{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:03:09Z","timestamp":1775815389357,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"AI Singapore","award":["AISG2-RP-2020-018"],"award-info":[{"award-number":["AISG2-RP-2020-018"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645520","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"1158-1169","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ModelGo: A Practical Tool for Machine Learning License Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5402-6634","authenticated-orcid":false,"given":"Moming","family":"Duan","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6539-6443","authenticated-orcid":false,"given":"Qinbin","family":"Li","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8618-4581","authenticated-orcid":false,"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2017.7"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_2_3_1","volume-title":"Towards standardization of data licenses: The montreal data license. arXiv preprint arXiv:1903.12262","author":"Benjamin Misha","year":"2019","unstructured":"Misha Benjamin, Paul Gagnon, Negar Rostamzadeh, Chris Pal, Yoshua Bengio, and Alex Shee. 2019. Towards standardization of data licenses: The montreal data license. arXiv preprint arXiv:1903.12262 (2019)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528004"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833747"},{"key":"e_1_3_2_2_7_1","volume-title":"2023 a. Artificial intelligence and CC licenses. https:\/\/creativecommons.org\/faq\/#artificial-intelligence-and-cc-licenses Retrieved","author":"Commons Creative","year":"2023","unstructured":"Creative Commons. 2023 a. Artificial intelligence and CC licenses. https:\/\/creativecommons.org\/faq\/#artificial-intelligence-and-cc-licenses Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_8_1","volume-title":"2023 b. Creative Commons Licenses List. https:\/\/creativecommons.org\/licenses\/ Retrieved","author":"Commons Creative","year":"2023","unstructured":"Creative Commons. 2023 b. Creative Commons Licenses List. https:\/\/creativecommons.org\/licenses\/ Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533143"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00050"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19--1423"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML). PMLR, 1607--1616","author":"Furlanello Tommaso","year":"2018","unstructured":"Tommaso Furlanello, Zachary Lipton, Michael Tschannen, Laurent Itti, and Anima Anandkumar. 2018. Born again neural networks. In Proceedings of the 35th International Conference on Machine Learning (ICML). PMLR, 1607--1616."},{"key":"e_1_3_2_2_13_1","volume-title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027","author":"Gao Leo","year":"2020","unstructured":"Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027 (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1858996.1859088"},{"key":"e_1_3_2_2_15_1","volume-title":"Vision models are more robust and fair when pretrained on uncurated images without supervision. arXiv preprint arXiv:2202.08360","author":"Goyal Priya","year":"2022","unstructured":"Priya Goyal, Quentin Duval, Isaac Seessel, Mathilde Caron, Mannat Singh, Ishan Misra, Levent Sagun, Armand Joulin, and Piotr Bojanowski. 2022. Vision models are more robust and fair when pretrained on uncurated images without supervision. arXiv preprint arXiv:2202.08360 (2022)."},{"key":"e_1_3_2_2_16_1","first-page":"1297","article-title":"The Non-Discrimination Principle in Open Source Licensing","volume":"37","author":"Greenbaum Eli","year":"2016","unstructured":"Eli Greenbaum. 2016. The Non-Discrimination Principle in Open Source Licensing. Cardozo Law Review, Vol. 37, 4 (2016), 1297--1344.","journal-title":"Cardozo Law Review"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"e_1_3_2_2_20_1","first-page":"324","article-title":"I Think, Therefore I Create: Claiming Copyright in the Outputs of Algorithms","volume":"8","author":"Hedrick Samantha Fink","year":"2019","unstructured":"Samantha Fink Hedrick. 2019. I Think, Therefore I Create: Claiming Copyright in the Outputs of Algorithms. New York University Journal of Intellectual Property & Entertainment Law (JIPEL), Vol. 8, 2 (2019), 324--375.","journal-title":"New York University Journal of Intellectual Property & Entertainment Law (JIPEL)"},{"key":"e_1_3_2_2_21_1","volume-title":"Foundation models and fair use. arXiv preprint arXiv:2303.15715","author":"Henderson Peter","year":"2023","unstructured":"Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, and Percy Liang. 2023. Foundation models and fair use. arXiv preprint arXiv:2303.15715 (2023)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5033\/ifosslr.v9i1.123"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00206"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2016.06.064"},{"key":"e_1_3_2_2_27_1","volume-title":"Jia Li, Chenghao Mou, Carlos Mu noz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, et al.","author":"Kocetkov Denis","year":"2023","unstructured":"Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Mu noz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, et al. 2023. The Stack: 3 TB of permissively licensed source code. Transactions on Machine Learning Research (TMLR) (2023)."