{"id":"https://openalex.org/W4402673621","doi":"https://doi.org/10.1109/e-science62913.2024.10678671","title":"Deriva-ML: A Continuous FAIRness Approach to Reproducible Machine Learning Models","display_name":"Deriva-ML: A Continuous FAIRness Approach to Reproducible Machine Learning Models","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402673621","doi":"https://doi.org/10.1109/e-science62913.2024.10678671"},"language":"en","primary_location":{"id":"doi:10.1109/e-science62913.2024.10678671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science62913.2024.10678671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100409100","display_name":"Zhiwei Li","orcid":"https://orcid.org/0000-0003-2557-4118"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwei Li","raw_affiliation_strings":["University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085298473","display_name":"Carl Kesselman","orcid":"https://orcid.org/0000-0003-0917-1562"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Kesselman","raw_affiliation_strings":["University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033206229","display_name":"Mike D\u2019Arcy","orcid":"https://orcid.org/0000-0003-2280-917X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike D\u2019Arcy","raw_affiliation_strings":["University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018321151","display_name":"Michael J. Pazzani","orcid":"https://orcid.org/0000-0002-4240-7349"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Pazzani","raw_affiliation_strings":["University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute Viterbi School of Engineering,Marina del Rey,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101393729","display_name":"Benjamin Yizing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Yizing Xu","raw_affiliation_strings":["University of Southern California,Keck School of Medicine,Department of Ophthalmology,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Keck School of Medicine,Department of Ophthalmology,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":5.3438,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96191304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9584000110626221,"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":0.9584000110626221,"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"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9054999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7675864100456238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37497955560684204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675864100456238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37497955560684204}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science62913.2024.10678671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science62913.2024.10678671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1967180811","https://openalex.org/W2020490061","https://openalex.org/W2137125422","https://openalex.org/W2302501749","https://openalex.org/W2562004858","https://openalex.org/W2592114463","https://openalex.org/W2770021808","https://openalex.org/W2922234936","https://openalex.org/W2963957599","https://openalex.org/W3118813946","https://openalex.org/W4288052974","https://openalex.org/W4289132944","https://openalex.org/W4312444110","https://openalex.org/W4360995249","https://openalex.org/W4363648773","https://openalex.org/W4385248297","https://openalex.org/W4385576721","https://openalex.org/W4387006143","https://openalex.org/W4387030151","https://openalex.org/W4388041079","https://openalex.org/W4392488972"],"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":{"Increasingly,":[0],"artificial":[1],"intelligence":[2],"(AI)":[3],"and":[4,47,86,97,105,121,157,207,215,220],"machine":[5],"learning":[6],"(ML)":[7],"are":[8,32,94],"used":[9,44,171,230],"in":[10],"eScience":[11,110,192,202,234],"applications":[12],"[9].":[13],"While":[14],"these":[15,182],"approaches":[16,26,69,102],"have":[17],"great":[18],"potential,":[19],"the":[20,49,55,72,88,143,148,165,185,198],"literature":[21],"has":[22,64],"shown":[23],"that":[24,31,70,123,145,169,180],"ML-based":[25,191,233],"frequently":[27],"suffer":[28],"from":[29,75],"results":[30,63],"either":[33],"incorrect":[34],"or":[35,40],"unreproducible":[36],"due":[37],"to":[38,66,78,84,103,184,204,231],"mismanagement":[39],"misuse":[41],"of":[42,54,57,80,147,167,189,200,217],"data":[43,59,82,122,138,149,168],"for":[45,60,100,109,150,172],"training":[46],"validating":[48],"models":[50,89,120],"[12],":[51],"[15].":[52],"Recognition":[53],"necessity":[56],"high-quality":[58,81],"correct":[61,206],"ML":[62,68,107,151,173,209],"led":[65],"data-centric":[67,101],"shift":[71],"central":[73],"focus":[74],"model":[76],"development":[77],"creation":[79],"sets":[83],"train":[85],"validate":[87],"[14],":[90],"[20].":[91],"However,":[92],"there":[93],"limited":[95],"tools":[96,140,183,219],"methods":[98],"available":[99],"explore":[104],"evaluate":[106],"solutions":[108],"problems":[111],"which":[112],"often":[113],"require":[114],"collaborative":[115],"multidisciplinary":[116],"teams":[117],"working":[118],"with":[119,177],"will":[124],"rapidly":[125],"evolve":[126],"as":[127],"an":[128,190,201,213],"investigation":[129],"unfolds":[130],"[1].":[131],"In":[132],"this":[133],"paper,":[134],"we":[135,194],"show":[136],"how":[137,226],"management":[139],"based":[141],"on":[142],"principle":[144],"all":[146],"should":[152],"be":[153,229],"findable,":[154],"accessible,":[155],"interoperable":[156],"reusable":[158],"(i.e.":[159],"FAIR":[160],"[26])":[161],"can":[162,195,228],"significantly":[163,196],"improve":[164,197,232],"quality":[166],"is":[170],"applications.":[174],"When":[175],"combined":[176],"best":[178],"practices":[179],"apply":[181],"entire":[186],"life":[187],"cycle":[188],"investigation,":[193],"ability":[199],"team":[203],"create":[205],"reproducible":[208],"solutions.":[210],"We":[211],"propose":[212],"architecture":[214],"implementation":[216],"such":[218],"demonstrate":[221],"through":[222],"two":[223],"use":[224],"cases":[225],"they":[227],"investigations.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
