{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T21:02:57Z","timestamp":1765486977714,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s10664-023-10377-w","type":"journal-article","created":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T11:02:28Z","timestamp":1699441348000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The software heritage license dataset (2022 edition)"],"prefix":"10.1007","volume":"28","author":[{"given":"Jesus M.","family":"Gonzalez-Barahona","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Montes-Leon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregorio","family":"Robles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4576-136X","authenticated-orcid":false,"given":"Stefano","family":"Zacchiroli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,8]]},"reference":[{"issue":"10","key":"10377_CR1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/3183558","volume":"61","author":"JF Abramatic","year":"2018","unstructured":"Abramatic JF, Di Cosmo R, Zacchiroli S (2018) Building the universal archive of source code. Communications of the ACM 61(10):29\u201331","journal-title":"Communications of the ACM"},{"doi-asserted-by":"crossref","unstructured":"Allan\u00e7on T, A Pietri, S Zacchiroli (2021) The software heritage filesystem (swhfs): Integrating source code archival with development. In 43rd IEEE\/ACM International Conference on Software Engineering: Companion Proceedings, ICSE Companion 2021, Madrid, Spain, May 25-28, 2021, pages 45\u201348. IEEE","key":"10377_CR2","DOI":"10.1109\/ICSE-Companion52605.2021.00032"},{"unstructured":"Bird S (2006) NLTK: the natural language toolkit. In Nicoletta Calzolari, Claire Cardie, and Pierre Isabelle, editors, ACL 2006, 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Sydney, Australia, 17-21 July 2006. The Association for Computer Linguistics","key":"10377_CR3"},{"doi-asserted-by":"crossref","unstructured":"Boldi P, Pietri A, Vigna S, Zacchiroli S (2020) Ultra-large-scale repository analysis via graph compression. In SANER 2020: The 27th IEEE International Conference on Software Analysis, Evolution and Reengineering. IEEE, 2020","key":"10377_CR4","DOI":"10.1109\/SANER48275.2020.9054827"},{"key":"10377_CR5","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1007\/s10664-016-9461-5","volume":"22","author":"M Caneill","year":"2017","unstructured":"Caneill M, Germ\u00e1n DM, Zacchiroli S (2017) The debsources dataset: Two decades of free and open source software. Empirical Software Engineering 22:1405\u20131437","journal-title":"Empirical Software Engineering"},{"unstructured":"ClearlyDefined (2023) ClearlyDefined, 2023. https:\/\/clearlydefined.io. Accessed 2023-05-08","key":"10377_CR6"},{"doi-asserted-by":"crossref","unstructured":"Collet Y (2022) RFC 8878 - Zstandard compression and the \u201capplication\/zstd\u201d media type, 2021. Accessed 2022-01-24","key":"10377_CR7","DOI":"10.17487\/RFC8878"},{"unstructured":"Di\u00a0Cosmo R, Gruenpeter M, Zacchiroli S (2018) Identifiers for digital objects: the case of software source code preservation. In Proceedings of the 15th International Conference on Digital Preservation, iPRES 2018, Boston, USA","key":"10377_CR8"},{"unstructured":"Di\u00a0Cosmo R, Zacchiroli S (2017) Software Heritage: Why and how to preserve software source code. In Proceedings of the 14th International Conference on Digital Preservation, iPRES 2017","key":"10377_CR9"},{"doi-asserted-by":"crossref","unstructured":"Di\u00a0Penta M, German DM, Ga\u00ebl Gu\u00e9h\u00e9neuc Y, Antoniol G (2010) An exploratory study of the evolution of software licensing. In Proceedings of the 32nd ACM\/IEEE International Conference on Software Engineering - Volume 1, ICSE \u201910, page 145-154, New York, NY, USA, 2010. Association for Computing Machinery","key":"10377_CR10","DOI":"10.1145\/1806799.1806824"},{"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):7:1\u20137:34","key":"10377_CR11","DOI":"10.1145\/2803171"},{"doi-asserted-by":"crossref","unstructured":"Flint SW, Chauhan J, Dyer R (2021) Escaping the time pit: Pitfalls and guidelines for using time-based git data. In 18th IEEE\/ACM International Conference on Mining Software Repositories, MSR 2021, Madrid, Spain, May 17-19, 2021 85\u201396. IEEE, 2021","key":"10377_CR12","DOI":"10.1109\/MSR52588.2021.00022"},{"doi-asserted-by":"crossref","unstructured":"Gandhi RA, Germonprez M, GJP Link (2018) Open data standards for open source software risk management routines: An examination of SPDX. In Forte A, Prilla M, Vivacqua AS, M\u00fcller C, and Lionel P.