{"id":"https://openalex.org/W2611130659","doi":"https://doi.org/10.1145/3076246.3076248","title":"Versioning for End-to-End Machine Learning Pipelines","display_name":"Versioning for End-to-End Machine Learning Pipelines","publication_year":2017,"publication_date":"2017-05-02","ids":{"openalex":"https://openalex.org/W2611130659","doi":"https://doi.org/10.1145/3076246.3076248","mag":"2611130659"},"language":"en","primary_location":{"id":"doi:10.1145/3076246.3076248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3076246.3076248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"article","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/A5010182820","display_name":"Tom van der Weide","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tom van der Weide","raw_affiliation_strings":["Schibsted Media Group"],"affiliations":[{"raw_affiliation_string":"Schibsted Media Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002671343","display_name":"Dimitris Papadopoulos","orcid":"https://orcid.org/0000-0002-0725-3954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitris Papadopoulos","raw_affiliation_strings":["Schibsted Media Group"],"affiliations":[{"raw_affiliation_string":"Schibsted Media Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007202775","display_name":"O. Smirnov","orcid":"https://orcid.org/0000-0002-5238-0442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Smirnov","raw_affiliation_strings":["Schibsted Media Group"],"affiliations":[{"raw_affiliation_string":"Schibsted Media Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029508763","display_name":"Micha\u0142 Zieli\u0144ski","orcid":"https://orcid.org/0000-0002-7239-2504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michal Zielinski","raw_affiliation_strings":["Schibsted Media Group"],"affiliations":[{"raw_affiliation_string":"Schibsted Media Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032255330","display_name":"Tim van Kasteren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim van Kasteren","raw_affiliation_strings":["Schibsted Media Group"],"affiliations":[{"raw_affiliation_string":"Schibsted Media Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010182820"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5901,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96986868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991000294685364,"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":0.9991000294685364,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.994700014591217,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9883999824523926,"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":0.7709762454032898},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7621760964393616},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7252933979034424},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7168076634407043},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.529392421245575},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4424198269844055},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3586188852787018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2684484124183655},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20185840129852295},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12674963474273682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709762454032898},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7621760964393616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7252933979034424},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7168076634407043},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.529392421245575},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4424198269844055},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3586188852787018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2684484124183655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20185840129852295},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12674963474273682},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3076246.3076248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3076246.3076248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1531630191","https://openalex.org/W2038157364","https://openalex.org/W2055311027","https://openalex.org/W2065867349","https://openalex.org/W2070996757","https://openalex.org/W2081757705","https://openalex.org/W2101234009","https://openalex.org/W2124789775","https://openalex.org/W2131400476","https://openalex.org/W2260378577","https://openalex.org/W2306526421","https://openalex.org/W2337042987","https://openalex.org/W2395358760","https://openalex.org/W2432911982","https://openalex.org/W2438792749","https://openalex.org/W2584502673","https://openalex.org/W2584881186","https://openalex.org/W2599070920","https://openalex.org/W2963288913","https://openalex.org/W2997591727","https://openalex.org/W4298074235"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2000444236","https://openalex.org/W2384475851","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2353602216","https://openalex.org/W2938107654","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W3008587939"],"abstract_inverted_index":{"End-to-end":[0],"machine":[1],"learning":[2],"pipelines":[3,14,49],"that":[4],"run":[5],"in":[6,41,51,57],"shared":[7],"environments":[8],"are":[9,27],"challenging":[10],"to":[11,29,34,87,92,98],"implement.":[12],"Production":[13],"typically":[15],"consist":[16],"of":[17,44,54,59,79],"multiple":[18],"interdependent":[19],"processing":[20,48,81],"stages.":[21],"Between":[22],"stages,":[23],"the":[24,42,52,70,80],"intermediate":[25],"results":[26,38,65],"persisted":[28,64],"reduce":[30],"redundant":[31],"computation":[32],"and":[33,105],"improve":[35],"robustness.":[36],"Those":[37],"might":[39],"come":[40],"form":[43,53],"datasets":[45,101],"for":[46],"data":[47],"or":[50,90],"model":[55,60],"coefficients":[56],"case":[58],"training":[61],"pipelines.":[62],"Reusing":[63],"improves":[66],"efficiency":[67],"but":[68],"at":[69],"same":[71],"time":[72,77],"creates":[73],"complicated":[74],"dependencies.":[75],"Every":[76],"one":[78],"stages":[82],"is":[83],"changed,":[84],"either":[85],"due":[86,91],"code":[88],"change":[89],"parameters":[93],"change,":[94],"it":[95],"becomes":[96],"difficult":[97],"find":[99],"which":[100,106],"can":[102],"be":[103,108],"reused":[104],"should":[107],"recomputed.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}