{"id":"https://openalex.org/W4400242886","doi":"https://doi.org/10.1145/3643991.3644864","title":"CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code","display_name":"CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4400242886","doi":"https://doi.org/10.1145/3643991.3644864"},"language":"en","primary_location":{"id":"doi:10.1145/3643991.3644864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643991.3644864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107246651","display_name":"Martin Weyssow","orcid":"https://orcid.org/0000-0002-5987-850X"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Weyssow","raw_affiliation_strings":["DIRO, University of Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5987-850X","affiliations":[{"raw_affiliation_string":"DIRO, University of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047553297","display_name":"Claudio Di Sipio","orcid":"https://orcid.org/0000-0001-9872-9542"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Di Sipio","raw_affiliation_strings":["University of l'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9872-9542","affiliations":[{"raw_affiliation_string":"University of l'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002764716","display_name":"Davide Di Ruscio","orcid":"https://orcid.org/0000-0002-5077-6793"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Di Ruscio","raw_affiliation_strings":["University of L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5077-6793","affiliations":[{"raw_affiliation_string":"University of L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009574640","display_name":"Houari Sahraoui","orcid":"https://orcid.org/0000-0001-6304-9926"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Houari Sahraoui","raw_affiliation_strings":["DIRO, University of Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6304-9926","affiliations":[{"raw_affiliation_string":"DIRO, University of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1303805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9781000018119812,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.95169997215271,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844988107681274},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.6037123203277588},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5858545303344727},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4579973816871643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41524291038513184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39198288321495056},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.371993750333786},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3234439492225647},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2380136251449585},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07546809315681458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844988107681274},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.6037123203277588},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5858545303344727},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4579973816871643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41524291038513184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39198288321495056},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.371993750333786},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3234439492225647},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2380136251449585},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07546809315681458},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3643991.3644864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643991.3644864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2796104318","https://openalex.org/W2954401434","https://openalex.org/W3119696503","https://openalex.org/W3121596715","https://openalex.org/W4224280711","https://openalex.org/W4288080276","https://openalex.org/W4375957737","https://openalex.org/W4382363007","https://openalex.org/W4384009705","https://openalex.org/W4384345739"],"related_works":["https://openalex.org/W2364105709","https://openalex.org/W2384383462","https://openalex.org/W2380954666","https://openalex.org/W422428167","https://openalex.org/W1981922029","https://openalex.org/W2037025106","https://openalex.org/W2499777278","https://openalex.org/W2391851613","https://openalex.org/W1485190762","https://openalex.org/W4372778609"],"abstract_inverted_index":{"Motivated":[0],"by":[1,33],"recent":[2],"work":[3],"on":[4,22],"lifelong":[5,18,50,120],"learning":[6,19,51,124],"applications":[7],"for":[8,123],"language":[9],"models":[10],"(LMs)":[11],"of":[12,36,68,80,98,117,142],"code,":[13],"we":[14,75],"introduce":[15,76],"CodeLL,":[16,81],"a":[17,28,37],"dataset":[20,56,91,129],"focused":[21],"code":[23,43,61,99,125],"changes.":[24,126],"Our":[25],"contribution":[26],"addresses":[27],"notable":[29],"research":[30],"gap":[31],"marked":[32],"the":[34,64,93,106,115,128,140],"absence":[35],"long-term":[38],"temporal":[39],"dimension":[40],"in":[41,49,119],"existing":[42],"change":[44],"datasets,":[45],"limiting":[46],"their":[47],"suitability":[48],"scenarios.":[52],"In":[53,72],"contrast,":[54],"our":[55],"aims":[57],"to":[58],"comprehensively":[59],"capture":[60],"changes":[62,100],"across":[63],"entire":[65],"release":[66],"history":[67],"open-source":[69],"software":[70,137],"repositories.":[71],"this":[73],"work,":[74],"an":[77],"initial":[78],"version":[79],"comprising":[82],"71":[83],"machine-learning-based":[84],"projects":[85],"mined":[86],"from":[87],"Software":[88],"Heritage.":[89],"This":[90],"enables":[92,112],"extraction":[94],"and":[95,108,139],"in-depth":[96],"analysis":[97],"spanning":[101],"2,483":[102],"releases":[103],"at":[104],"both":[105],"method":[107],"API":[109,143],"levels.":[110],"CodeLL":[111],"researchers":[113],"studying":[114,132],"behaviour":[116],"LMs":[118],"fine-tuning":[121],"settings":[122],"Additionally,":[127],"can":[130],"help":[131],"data":[133],"distribution":[134],"shifts":[135],"within":[136],"repositories":[138],"evolution":[141],"usages":[144],"over":[145],"time.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
