{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:07:10Z","timestamp":1784653630629,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MICIU\/AEI\/10.13039\/501100011033 and ERDF, EU","award":["PID2024-156019OB-I00"],"award-info":[{"award-number":["PID2024-156019OB-I00"]}]},{"name":"Generalitat de Catalunya, Department of Research and Universities (Departament de Recerca i Universitats), via AGAUR, FI-STEP programme, co-funded by the European Social Fund Plus (FSE+)","award":["2025 STEP-00407"],"award-info":[{"award-number":["2025 STEP-00407"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3793655.3793717","type":"proceedings-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:04:46Z","timestamp":1784649886000},"page":"238-242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SEMODS: A Validated Dataset of Open-Source Software Engineering Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7634-0343","authenticated-orcid":false,"given":"Alexandra","family":"Gonz\u00e1lez","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC), Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9733-8830","authenticated-orcid":false,"given":"Xavier","family":"Franch","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC), Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9928-133X","authenticated-orcid":false,"given":"Silverio","family":"Mart\u00ednez-Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC), Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"GitHub Models - GitHub Docs \u2014 docs.github.com. https:\/\/docs.github.com\/en\/github-models. [Accessed 03-11-2025]."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Ait A. Izquierdo J. L.\u00a0C. and Cabot J. HFCommunity: A Tool to Analyze the Hugging Face Hub Community. In 2023 IEEE International Conference on Software Analysis Evolution and Reengineering (SANER) (2023) pp.\u00a0728\u2013732.","DOI":"10.1109\/SANER56733.2023.00080"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Ait A. Izquierdo J. L.\u00a0C. and Cabot J. HFCommunity: An extraction process and relational database to analyze Hugging Face Hub data. Science of Computer Programming 234 (2024) 103079.","DOI":"10.1016\/j.scico.2024.103079"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Ajibode A. Bangash A.\u00a0A. Cogo F.\u00a0R. Adams B. and Hassan A.\u00a0E. Towards semantic versioning of open pre-trained language model releases on hugging face. Empirical Software Engineering 30 3 (2025) 1\u201363.","DOI":"10.1007\/s10664-025-10631-3"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Amershi S. Begel A. Bird C. DeLine R. Gall H. Kamar E. Nagappan N. Nushi B. and Zimmermann T. Software Engineering for Machine Learning: A Case Study. In 2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) (2019) pp.\u00a0291\u2013300.","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_3_1_7_2","unstructured":"Austin J. Odena A. Nye M. Bosma M. Michalewski H. Dohan D. Jiang E. Cai C. Terry M. Le Q. et\u00a0al. Program synthesis with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.07732 (2021)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Casta\u00f1o J. Mart\u00ednez-Fern\u00e1ndez S. Franch X. and Bogner J. Analyzing the evolution and maintenance of ml models on hugging face. In Proceedings of the 21st International Conference on Mining Software Repositories (New York NY USA 2024) MSR \u201924 Association for Computing Machinery p.\u00a0607\u2013618.","DOI":"10.1145\/3643991.3644898"},{"key":"e_1_3_3_1_9_2","unstructured":"Chen M. Evaluating large language models trained on code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Davis J.\u00a0C. Jajal P. Jiang W. Schorlemmer T.\u00a0R. Synovic N. and Thiruvathukal G.\u00a0K. Reusing deep learning models: Challenges and directions in software engineering. In 2023 IEEE John Vincent Atanasoff International Symposium on Modern Computing (JVA) (2023) IEEE pp.\u00a017\u201330.","DOI":"10.1109\/JVA60410.2023.00015"},{"key":"e_1_3_3_1_11_2","unstructured":"Delangue C. We just crossed 1 500 000 public models on Hugging Face \u2014 linkedin.com. https:\/\/huggingface.co\/posts\/clem\/238420842235482\/. [Accessed 29-05-2025]."