{"id":"https://openalex.org/W6893065554","doi":"https://doi.org/10.5281/zenodo.14267550","title":"CofeXHug: A curated dataset of HuggingFace pre-trained models exploited in the GitHub ecosystem","display_name":"CofeXHug: A curated dataset of HuggingFace pre-trained models exploited in the GitHub ecosystem","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W6893065554","doi":"https://doi.org/10.5281/zenodo.14267550"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14267550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14267550","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14267550","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Di Sipio, Claudio","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":"Di Sipio, Claudio","raw_affiliation_strings":["University of L'Aquila"],"raw_orcid":"https://orcid.org/0000-0001-9872-9542","affiliations":[{"raw_affiliation_string":"University of L'Aquila","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Di Rocco, Juri","orcid":"https://orcid.org/0000-0002-7909-3902"},"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":"Di Rocco, Juri","raw_affiliation_strings":["University of L'Aquila"],"raw_orcid":"https://orcid.org/0000-0002-7909-3902","affiliations":[{"raw_affiliation_string":"University of L'Aquila","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Di Ruscio, Davide","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":"Di Ruscio, Davide","raw_affiliation_strings":["University of L'Aquila"],"raw_orcid":"https://orcid.org/0000-0002-5077-6793","affiliations":[{"raw_affiliation_string":"University of L'Aquila","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"last","author":{"id":null,"display_name":"Palombo, Stefano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palombo, Stefano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.881600022315979},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7077000141143799},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.6762999892234802},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5586000084877014},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.38830000162124634},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.34459999203681946},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646999955177307},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7077000141143799},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6306999921798706},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5200999975204468},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.250900000333786},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14267550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14267550","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14267550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14267550","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"models":[1,37,146],"(PTMs)":[2],"are":[3,51,83,173],"becoming":[4],"increasingly":[5],"popular":[6,163],"in":[7,38,53,85,88,101,143],"the":[8,32,62,68,102,107,128,139,158,161,166,178,185,191],"software":[9,192],"engineering":[10,193],"community.":[11,194],"Their":[12],"usage":[13],"is":[14,41],"facilitated":[15],"by":[16,182],"model":[17,125],"repositories,":[18],"e.g.,":[19],"HuggingFace,":[20],"which":[21,171],"collect,":[22],"store,":[23],"and":[24,80,123,147,165,184],"maintain":[25],"a":[26,59,71,94,114,121,124,154],"wide":[27],"range":[28],"of":[29,35,49,97,138,157,187],"PTMs.":[30],"However,":[31],"actual":[33,136],"adoption":[34],"these":[36],"real-world":[39],"projects":[40,55],"still":[42],"an":[43],"open":[44],"question.":[45],"In":[46],"particular,":[47],"many":[48],"them":[50,87],"used":[52],"toy":[54],"or":[56],"simply":[57],"as":[58],"mirror":[60],"for":[61,70,170,190],"HF":[63,109],"repository.":[64],"Thus,":[65],"we":[66,111,176],"see":[67],"need":[69],"curated":[72,95],"codebase":[73],"related":[74],"to":[75,77,117,134],"PTMs":[76,99,119,164],"support":[78],"developers":[79],"practitioners":[81],"who":[82],"interested":[84],"using":[86],"their":[89],"projects.This":[90],"artifact":[91],"contains":[92],"CodeXHug,":[93],"dataset":[96],"HuggingFace":[98],"exploited":[100],"GitHub":[103,129],"ecosystem.":[104],"Starting":[105],"from":[106],"latest":[108],"dump,":[110],"first":[112],"conduct":[113],"data":[115],"curation":[116],"collect":[118],"with":[120],"tag":[122],"card.":[126],"Then,":[127],"platform":[130],"has":[131],"been":[132],"queried":[133],"find":[135],"usages":[137],"identified":[140],"PTMs,":[141],"resulting":[142],"7,325":[144],"different":[145],"372,063":[148],"Python":[149],"files.":[150],"We":[151],"also":[152],"present":[153],"statistical":[155],"analysis":[156],"dataset,":[159],"highlighting":[160],"most":[162,167],"common":[168],"tasks":[169],"they":[172],"used.":[174],"Finally,":[175],"discuss":[177],"research":[179],"opportunities":[180],"enabled":[181],"CodeXHug":[183],"implications":[186],"our":[188],"findings":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
