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10608-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-024-10608-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10608-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:46:01Z","timestamp":1746193561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-024-10608-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,18]]},"references-count":90,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10608"],"URL":"https:\/\/doi.org\/10.1007\/s10664-024-10608-8","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,18]]},"assertion":[{"value":"16 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interests"}}],"article-number":"57"}}