{"id":"https://openalex.org/W4401455417","doi":"https://doi.org/10.1145/3643664.3648204","title":"Lessons Learned from Mining the Hugging Face Repository","display_name":"Lessons Learned from Mining the Hugging Face Repository","publication_year":2024,"publication_date":"2024-04-16","ids":{"openalex":"https://openalex.org/W4401455417","doi":"https://doi.org/10.1145/3643664.3648204"},"language":"en","primary_location":{"id":"doi:10.1145/3643664.3648204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643664.3648204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st IEEE/ACM International Workshop on Methodological Issues with Empirical Studies in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/6561fdc2-69e7-4126-8fa3-5be72b9d4f4c/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103024758","display_name":"Joel Casta\u00f1o","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Joel Casta\u00f1o","raw_affiliation_strings":["Universitat Politecnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050955846","display_name":"Silverio Mart\u00ednez\u2010Fern\u00e1ndez","orcid":"https://orcid.org/0000-0001-9928-133X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Silverio Mart\u00ednez-Fern\u00e1ndez","raw_affiliation_strings":["Universitat Politecnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027686521","display_name":"Xavier Franch","orcid":"https://orcid.org/0000-0001-9733-8830"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Franch","raw_affiliation_strings":["Universitat Politecnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103024758"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":17.8589,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98978307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.6320000290870667,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.6320000290870667,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12755","display_name":"Legal Education and Practice Innovations","score":0.6043999791145325,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.6015999913215637,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6992493867874146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6779239177703857},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4012444019317627},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36957770586013794},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3221360445022583},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10890448093414307}],"concepts":[{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6992493867874146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779239177703857},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4012444019317627},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36957770586013794},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3221360445022583},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10890448093414307},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3643664.3648204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643664.3648204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st IEEE/ACM International Workshop on Methodological Issues with Empirical Studies in Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/418576","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/418576","pdf_url":"https://upcommons.upc.edu/bitstreams/6561fdc2-69e7-4126-8fa3-5be72b9d4f4c/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/418576","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/418576","pdf_url":"https://upcommons.upc.edu/bitstreams/6561fdc2-69e7-4126-8fa3-5be72b9d4f4c/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3681454997","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4042783231","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4126322094","display_name":null,"funder_award_id":"01100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G417802509","display_name":null,"funder_award_id":"TED2021-130923B-I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G465903436","display_name":null,"funder_award_id":"Next Generation EU/PRTR","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G661330594","display_name":null,"funder_award_id":"00110","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6685425346","display_name":null,"funder_award_id":"0011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8260616629","display_name":null,"funder_award_id":"011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401455417.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1814291772","https://openalex.org/W1999649023","https://openalex.org/W2167271913","https://openalex.org/W3118630514","https://openalex.org/W3204368535","https://openalex.org/W4200065965","https://openalex.org/W4323557410","https://openalex.org/W4376606869","https://openalex.org/W4379538741","https://openalex.org/W4387355748","https://openalex.org/W4388115877","https://openalex.org/W4388963745","https://openalex.org/W4390707532","https://openalex.org/W4393718226","https://openalex.org/W6636001999"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0,127],"rapidly":[1],"evolving":[2],"fields":[3],"of":[4,15,51,79,87,152,170,191,198,202],"Machine":[5],"Learning":[6],"(ML)":[7],"and":[8,27,45,48,99,123,162,188,193],"Artificial":[9],"Intelligence":[10],"have":[11],"witnessed":[12],"the":[13,46,72,77,85,88,96,115,149,167,171,186,199],"emergence":[14],"platforms":[16],"like":[17],"Hugging":[18],"Face":[19],"(HF)":[20],"as":[21,178],"central":[22],"hubs":[23],"for":[24,62,114,182],"model":[25,151,173],"development":[26],"sharing.":[28],"This":[29,155],"experience":[30],"report":[31,128,176],"synthesizes":[32],"insights":[33],"from":[34,134],"two":[35],"comprehensive":[36,124],"studies":[37,70],"conducted":[38],"on":[39,42,66],"HF,":[40],"focusing":[41],"carbon":[43],"emissions":[44],"evolutionary":[47],"maintenance":[49],"aspects":[50],"ML":[52,150,203],"models.":[53,204],"Our":[54,175],"objective":[55],"is":[56,157,163],"to":[57,75,137,140,165,185],"provide":[58],"a":[59,108,121,179,195],"practical":[60],"guide":[61],"future":[63],"researchers":[64],"embarking":[65],"mining":[67,136,145],"software":[68],"repository":[69,135,144],"within":[71,148],"HF":[73,117,153,172],"ecosystem":[74],"enhance":[76],"quality":[78],"these":[80],"studies.":[81],"We":[82],"delve":[83],"into":[84],"intricacies":[86],"replication":[89],"package":[90],"used":[91],"in":[92,143],"our":[93,103],"studies,":[94,139,146],"highlighting":[95],"pivotal":[97],"tools":[98],"methodologies":[100],"that":[101],"facilitated":[102],"analysis.":[104],"Furthermore,":[105],"we":[106],"propose":[107],"nuanced":[109],"stratified":[110],"sampling":[111],"strategy":[112],"tailored":[113],"diverse":[116],"Hub":[118],"dataset,":[119],"ensuring":[120],"representative":[122],"analytical":[125],"approach.":[126],"also":[129],"introduces":[130],"preliminary":[131],"guidelines,":[132],"transitioning":[133],"cohort":[138],"establish":[141],"causality":[142],"particularly":[147],"context.":[154],"transition":[156],"inspired":[158],"by":[159],"existing":[160],"frameworks":[161],"adapted":[164],"suit":[166],"unique":[168],"characteristics":[169],"ecosystem.":[174],"serves":[177],"guiding":[180],"framework":[181],"researchers,":[183],"contributing":[184],"responsible":[187],"sustainable":[189],"advancement":[190],"ML,":[192],"fostering":[194],"deeper":[196],"understanding":[197],"broader":[200],"implications":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-08-10T00:00:00"}
