{"id":"https://openalex.org/W7083698550","doi":"https://doi.org/10.5281/zenodo.17229471","title":"A Tool for Automatically Cataloguing, Selecting, and Sampling Pre-Trained Models and Datasets for Software Engineering","display_name":"A Tool for Automatically Cataloguing, Selecting, and Sampling Pre-Trained Models and Datasets for Software Engineering","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W7083698550","doi":"https://doi.org/10.5281/zenodo.17229471"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.17229471","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17229471","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":"article"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17229471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gonz\u00e1lez \u00c1lvarez, Alexandra","orcid":"https://orcid.org/0009-0003-7634-0343"},"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":"Gonz\u00e1lez \u00c1lvarez, Alexandra","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cerezo, Oscar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cerezo, Oscar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Franch, Xavier","orcid":"https://orcid.org/0000-0001-9733-8830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franch, Xavier","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mart\u00ednez-Fern\u00e1ndez, Silverio","orcid":"https://orcid.org/0000-0001-9928-133X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00ednez-Fern\u00e1ndez, Silverio","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":{"id":"https://openalex.org/T10284","display_name":"Anaerobic Digestion and Biogas Production","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10284","display_name":"Anaerobic Digestion and Biogas Production","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11108","display_name":"Municipal Solid Waste Management","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11259","display_name":"Agriculture Sustainability and Environmental Impact","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5698000192642212},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5597000122070312},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.4844000041484833},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48399999737739563},{"id":"https://openalex.org/keywords/asset","display_name":"Asset (computer security)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501000165939331},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4438000023365021},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2778531742","wikidata":"https://www.wikidata.org/wiki/Q17009281","display_name":"Discoverability","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.26750001311302185},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17229471","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17229471","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":"article"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17229471","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17229471","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"repository":[1],"contains":[2],"the":[3,45,50,54,60,87,90,160,164],"source":[4],"code":[5,80],"for":[6,13,23],"ML":[7,37,55,68],"Asset":[8],"Selection,":[9],"a":[10,34,100,126],"tool":[11,32,172],"designed":[12],"automatically":[14],"cataloguing,":[15],"selecting,":[16],"and":[17,66,99,120,132,144,155,162,167],"sampling":[18],"Machine":[19],"Learning":[20],"(ML)":[21],"assets":[22,38,69,108],"Software":[24],"Engineering":[25],"(SE)":[26],"tasks":[27,78],"from":[28,70],"large":[29],"registries.":[30],"The":[31,57,170],"operationalizes":[33],"classification":[35,168],"of":[36,47,53,89],"specifically":[39],"tailored":[40],"to":[41,76,106,152,158],"SE":[42,77,115],"activities,":[43],"addressing":[44],"challenge":[46],"discoverability":[48],"in":[49],"rapid":[51],"growth":[52],"ecosystem.":[56],"package":[58],"includes":[59],"backend":[61],"service":[62],"that":[63,130],"continuously":[64],"extracts":[65],"classifies":[67],"registries":[71],"based":[72,135],"on":[73,136],"their":[74],"relevance":[75],"(e.g.,":[79],"generation,":[81],"vulnerability":[82],"detection).":[83],"It":[84],"also":[85],"provides":[86],"implementation":[88],"interactive":[91,111],"web":[92],"application,":[93],"built":[94],"with":[95],"an":[96],"Angular":[97],"frontend":[98],"FastAPI":[101],"backend,":[102],"which":[103],"enables":[104],"users":[105,157],"filter":[107],"by":[109],"multiple":[110],"attributes,":[112],"such":[113],"as":[114],"task,":[116],"license,":[117],"popularity,":[118],"activity,":[119],"metadata.":[121],"In":[122],"addition,":[123],"it":[124],"offers":[125],"configurable":[127],"leaderboard":[128],"engine":[129],"standardizes":[131],"ranks":[133],"models":[134],"self-reported":[137],"performance":[138],"metrics":[139],"across":[140],"SE-relevant":[141],"benchmarks.":[142],"Documentation":[143],"configuration":[145],"files,":[146],"including":[147],"Docker":[148],"setups,":[149],"are":[150],"included":[151],"ensure":[153],"reproducibility":[154],"allow":[156],"replicate":[159],"environment":[161],"re-run":[163],"asset":[165],"ingestion":[166],"pipelines.":[169],"live":[171],"is":[173],"available":[174],"at:":[175],"http://mlassetselection.essi.upc.edu:3000/home":[176]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