\u00a0Robert Jr., editors, Proceedings of the 2018 ACM Conference on Supporting Groupwork, GROUP 2018, Sanibel Island, FL, USA, January 07 - 10, pages 219\u2013229. ACM, 2018","key":"10377_CR13","DOI":"10.1145\/3148330.3148333"},{"doi-asserted-by":"crossref","unstructured":"German DM, Di\u00a0Penta M, Davies J (2010) Understanding and auditing the licensing of open source software distributions. In 2010 IEEE 18th International Conference on Program Comprehension 84\u201393","key":"10377_CR14","DOI":"10.1109\/ICPC.2010.48"},{"doi-asserted-by":"crossref","unstructured":"German DM, Gonz\u00e1lez-Barahona JM (2009) An empirical study of the reuse of software licensed under the GNU General Public License. In Boldyreff C, Crowston K, Lundell B, and Wasserman AI, editors, Open Source Ecosystems: Diverse Communities Interacting, pages 185\u2013198, Berlin, Heidelberg, 2009. Springer Berlin Heidelberg","key":"10377_CR15","DOI":"10.1007\/978-3-642-02032-2_17"},{"doi-asserted-by":"crossref","unstructured":"German DM, Hassan AE (2009) License integration patterns: Addressing license mismatches in component-based development. In 2009 IEEE 31st International Conference on Software Engineering 188\u2013198","key":"10377_CR16","DOI":"10.1109\/ICSE.2009.5070520"},{"doi-asserted-by":"crossref","unstructured":"Germ\u00e1n DM, Manabe Y, Inoue K (2010) A sentence-matching method for automatic license identification of source code files. In Pecheur C, Andrews J, and Di Nitto E, editors, ASE 2010, 25th IEEE\/ACM International Conference on Automated Software Engineering, Antwerp, Belgium, September 20-24, pages 437\u2013446. ACM, 2010","key":"10377_CR17","DOI":"10.1145\/1858996.1859088"},{"doi-asserted-by":"crossref","unstructured":"Germ\u00e1n DM, Di Penta M (2012) A method for open source license compliance of java applications. IEEE Softw 29(3):58\u201363","key":"10377_CR18","DOI":"10.1109\/MS.2012.50"},{"unstructured":"GitHub. Licensee (2023). https:\/\/licensee.github.io\/licensee\/. Accessed 2023-05-08","key":"10377_CR19"},{"doi-asserted-by":"crossref","unstructured":"Gobeille R (2008) The fossology project. In Hassan AE, Lanza M, and Godfrey MW, editors, Proceedings of the 2008 International Working Conference on Mining Software Repositories, MSR 2008 (Co-located with ICSE), Leipzig, Germany, May 10-11, 2008, Proceedings 47\u201350. ACM","key":"10377_CR20","DOI":"10.1145\/1370750.1370763"},{"unstructured":"Gomulkiewicz RW (2009) Open source license proliferation: Helpful diversity or hopeless confusion. Wash. UJL & Pol\u2019y 30:261","key":"10377_CR21"},{"doi-asserted-by":"publisher","unstructured":"Gonzalez-Barahona JM, Montes-Leon S, Robles G, Zacchiroli S (2023) The Software Heritage License Dataset (2022 Edition). https:\/\/doi.org\/10.5281\/zenodo.8200352","key":"10377_CR22","DOI":"10.5281\/zenodo.8200352"},{"doi-asserted-by":"crossref","unstructured":"Gousios G, Spinellis D (2012) Ghtorrent: Github\u2019s data from a firehose. In Lanza M, Di Penta M, and Xie T, editors, 9th IEEE Working Conference of Mining Software Repositories, MSR, pages 12\u201321. IEEE Computer Society, 2012","key":"10377_CR23","DOI":"10.1109\/MSR.2012.6224294"},{"doi-asserted-by":"crossref","unstructured":"Harutyunyan N (2020) Managing your open source supply chain-why and how? Computer 53(6):77\u201381","key":"10377_CR24","DOI":"10.1109\/MC.2020.2983530"},{"unstructured":"Libraries.io. Libraries.io (2023). https:\/\/libraries.io. Accessed 2023-05-08","key":"10377_CR25"},{"unstructured":"Lindberg V (2008) Intellectual property and open source: a practical guide to protecting. O\u2019Reilly Media, Inc., 2008","key":"10377_CR26"},{"doi-asserted-by":"crossref","unstructured":"Ma Y, Dey T, Bogart C, Amreen S, Valiev M, Tutko