{"id":"https://openalex.org/W4398161289","doi":"https://doi.org/10.1145/3605098.3636056","title":"A Large-Scale Study of ML-Related Python Projects","display_name":"A Large-Scale Study of ML-Related Python Projects","publication_year":2024,"publication_date":"2024-04-08","ids":{"openalex":"https://openalex.org/W4398161289","doi":"https://doi.org/10.1145/3605098.3636056"},"language":"en","primary_location":{"id":"doi:10.1145/3605098.3636056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636056","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing","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/10.1145/3605098.3636056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102024970","display_name":"Samuel O. Idowu","orcid":"https://orcid.org/0000-0002-4143-322X"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Samuel Idowu","raw_affiliation_strings":["Chalmers | University of Gothenburg, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers | University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098728999","display_name":"Yorick Sens","orcid":"https://orcid.org/0009-0002-5845-5887"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yorick Sens","raw_affiliation_strings":["Ruhr University Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072456187","display_name":"Thorsten Berger","orcid":"https://orcid.org/0000-0002-3870-5167"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Berger","raw_affiliation_strings":["Ruhr University Bochum and Chalmers | University of Gothenburg, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University Bochum and Chalmers | University of Gothenburg, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109721882","display_name":"Jacob Krueger","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jacob Krueger","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005248504","display_name":"Michael Vierhauser","orcid":"https://orcid.org/0000-0003-2672-9230"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Vierhauser","raw_affiliation_strings":["Ruhr University Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102024970"],"corresponding_institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"],"apc_list":null,"apc_paid":null,"fwci":6.3078,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96256309,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1272","last_page":"1281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.994700014591217,"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":0.994700014591217,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10260","display_name":"Software Engineering Research","score":0.9835000038146973,"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/python","display_name":"Python (programming language)","score":0.8142738342285156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6146224141120911},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4514271020889282}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8142738342285156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6146224141120911},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4514271020889282}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3605098.3636056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636056","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/789dbffc-9e71-4fa6-b507-7ac323604acb","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/789dbffc-9e71-4fa6-b507-7ac323604acb","pdf_url":"https://pure.tue.nl/ws/files/349846857/3605098.3636056.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Idowu, S, Sens, Y, Berger, T, Krueger, J & Vierhauser, M 2024, A Large-Scale Study of ML-Related Python Projects. in SAC '24 : Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing. Association for Computing Machinery, Inc., pp. 1272-1281, 39th Annual ACM Symposium on Applied Computing, SAC 2024, Avila, Spain, 8/04/24. https://doi.org/10.1145/3605098.3636056","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.chalmers.se:541892","is_oa":true,"landing_page_url":"http://doi.org/10.1145/3605098.3636056","pdf_url":"https://research.chalmers.se/publication/541892/file/541892_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.tue.nl:openaire/789dbffc-9e71-4fa6-b507-7ac323604acb","is_oa":true,"landing_page_url":"https://research.tue.nl/files/349846857/3605098.3636056.