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Di\u00a0Sipio C. Rubei R. Di\u00a0Rocco J. Di\u00a0Ruscio D. and Nguyen P.\u00a0T. Automated categorization of pre-trained models in software engineering: A case study with a Hugging Face dataset. In Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering (New York NY USA 2024) EASE \u201924 Association for Computing Machinery p.\u00a0351\u2013356.","DOI":"10.1145\/3661167.3661215"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Giray G. A software engineering perspective on engineering machine learning systems: State of the art and challenges. JSS 180 (2021) 111031.","DOI":"10.1016\/j.jss.2021.111031"},{"key":"e_1_3_3_1_14_2","unstructured":"Gonz\u00e1lez A. Franch X. Lo D. and Mart\u00ednez-Fern\u00e1ndez S. Cataloguing Hugging Face Models to Software Engineering Activities: Automation and Findings. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.03013 (2025)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez A. Franch X. and Mart\u00ednez-Fern\u00e1ndez S. Replication Package for \"SEMODS: A Validated Dataset of Open-Source Software Engineering Models\". 10.5281\/zenodo.17674908 Nov. 2025.","DOI":"10.5281\/zenodo.17674908,"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez A. Franch X. and Mart\u00ednez-Fern\u00e1ndez S. SEMODS: A Validated Dataset of Open-Source Software Engineering Models (November 2025 Snapshot) \u2014 zenodo.org. 10.5281\/zenodo.17675255 Nov. 2025.","DOI":"10.5281\/zenodo.17675255,"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Han X. Zhang Z. Ding N. Gu Y. Liu X. Huo Y. Qiu J. Yao Y. Zhang A. Zhang L. et\u00a0al. Pre-trained models: Past present and future. AI Open 2 (2021) 225\u2013250.","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_3_3_1_18_2","unstructured":"Hiroyasu\u00a0Washizaki e.Guide to the Software Engineering Body of Knowledge (SWEBOK Guide) Version 4.0. IEEE Computer Society 2024."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Hou X. Zhao Y. Liu Y. Yang Z. Wang K. Li L. Luo X. Lo D. Grundy J. and Wang H. Large Language Models for Software Engineering: A Systematic Literature Review. ACM Trans. Softw. Eng. Methodol. (Sept. 2024). Just Accepted.","DOI":"10.1145\/3695988"},{"key":"e_1_3_3_1_20_2","unstructured":"Hugging Face. Hugging Face \u2013 The AI community building the future. \u2014 huggingface.co. https:\/\/huggingface.co [n.d.]. [Accessed: 30-10-2025]."},{"key":"e_1_3_3_1_21_2","unstructured":"Hugging Face Inc. Model Cards - Linking a Paper \u2014 huggingface.co. https:\/\/huggingface.co\/docs\/hub\/model-cards#linking-a-paper. [Accessed 30-10-2025]."},{"key":"e_1_3_3_1_22_2","unstructured":"Hugging Face Inc. Model Cards - Model card metadata \u2014 huggingface.co. https:\/\/huggingface.co\/docs\/hub\/model-cards#model-card-metadata. [Accessed 30-10-2025]."},{"key":"e_1_3_3_1_23_2","unstructured":"Hugging Face Inc. Hugging Face Hub documentation \u2014 huggingface.co. https:\/\/huggingface.co\/docs\/hub\/index [n.d.]. [Accessed 30-10-2025]."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Jiang W. Synovic N. Hyatt M. Schorlemmer T.\u00a0R. Sethi R. Lu Y.-H. Thiruvathukal G.\u00a0K. and Davis J.\u00a0C. An empirical study of pre-trained model reuse in the hugging face deep learning model registry. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE) (2023) IEEE pp.\u00a02463\u20132475.","DOI":"10.1109\/ICSE48619.2023.00206"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Jiang W. Synovic N. Jajal P. Schorlemmer T.\u00a0R. Tewari A. Pareek B. Thiruvathukal G.\u00a0K. and Davis J.\u00a0C. Ptmtorrent: A dataset for mining open-source pre-trained model packages. In 2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR) (2023) IEEE pp.\u00a057\u201361.","DOI":"10.1109\/MSR59073.2023.00021"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jiang W. Yasmin J. Jones J. Synovic N. Kuo J. Bielanski N. Tian Y. Thiruvathukal G.\u00a0K. and Davis J.