A, Kennard D, Zaretzki R, Mockus A (2021) World of code: enabling a research workflow for mining and analyzing the universe of open source VCS data. Empir Softw Eng 26(2):22","key":"10377_CR27","DOI":"10.1007\/s10664-020-09905-9"},{"doi-asserted-by":"crossref","unstructured":"Manabe Y, German DM, Inoue K (2014) Analyzing the relationship between the license of packages and their files in free and open source software. In Corral L, Sillitti A, Succi G, Vlasenko J, and Wasserman AI, editors, Open Source Software: Mobile Open Source Technologies 51\u201360, Berlin, Heidelberg, 2014. Springer Berlin Heidelberg","key":"10377_CR28","DOI":"10.1007\/978-3-642-55128-4_6"},{"doi-asserted-by":"crossref","unstructured":"Manabe Y, Hayase Y, Inoue K (2010) Evolutional analysis of licenses in FOSS. In Andrea Capiluppi, Anthony Cleve, and Naouel Moha, editors, Proceedings of the Joint ERCIM Workshop on Software Evolution (EVOL) and International Workshop on Principles of Software Evolution (IWPSE), Antwerp, Belgium, September 20-21, 2010, pages 83\u201387. ACM, 2010","key":"10377_CR29","DOI":"10.1145\/1862372.1862391"},{"doi-asserted-by":"crossref","unstructured":"Maryka T, Germ\u00e1n DM, Poo-Caama\u00f1o G (2015) On the variability of the BSD and MIT licenses. In Ernesto Damiani, Fulvio Frati, Dirk Riehle, and Anthony\u00a0I. Wasserman, editors, Open Source Systems: Adoption and Impact - 11th IFIP WG 2.13 International Conference, OSS 2015, Florence, Italy, May 16-17, 2015, Proceedings, volume 451 of IFIP Advances in Information and Communication Technology 146\u2013156. Springer, 2015","key":"10377_CR30","DOI":"10.1007\/978-3-319-17837-0_14"},{"doi-asserted-by":"crossref","unstructured":"Maryka T, German DM, Poo-Caama\u00f1o G (2015) On the variability of the bsd and mit licenses. In: Damiani Ernesto, Frati Fulvio, Riehle Dirk, Wasserman Anthony I (eds) Open Source Systems: Adoption and Impact (OSS 2015). pp. Springer International Publishing, Cham, pp 146\u2013156","key":"10377_CR31","DOI":"10.1007\/978-3-319-17837-0_14"},{"issue":"9","key":"10377_CR32","first-page":"1","volume":"14","author":"W McKinney","year":"2011","unstructured":"McKinney W et al (2011) Pandas: a foundational python library for data analysis and statistics. Python for high performance and scientific computing 14(9):1\u20139","journal-title":"Python for high performance and scientific computing"},{"unstructured":"nexB ScanCode (2022) https:\/\/www.aboutcode.org\/projects\/scancode.html. Accessed 2022-01-25","key":"10377_CR33"},{"unstructured":"nexB. ScanCode LicenseDB (2022). https:\/\/scancode-licensedb.aboutcode.org\/. Accessed 2022-01-26","key":"10377_CR34"},{"doi-asserted-by":"crossref","unstructured":"Philippe Ombredanne (2020) Free and open source software license compliance: Tools for software composition analysis. Computer 53(10):105\u2013109","key":"10377_CR35","DOI":"10.1109\/MC.2020.3011082"},{"unstructured":"Open Source Initiative (2022) Machine readable OSI license information, 2022. https:\/\/github.com\/OpenSourceOrg\/licenses\/. Accessed 2022-01-26","key":"10377_CR36"},{"unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et\u00a0al (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825\u20132830","key":"10377_CR37"},{"doi-asserted-by":"crossref","unstructured":"Phipps S, Zacchiroli S (2020) Continuous open source license compliance. Computer 53(12):115\u2013119","key":"10377_CR38","DOI":"10.1109\/MC.2020.3024403"},{"doi-asserted-by":"crossref","unstructured":"Pietri A, Spinellis D, Zacchiroli S (2019) The Software Heritage graph dataset: public software development under one roof. In Storey MAD, Adams B, and Haiduc S, editors, Proceedings of the 16th International Conference on Mining Software Repositories, MSR 2019, 26-27 May 2019, Montreal, Canada., pages 138\u2013142. IEEE \/ ACM","key":"10377_CR39","DOI":"10.1109\/MSR.2019.00030"},{"unstructured":"Rosen L (2005) Open source licensing, volume 692. Prentice Hall","key":"10377_CR40"},{"doi-asserted-by":"crossref","unstructured":"Rousseau G, Di\u00a0Cosmo R, Zacchiroli S (2020) Software provenance tracking at the scale of public source code. Empirical Software Engineering 