{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:42:05Z","timestamp":1787017325440,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1145\/3524842.3528491","type":"proceedings-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T20:08:36Z","timestamp":1666037316000},"page":"757-761","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["A large-scale dataset of (open source) license text variants"],"prefix":"10.1145","author":[{"given":"Stefano","family":"Zacchiroli","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion52605.2021.00032"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054827"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016-9461-5"},{"key":"e_1_3_2_1_5_1","unstructured":"Yann Collet. 2021. RFC 8878 - Zstandard Compression and the \"application\/zstd\" Media Type. https:\/\/datatracker.ietf.org\/doc\/html\/rfc8878 Accessed 2022-01-24.  Yann Collet. 2021. RFC 8878 - Zstandard Compression and the \"application\/zstd\" Media Type. https:\/\/datatracker.ietf.org\/doc\/html\/rfc8878 Accessed 2022-01-24."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.17605\/OSF.IO\/KDE56"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 14th International Conference on Digital Preservation, iPRES","author":"Cosmo Roberto Di","year":"2017","unstructured":"Roberto Di Cosmo and Stefano Zacchiroli . 2017 . Software Heritage: Why and How to Preserve Software Source Code . In Proceedings of the 14th International Conference on Digital Preservation, iPRES 2017. https:\/\/hal.archives-ouvertes.fr\/hal-01590958\/ Roberto Di Cosmo and Stefano Zacchiroli. 2017. Software Heritage: Why and How to Preserve Software Source Code. In Proceedings of the 14th International Conference on Digital Preservation, iPRES 2017. https:\/\/hal.archives-ouvertes.fr\/hal-01590958\/"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3148330.3148333"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2012.50"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1370750.1370763"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2012.6224294"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.2983530"},{"key":"e_1_3_2_1_13_1","volume-title":"Intellectual property and open source: a practical guide to protecting code","author":"Lindberg Van","unstructured":"Van Lindberg . 2008. Intellectual property and open source: a practical guide to protecting code . O'Reilly Media, Inc. Van Lindberg. 2008. Intellectual property and open source: a practical guide to protecting code. O'Reilly Media, Inc."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09905-9"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1862372.1862391"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-17837-0_14"},{"key":"e_1_3_2_1_17_1","unstructured":"Wes McKinney etal 2011. pandas: a foundational Python library for data analysis and statistics. Python for high performance and scientific computing 14 9 (2011) 1--9.  Wes McKinney et al. 2011. pandas: a foundational Python library for data analysis and statistics. Python for high performance and scientific computing 14 9 (2011) 1--9."},{"key":"e_1_3_2_1_18_1","unstructured":"nexB. 2022. ScanCode. https:\/\/www.aboutcode.org\/projects\/scancode.html Accessed 2022-01-25.  nexB. 2022. ScanCode. https:\/\/www.aboutcode.org\/projects\/scancode.html Accessed 2022-01-25."},{"key":"e_1_3_2_1_19_1","unstructured":"nexB. 2022. ScanCode LicenseDB. https:\/\/scancode-licensedb.aboutcode.org\/ Accessed 2022-01-26.  nexB. 2022. ScanCode LicenseDB. https:\/\/scancode-licensedb.aboutcode.org\/ Accessed 2022-01-26."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CTC.2013.9"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3011082"},{"key":"e_1_3_2_1_22_1","unstructured":"Open Source Initiative. 2022. Machine readable OSI license information. https:\/\/github.com\/OpenSourceOrg\/licenses\/ Accessed 2022-01-26.  Open Source Initiative. 2022. Machine readable OSI license information. https:\/\/github.com\/OpenSourceOrg\/licenses\/ Accessed 2022-01-26."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3024403"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00030"},{"key":"e_1_3_2_1_25_1","volume-title":"Open source licensing","author":"Rosen Lawrence","unstructured":"Lawrence Rosen . 2005. Open source licensing . Vol. 692 . Prentice Hall . Lawrence Rosen. 2005. Open source licensing. Vol. 692. Prentice Hall."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09828-5"},{"key":"e_1_3_2_1_27_1","unstructured":"Yakov Shafranovich. 2005. RFC 4180 - Common Format and MIME Type for Comma-Separated Values (CSV) Files. https:\/\/datatracker.ietf.org\/doc\/html\/rfc4180 Accessed 2022-01-24.  Yakov Shafranovich. 2005. RFC 4180 - Common Format and MIME Type for Comma-Separated Values (CSV) Files. https:\/\/datatracker.ietf.org\/doc\/html\/rfc4180 Accessed 2022-01-24."},{"key":"e_1_3_2_1_28_1","volume-title":"Software Package Data Exchange Licence List. https:\/\/spdx.org\/license-list https:\/\/spdx.org\/license-list, retrieved","author":"Workgroup SPDX","year":"2020","unstructured":"SPDX Workgroup . 2019. Software Package Data Exchange Licence List. https:\/\/spdx.org\/license-list https:\/\/spdx.org\/license-list, retrieved 30 March 2020 . SPDX Workgroup. 2019. Software Package Data Exchange Licence List. https:\/\/spdx.org\/license-list https:\/\/spdx.org\/license-list, retrieved 30 March 2020."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5033\/ifosslr.v4i1.45"},{"key":"e_1_3_2_1_31_1","unstructured":"The Open Group. 2018. file: determine file type. https:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/utilities\/file.html Accessed 2022-01-25.  The Open Group. 2018. file: determine file type. https:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/utilities\/file.html Accessed 2022-01-25."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016-9438-4"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.19"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6379164"}],"event":{"name":"MSR '22: 19th International Conference on Mining Software Repositories","location":"Pittsburgh Pennsylvania","acronym":"MSR '22","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 19th International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524842.3528491","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524842.3528491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:09:35Z","timestamp":1750169375000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524842.3528491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"alternative-id":["10.1145\/3524842.3528491","10.1145\/3524842"],"URL":"https:\/\/doi.org\/10.1145\/3524842.3528491","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}