{"id":"https://openalex.org/W4390707532","doi":"https://doi.org/10.1016/j.scico.2024.103079","title":"HFCommunity: An extraction process and relational database to analyze Hugging Face Hub data","display_name":"HFCommunity: An extraction process and relational database to analyze Hugging Face Hub data","publication_year":2024,"publication_date":"2024-01-10","ids":{"openalex":"https://openalex.org/W4390707532","doi":"https://doi.org/10.1016/j.scico.2024.103079"},"language":"en","primary_location":{"id":"doi:10.1016/j.scico.2024.103079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.scico.2024.103079","pdf_url":null,"source":{"id":"https://openalex.org/S21029587","display_name":"Science of Computer Programming","issn_l":"0167-6423","issn":["0167-6423","1872-7964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science of Computer Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.scico.2024.103079","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081900823","display_name":"Adem Ait","orcid":"https://orcid.org/0000-0002-5334-9041"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adem Ait","raw_affiliation_strings":["IN3 \u2013 UOC, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5334-9041","affiliations":[{"raw_affiliation_string":"IN3 \u2013 UOC, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011891628","display_name":"Javier Luis Izquierdo","orcid":"https://orcid.org/0000-0002-2326-1700"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Javier Luis C\u00e1novas Izquierdo","raw_affiliation_strings":["IN3 \u2013 UOC, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IN3 \u2013 UOC, Barcelona, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074872542","display_name":"Jordi Cabot","orcid":"https://orcid.org/0000-0003-2418-2489"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Jordi Cabot","raw_affiliation_strings":["Luxembourg Institute of Science and Technology, University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology, University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I4210112527","https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011891628","https://openalex.org/A5074872542","https://openalex.org/A5081900823"],"corresponding_institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4210112527"],"apc_list":{"value":2460,"currency":"USD","value_usd":2460},"apc_paid":{"value":2460,"currency":"USD","value_usd":2460},"fwci":6.9272,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.96440567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"234","issue":null,"first_page":"103079","last_page":"103079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9162017703056335},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5452022552490234},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5377367734909058},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5185418725013733},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5093935132026672},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5037207007408142},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4808700680732727},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44027724862098694},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4149683117866516},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38762354850769043},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36988258361816406},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10409995913505554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9162017703056335},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5452022552490234},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5377367734909058},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5185418725013733},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5093935132026672},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5037207007408142},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4808700680732727},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44027724862098694},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4149683117866516},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38762354850769043},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36988258361816406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10409995913505554},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.scico.2024.103079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.scico.2024.103079","pdf_url":null,"source":{"id":"https://openalex.org/S21029587","display_name":"Science of Computer Programming","issn_l":"0167-6423","issn":["0167-6423","1872-7964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science of Computer Programming","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.scico.2024.103079","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.scico.2024.103079","pdf_url":null,"source":{"id":"https://openalex.org/S21029587","display_name":"Science of Computer Programming","issn_l":"0167-6423","issn":["0167-6423","1872-7964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science of Computer Programming","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4253668592","https://openalex.org/W4287383930","https://openalex.org/W6783701926","https://openalex.org/W6840762099","https://openalex.org/W6847812053","https://openalex.org/W6852154484"],"related_works":["https://openalex.org/W2124842464","https://openalex.org/W2382657549","https://openalex.org/W4376877853","https://openalex.org/W75565505","https://openalex.org/W4214847518","https://openalex.org/W3200575725","https://openalex.org/W4242732953","https://openalex.org/W1535063848","https://openalex.org/W2186225517","https://openalex.org/W1153144596"],"abstract_inverted_index":{"Social":[0],"coding":[1],"platforms":[2,27],"such":[3],"as":[4],"GitHub":[5],"or":[6],"GitLab":[7],"have":[8,36],"become":[9],"the":[10,21,45,58,90,94,103,110,134],"de":[11],"facto":[12],"standard":[13],"for":[14,30,121],"developing":[15,33],"Open-Source":[16],"Software":[17],"(OSS)":[18],"projects.":[19,139],"With":[20,63],"emergence":[22],"of":[23,44,77,83,113,137],"Machine":[24],"Learning":[25],"(ML),":[26],"specifically":[28],"designed":[29],"hosting":[31],"and":[32,57,68,124],"ML-based":[34],"projects":[35],"appeared,":[37],"being":[38],"Hugging":[39],"Face":[40],"Hub":[41],"(HFH)":[42],"one":[43],"most":[46],"popular":[47],"ones.":[48],"HFH":[49,71,122],"aims":[50],"at":[51],"sharing":[52],"datasets,":[53],"pre-trained":[54],"ML":[55,84,138],"models":[56],"applications":[59],"built":[60],"with":[61],"them.":[62],"over":[64],"400":[65],"K":[66],"repositories,":[67],"growing":[69,135],"fast,":[70],"is":[72],"becoming":[73],"a":[74,125],"promising":[75],"source":[76],"empirical":[78,131],"data":[79,123],"on":[80,133],"all":[81],"aspects":[82],"project":[85],"development.":[86],"However,":[87],"apart":[88],"from":[89],"API":[91],"provided":[92],"by":[93],"platform,":[95],"there":[96],"are":[97],"no":[98],"easy-to-use":[99],"solutions":[100],"to":[101,108,128],"collect":[102],"data,":[104],"nor":[105],"prepackaged":[106],"datasets":[107],"explore":[109],"different":[111],"facets":[112],"HFH.":[114],"We":[115],"present":[116],"HFCommunity,":[117],"an":[118,130],"extraction":[119],"process":[120],"relational":[126],"database":[127],"facilitate":[129],"analysis":[132],"number":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