25(4):2930\u20132959","key":"10377_CR41","DOI":"10.1007\/s10664-020-09828-5"},{"doi-asserted-by":"crossref","unstructured":"Shafranovich Y (2005) RFC 4180 - common format and MIME type for comma-separated values (CSV) files, 2005. Accessed 2022-01-24","key":"10377_CR42","DOI":"10.17487\/rfc4180"},{"unstructured":"SPDX Workgroup (2020) Software package data exchange licence list, 2019. https:\/\/spdx.org\/license-list, retrieved 30 March 2020","key":"10377_CR43"},{"unstructured":"Srinivasa-Desikan B (2018) Natural Language Processing and Computational Linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras. Packt Publishing Ltd, 2018","key":"10377_CR44"},{"doi-asserted-by":"crossref","unstructured":"Stewart K, P Odence, Rockett E (2010) Software package data exchange (SPDX) specification. IFOSS L Rev 2:191","key":"10377_CR45","DOI":"10.5033\/ifosslr.v4i1.45"},{"unstructured":"The CodeMeta Project (2023) The CodeMeta Project, 2023. https:\/\/codemeta.github.io\/. Accessed 2023-05-08","key":"10377_CR46"},{"unstructured":"The Open Group (2018) file: determine file type, 2018. https:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/utilities\/file.html. Accessed 2022-01-25","key":"10377_CR47"},{"doi-asserted-by":"crossref","unstructured":"Vendome C, Bavota G, Di\u00a0Penta M, V\u00e1squez ML, Germ\u00e1n DM, Poshyvanyk D (2017) License usage and changes: a large-scale study on GitHub. Empir Softw Eng 22(3):1537\u20131577","key":"10377_CR48","DOI":"10.1007\/s10664-016-9438-4"},{"doi-asserted-by":"crossref","unstructured":"Vendome C, Linares-V\u00e1squez M, Bavota G, Di\u00a0Penta M, German DM, Poshyvanyk D (2015) When and why developers adopt and change software licenses. In 2015 IEEE International Conference on Software Maintenance and Evolution (ICSME) pages 31\u201340","key":"10377_CR49","DOI":"10.1109\/ICSM.2015.7332449"},{"doi-asserted-by":"crossref","unstructured":"Vendome C, V\u00e1squez ML, Bavota G, Di Penta M, Germ\u00e1n DM, Poshyvanyk D (2017) Machine learning-based detection of open source license exceptions. In Sebasti\u00e1n Uchitel, Alessandro Orso, and Martin\u00a0P. Robillard, editors, Proceedings of the 39th International Conference on Software Engineering, ICSE 2017, Buenos Aires, Argentina, May 20-28, 2017, pages 118\u2013129. IEEE \/ ACM, 2017","key":"10377_CR50","DOI":"10.1109\/ICSE.2017.19"},{"doi-asserted-by":"crossref","unstructured":"Xu S, Gao Y, Fan L, Liu Z, Liu Y, and Ji H (2023) Lidetector: License incompatibility detection for open source software. ACM Trans. Softw Eng Methodol 32(1)","key":"10377_CR51","DOI":"10.1145\/3518994"},{"doi-asserted-by":"crossref","unstructured":"Zacchiroli S (2022) A large-scale dataset of (open source) license text variants. In The 2022 Mining Software Repositories Conference (MSR 2022), pages 757\u2013761. ACM, 2022","key":"10377_CR52","DOI":"10.1145\/3524842.3528491"},{"doi-asserted-by":"crossref","unstructured":"Zhang D, Luo P, Tang W, and Zhou M (2021) Osldetector: Identifying open-source libraries through binary analysis. In Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering, ASE \u201920, page 1312-1315, New York, NY, USA, 2021. Association for Computing Machinery","key":"10377_CR53","DOI":"10.1145\/3324884.3415303"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-023-10377-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-023-10377-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-023-10377-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T12:18:14Z","timestamp":1701260294000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-023-10377-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":53,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["10377"],"URL":"https:\/\/doi.org\/10.1007\/s10664-023-10377-w","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"type":"print","value":"1382-3256"},{"type":"electronic","value":"1573-7616"}],"subject":[],"published":{"date-parts":[[2023,11]]},"assertion":[{"value":"24 July 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2023","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 declared that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"147"}}