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Idowu, S, Sens, Y, Berger, T, Krueger, J & Vierhauser, M 2024, A Large-Scale Study of ML-Related Python Projects. in SAC '24 : Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing. Association for Computing Machinery, Inc., pp. 1272-1281, 39th Annual ACM Symposium on Applied Computing, SAC 2024, Avila, Spain, 8/04/24. https://doi.org/10.1145/3605098.3636056","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3605098.3636056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636056","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6210056245","display_name":null,"funder_award_id":"Wallenberg Academy Fellowship","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"}],"funders":[{"id":"https://openalex.org/F4320320936","display_name":"Royal Swedish Academy of Sciences","ror":"https://ror.org/00j62qv07"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398161289.pdf","grobid_xml":"https://content.openalex.org/works/W4398161289.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2033626294","https://openalex.org/W2089838497","https://openalex.org/W2620921533","https://openalex.org/W2767825081","https://openalex.org/W2896671475","https://openalex.org/W2909369566","https://openalex.org/W2921408567","https://openalex.org/W2922234936","https://openalex.org/W2987135509","https://openalex.org/W2997681568","https://openalex.org/W3011700633","https://openalex.org/W3029504795","https://openalex.org/W3035250811","https://openalex.org/W3036714619","https://openalex.org/W3042862593","https://openalex.org/W3098910265","https://openalex.org/W3102694483","https://openalex.org/W3107926801","https://openalex.org/W3157059443","https://openalex.org/W3160326234","https://openalex.org/W3162560068","https://openalex.org/W3163379266","https://openalex.org/W3180094739","https://openalex.org/W4280577524","https://openalex.org/W4309389067","https://openalex.org/W4317952684","https://openalex.org/W4362584426"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,15,42,44,47,111,125,143,162,191,198,208],"machine":[3],"learning":[4],"(ML)":[5],"for":[6,23,77,97,155,235],"solving":[7],"current":[8,109],"and":[9,26,59,72,91,108,149,177,196,202,213,224,230],"future":[10],"problems":[11,110],"increased":[12],"the":[13,45,106,123,126,192,199,206],"production":[14],"ML-enabled":[16,48,99,144],"software":[17,88,150],"systems.":[18],"Unfortunately,":[19],"standardized":[20],"tool":[21,225],"chains":[22],"developing,":[24],"employing,":[25],"maintaining":[27],"such":[28,74],"projects":[29,114,145,166],"are":[30,81],"not":[31],"yet":[32],"mature,":[33],"which":[34],"can":[35],"mainly":[36],"be":[37],"attributed":[38],"to":[39,57,104],"a":[40,153,159,182],"lack":[41],"understanding":[43],"properties":[46,107,201],"software.":[49],"For":[50],"instance,":[51],"it":[52,101],"is":[53,102],"still":[54],"unclear":[55],"how":[56],"manage":[58],"evolve":[60],"ML-specific":[61,70],"assets":[62,128],"together":[63,184],"with":[64,86,170,185,241],"other":[65],"software-engineering":[66,243],"assets.":[67],"In":[68],"particular,":[69],"tools":[71,90,96,234],"processes,":[73],"as":[75,84],"those":[76],"managing":[78,236],"ML":[79,165,210,237],"experiments,":[80,147],"often":[82],"perceived":[83],"incompatible":[85],"practitioners'":[87],"engineering":[89],"processes.":[92],"To":[93],"design":[94],"new":[95],"developing":[98,112],"software,":[100],"crucial":[103],"understand":[105],"these":[113],"by":[115],"eliciting":[116],"empirical":[117,186],"data":[118,187],"from":[119],"real":[120],"projects,":[121,238],"including":[122],"evolution":[124],"different":[127,209],"involved.":[129],"Moreover,":[130],"while":[131],"studies":[132,229],"in":[133],"this":[134],"direction":[135],"have":[136],"recently":[137],"been":[138],"conducted,":[139],"identifying":[140],"certain":[141],"types":[142,195],"(e.g.,":[146],"libraries":[148],"systems)":[151],"remains":[152],"challenge":[154],"researchers.":[156],"We":[157,216],"present":[158],"large-scale":[160],"study":[161],"over":[163],"31,066":[164],"found":[167],"on":[168,173],"GitHub,":[169],"an":[171,189],"emphasis":[172],"their":[174,214],"development":[175,211],"stages":[176,212],"evolution.":[178,215],"Our":[179],"contributions":[180],"include":[181],"dataset,":[183],"providing":[188],"overview":[190],"existing":[193],"project":[194],"analysis":[197],"projects'":[200],"characteristics,":[203],"especially":[204,231],"regarding":[205],"implementation":[207],"believe":[217],"that":[218],"our":[219],"results":[220],"support":[221],"researchers,":[222],"practitioners,":[223],"builders":[226],"conduct":[227],"follow-up":[228],"build":[232],"novel":[233],"ideally":[239],"unified":[240],"traditional":[242],"tools.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}