{"id":"https://openalex.org/W4399577216","doi":"https://doi.org/10.1145/3650105.3652298","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","display_name":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4399577216","doi":"https://doi.org/10.1145/3650105.3652298"},"language":"en","primary_location":{"id":"doi:10.1145/3650105.3652298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652298","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652298","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080480598","display_name":"Jonathan Katzy","orcid":"https://orcid.org/0009-0005-9574-2414"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jonathan Katzy","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0009-0005-9574-2414","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986046","display_name":"Razvan Mihai Popescu","orcid":"https://orcid.org/0009-0003-6251-770X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Razvan Popescu","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0009-0003-6251-770X","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090401584","display_name":"Arie van Deursen","orcid":"https://orcid.org/0000-0003-4850-3312"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arie Van Deursen","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4850-3312","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064355563","display_name":"Maliheh Izadi","orcid":"https://orcid.org/0000-0001-5093-5523"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maliheh Izadi","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5093-5523","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080480598"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":2.6491,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90936335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9516000151634216,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257286548614502},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.7402676939964294},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.6796707510948181},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6070550084114075},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5831562876701355},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5139865279197693},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5053237080574036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.503236711025238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44594186544418335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35320770740509033},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29768067598342896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257286548614502},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7402676939964294},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.6796707510948181},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6070550084114075},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5831562876701355},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5139865279197693},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5053237080574036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.503236711025238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44594186544418335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35320770740509033},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29768067598342896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650105.3652298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652298","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650105.3652298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652298","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399577216.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1992218759","https://openalex.org/W2134852596","https://openalex.org/W2147209048","https://openalex.org/W3098605233","https://openalex.org/W3138815606","https://openalex.org/W4221166942","https://openalex.org/W4307751519","https://openalex.org/W4312933868","https://openalex.org/W4385270018","https://openalex.org/W4385572142","https://openalex.org/W4389009541","https://openalex.org/W4389519352","https://openalex.org/W4389524330","https://openalex.org/W4394744221","https://openalex.org/W4396870811"],"related_works":["https://openalex.org/W2606446052","https://openalex.org/W2036021480","https://openalex.org/W3195777957","https://openalex.org/W2382668227","https://openalex.org/W2348482143","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Does":[0],"the":[1,36,40,43,49,72,78],"training":[2,24,50],"of":[3,45,51,74,87,114],"large":[4,52,89],"language":[5,53,90],"models":[6,26,65,91],"potentially":[7],"infringe":[8],"upon":[9],"code":[10,47],"licenses?":[11,30],"Furthermore,":[12],"are":[13],"there":[14],"any":[15],"datasets":[16,60,100],"available":[17,59],"that":[18],"can":[19,66],"be":[20,67],"safely":[21],"used":[22],"for":[23],"these":[25,64],"without":[27,71],"violating":[28],"such":[29],"In":[31],"our":[32],"study,":[33],"we":[34,56,83,110],"assess":[35],"current":[37],"trends":[38],"in":[39,77],"field":[41],"and":[42,101],"importance":[44],"incorporating":[46],"into":[48],"models.":[54],"Additionally,":[55],"examine":[57],"publicly":[58],"to":[61],"see":[62],"whether":[63],"trained":[68,92],"on":[69,93],"them":[70],"risk":[73],"legal":[75],"issues":[76],"future.":[79],"To":[80],"accomplish":[81],"this,":[82],"compiled":[84],"a":[85,108],"list":[86],"53":[88],"file-level":[94],"code.":[95,117],"We":[96],"then":[97],"extracted":[98],"their":[99],"analyzed":[102],"how":[103],"much":[104],"they":[105],"overlap":[106],"with":[107],"dataset":[109],"created,":[111],"consisting":[112],"exclusively":[113],"strong":[115],"copyleft":[116]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}