},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML). PMLR, 5948--5958","author":"Lam Thanh Chi","year":"2021","unstructured":"Thanh Chi Lam, Nghia Hoang, Bryan Kian Hsiang Low, and Patrick Jaillet. 2021. Model Fusion for Personalized Learning. In Proceedings of the 38th International Conference on Machine Learning (ICML). PMLR, 5948--5958."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"e_1_3_2_2_30_1","volume-title":"https:\/\/huggingface.co\/dreamlike-art\/dreamlike-photoreal-2.0 Retrieved","author":"Ltd Dreamlike Tech","year":"2023","unstructured":"Dreamlike Tech Ltd. 2023. Dreamlike Photoreal 2.0. https:\/\/huggingface.co\/dreamlike-art\/dreamlike-photoreal-2.0 Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3299523"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEW.2012.24"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS). 1273--1282","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS). 1273--1282."},{"key":"e_1_3_2_2_34_1","volume-title":"Llama2 Community License. https:\/\/ai.meta.com\/llama\/license\/ Retrieved","author":"Inc. Meta Platforms. 2023.","year":"2023","unstructured":"Inc. Meta Platforms. 2023. Llama2 Community License. https:\/\/ai.meta.com\/llama\/license\/ Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3011082"},{"key":"e_1_3_2_2_36_1","volume-title":"July 31, 1978. Library of Congress.","author":"National Commission on New Technological Uses of Copyrighted Works (US).","year":"1979","unstructured":"National Commission on New Technological Uses of Copyrighted Works (US). 1979. Final Report of the National Commission on New Technological Uses of Copyrighted Works, July 31, 1978. Library of Congress."},{"key":"e_1_3_2_2_37_1","volume-title":"The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116","author":"Penedo Guilherme","year":"2023","unstructured":"Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01113--3"},{"key":"e_1_3_2_2_39_1","volume-title":"The open source definition. Open sources: voices from the open source revolution","author":"Perens Bruce","year":"1999","unstructured":"Bruce Perens. 1999. The open source definition. Open sources: voices from the open source revolution , Vol. 1 (1999), 171--188."},{"key":"e_1_3_2_2_40_1","volume-title":"Midjourney's Terms of Service. https:\/\/docs.midjourney.com\/docs\/terms-of-service Retrieved","author":"Midjourney","year":"2023","unstructured":"Midjourney platform. 2023. Midjourney's Terms of Service. https:\/\/docs.midjourney.com\/docs\/terms-of-service Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_41_1","volume-title":"Openjourney v4. https:\/\/www.openjourney.art\/ Retrieved","year":"2023","unstructured":"PromptHero. 2023. Openjourney v4. https:\/\/www.openjourney.art\/ Retrieved September 25, 2023 from"},{"key":"e_1_3_2_2_42_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_2_43_1","unstructured":"Gopi Krishnan Rajbahadur Erika Tuck Li Zi Dayi Lin Boyuan Chen Zhen Ming Daniel M German et al. 2021. Can I use this publicly available dataset to build commercial AI software?--A Case Study on Publicly Available Image Datasets. arXiv preprint arXiv:2111.02374 (2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_45_1","volume-title":"Open Source Licensing: Software Freedom and Intellectual Property Law","author":"Rosen Lawrence","unstructured":"Lawrence Rosen. 2005. Open Source Licensing: Software Freedom and Intellectual Property Law. Prentice Hall Professional Technical Reference, New Jersey."},{"key":"e_1_3_2_2_46_1","volume-title":"Francc ois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Francc ois Yvon, Matthias Gall\u00e9, et al. 2022. BLOOM: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_2_47_1","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems (NeurIPS) , Vol. 35 (2022), 25278--25294.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"e_1_3_2_2_49_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.19"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587345"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2015.37"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016--9487--8"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3469471"},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of the 11th International Conference on Learning Representations (ICLR).","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et al. 2023. GLM-130B: An Open Bilingual Pre-trained Model. Proceedings of the 11th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_57_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR). io","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In Proceedings of the 6th International Conference on Learning Representations (ICLR). io"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645520","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:23:32Z","timestamp":1755822212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":57,"alternative-id":["10.1145\/3589334.3645520","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645520","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}