\u00a0C. Peatmoss: A dataset and initial analysis of pre-trained models in open-source software. In Proceedings of the 21st International Conference on Mining Software Repositories (2024) pp.\u00a0431\u2013443.","DOI":"10.1145\/3643991.3644907"},{"key":"e_1_3_3_1_27_2","unstructured":"Koohjani M. and Costa D.\u00a0E. Exploring the Lifecycle and Maintenance Practices of Pre-Trained Models in Open-Source Software Repositories. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.06040 (2025)."},{"key":"e_1_3_3_1_28_2","unstructured":"Laufer B. Oderinwale H. and Kleinberg J. Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.06811 (2025)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Mitchell M. Wu S. Zaldivar A. Barnes P. Vasserman L. Hutchinson B. Spitzer E. Raji I.\u00a0D. and Gebru T. Model cards for model reporting. In Proceedings of the conference on fairness accountability and transparency (2019) pp.\u00a0220\u2013229.","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"O\u2019Connor C. and Joffe H. Intercoder reliability in qualitative research: debates and practical guidelines. International journal of qualitative methods 19 (2020) 1609406919899220.","DOI":"10.1177\/1609406919899220"},{"key":"e_1_3_3_1_31_2","unstructured":"PyTorch Foundation. PyTorch Hub \u2014 pytorch.org. https:\/\/pytorch.org\/hub\/ [n.d.]. [Accessed 03-11-2025]."},{"key":"e_1_3_3_1_32_2","unstructured":"Qualtrics. Sample Size Calculator - Qualtrics \u2014 qualtrics.com. https:\/\/www.qualtrics.com\/blog\/calculating-sample-size\/. [Accessed 21-05-2025]."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Sim J. and Wright C.\u00a0C. The kappa statistic in reliability studies: use interpretation and sample size requirements. Physical therapy 85 3 (2005) 257\u2013268.","DOI":"10.1093\/ptj\/85.3.257"},{"key":"e_1_3_3_1_34_2","unstructured":"Sommerville I.Software Engineering 10\u00a0ed. Pearson 2015."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Suryani M.\u00a0A. Karmakar S. and Mathiak B. Exploration of Hugging Face Models by Heterogeneous Information Network and Linking Across Scholarly Repositories. In International Conference on Advances in Social Networks Analysis and Mining (2024) Springer pp.\u00a0371\u2013386.","DOI":"10.1007\/978-3-031-78548-1_27"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Suryani M.\u00a0A. Karmakar S. Mathiak B. and Mayr P. Model Card Metadata Collection from Hugging Face to Foster Multidisciplinary AI Research: A Dataset. In Proceedings of the 14th International Conference on Data Science Technology and Applications (2025) pp.\u00a0583\u2013590.","DOI":"10.5220\/0013571800003967"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Tan X. Li T. Chen R. Liu F. and Zhang L. Challenges of Using Pre-trained Models: the Practitioners\u2019 Perspective. In SANER\u201924 (2024) IEEE pp.\u00a067\u201378.","DOI":"10.1109\/SANER60148.2024.00015"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Zhao Z. Chen Y. Bangash A.\u00a0A. Adams B. and Hassan A.\u00a0E. An empirical study of challenges in machine learning asset management. Empirical Software Engineering 29 4 (2024) 98.","DOI":"10.1007\/s10664-024-10474-4"},{"key":"e_1_3_3_1_39_2","unstructured":"Zhou D.-W. and Ye H.-J. A Unifying Perspective on Model Reuse: From Small to Large Pre-Trained Models."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Zhuang F. Qi Z. Duan K. Xi D. Zhu Y. Zhu H. Xiong H. and He Q. A comprehensive survey on transfer learning. Proceedings of the IEEE 109 1 (2020) 43\u201376.","DOI":"10.1109\/JPROC.2020.3004555"}],"event":{"name":"FORGE '26: IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering","location":"Rio de Janeiro , Brazil","acronym":"FORGE '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793655.3793717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:49:01Z","timestamp":1784652541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793655.3793717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":39,"alternative-id":["10.1145\/3793655.3793717","10.1145\/3793655"],"URL":"https:\/\/doi.org\/10.1145\/3793655.3793717","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}