{"id":"https://openalex.org/W4399531343","doi":"https://doi.org/10.1145/3644815.3644963","title":"An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications","display_name":"An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4399531343","doi":"https://doi.org/10.1145/3644815.3644963"},"language":"en","primary_location":{"id":"doi:10.1145/3644815.3644963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3644815.3644963","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3644815.3644963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3644815.3644963","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070576670","display_name":"Tajkia Rahman Toma","orcid":"https://orcid.org/0000-0003-4383-3494"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tajkia Rahman Toma","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4383-3494","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066994589","display_name":"Cor\u2010Paul Bezemer","orcid":"https://orcid.org/0000-0002-0474-5718"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cor-Paul Bezemer","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0474-5718","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8733,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86138887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9980000257492065,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973999857902527,"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":0.8230910897254944},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6345424056053162},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5905025005340576},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5297445058822632},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5105777382850647},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.48425933718681335},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4728330075740814},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44873932003974915},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.42090222239494324},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37116003036499023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3467879891395569},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17018264532089233},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10534024238586426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230910897254944},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6345424056053162},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5905025005340576},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5297445058822632},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5105777382850647},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.48425933718681335},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4728330075740814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44873932003974915},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.42090222239494324},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37116003036499023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3467879891395569},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17018264532089233},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10534024238586426},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3644815.3644963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3644815.3644963","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3644815.3644963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3644815.3644963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3644815.3644963","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3644815.3644963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319946","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399531343.pdf","grobid_xml":"https://content.openalex.org/works/W4399531343.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2182687482","https://openalex.org/W2896671475","https://openalex.org/W2922234936","https://openalex.org/W2955440819","https://openalex.org/W2997591727","https://openalex.org/W3035250811","https://openalex.org/W3098910265","https://openalex.org/W3135028703","https://openalex.org/W3160326234","https://openalex.org/W3162560068","https://openalex.org/W3173543662","https://openalex.org/W3202461888","https://openalex.org/W4214942037","https://openalex.org/W4221072216","https://openalex.org/W4283023890","https://openalex.org/W4284670548","https://openalex.org/W4296422567","https://openalex.org/W4312501142","https://openalex.org/W4316126954","https://openalex.org/W4317952684","https://openalex.org/W4393515867","https://openalex.org/W6893881405"],"related_works":["https://openalex.org/W2061122711","https://openalex.org/W4247954915","https://openalex.org/W2131958170","https://openalex.org/W2273754158","https://openalex.org/W2336747664","https://openalex.org/W2357130048","https://openalex.org/W4206605161","https://openalex.org/W2092234295","https://openalex.org/W4282583532","https://openalex.org/W4256076151"],"abstract_inverted_index":{"Datasets":[0],"and":[1,19,33,47,64,83,96,109,117,130,136],"models":[2,34,48,84,118,137],"are":[3,35,52,62,103,138,147],"two":[4],"key":[5],"artifacts":[6,61],"in":[7,22,49,106,150],"machine":[8],"learning":[9],"(ML)":[10],"applications.":[11,39,68],"Although":[12],"there":[13],"exist":[14],"tools":[15],"to":[16,80,140],"support":[17],"dataset":[18],"model":[20,97],"developers":[21],"managing":[23],"ML":[24,38,50],"artifacts,":[25],"little":[26],"is":[27,85],"known":[28],"about":[29],"how":[30,45,59],"these":[31,60],"datasets":[32,46,82,116,135],"integrated":[36],"into":[37],"In":[40,54],"this":[41],"paper,":[42],"we":[43,56,73],"study":[44],"applications":[51],"managed.":[53],"particular,":[55],"focus":[57],"on":[58],"stored":[63,104],"versioned":[65],"alongside":[66],"the":[67,75,86,115,123,143],"After":[69],"analyzing":[70],"93":[71],"repositories,":[72],"identified":[74],"most":[76],"common":[77],"storage":[78,108],"location":[79],"store":[81],"file":[87],"system,":[88,126],"which":[89],"causes":[90],"availability":[91],"issues.":[92,132],"Notably,":[93],"large":[94],"data":[95],"files,":[98],"exceeding":[99],"approximately":[100],"60":[101],"MB,":[102],"exclusively":[105],"remote":[107],"downloaded":[110],"as":[111],"needed.":[112],"Most":[113],"of":[114],"lack":[119],"proper":[120],"integration":[121],"with":[122],"version":[124],"control":[125],"posing":[127],"potential":[128],"trace-ability":[129],"reproducibility":[131],"Additionally,":[133],"although":[134],"likely":[139],"evolve":[141],"during":[142],"application":[144,151],"development,":[145],"they":[146],"rarely":[148],"updated":[149],"repositories.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
