{"id":"https://openalex.org/W4210354100","doi":"https://doi.org/10.1007/s00778-021-00726-w","title":"Data distribution debugging in machine learning pipelines","display_name":"Data distribution debugging in machine learning pipelines","publication_year":2022,"publication_date":"2022-01-31","ids":{"openalex":"https://openalex.org/W4210354100","doi":"https://doi.org/10.1007/s00778-021-00726-w"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-021-00726-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-021-00726-w","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/data-distribution-debugging-in-machine-learning-pipelines(a87cddc2-b9cf-4db4-8981-02ea705f54ff).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081322278","display_name":"Stefan Grafberger","orcid":"https://orcid.org/0000-0002-9884-9517"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stefan Grafberger","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034924491","display_name":"Paul Groth","orcid":"https://orcid.org/0000-0003-0183-6910"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082830839","display_name":"Julia Stoyanovich","orcid":"https://orcid.org/0000-0002-1587-0450"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Stoyanovich","raw_affiliation_strings":["New York University, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090934117"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":10.2741,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97437554,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"31","issue":"5","first_page":"1103","last_page":"1126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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/T11719","display_name":"Data Quality and Management","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8363254070281982},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6136187314987183},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5801762342453003},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5633566379547119},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5598160624504089},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4901733994483948},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.473240464925766},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4157545566558838},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.41196703910827637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10895344614982605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363254070281982},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6136187314987183},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5801762342453003},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5633566379547119},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5598160624504089},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4901733994483948},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.473240464925766},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4157545566558838},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41196703910827637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10895344614982605},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00778-021-00726-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-021-00726-w","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/a87cddc2-b9cf-4db4-8981-02ea705f54ff","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/data-distribution-debugging-in-machine-learning-pipelines(a87cddc2-b9cf-4db4-8981-02ea705f54ff).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grafberger, S, Groth, P, Stoyanovich, J & Schelter, S 2022, 'Data distribution debugging in machine learning pipelines', VLDB Journal, vol. 31, no. 5, pp. 1103-1126. https://doi.org/10.1007/s00778-021-00726-w","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/a87cddc2-b9cf-4db4-8981-02ea705f54ff","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/data-distribution-debugging-in-machine-learning-pipelines(a87cddc2-b9cf-4db4-8981-02ea705f54ff).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grafberger, S, Groth, P, Stoyanovich, J & Schelter, S 2022, 'Data distribution debugging in machine learning pipelines', VLDB Journal, vol. 31, no. 5, pp. 1103-1126. https://doi.org/10.1007/s00778-021-00726-w","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3257745963","display_name":"Collaborative Research: Framework for Integrative Data Equity Systems","funder_award_id":"1934464","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5693414920","display_name":"NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science Impact","funder_award_id":"1922658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5997955468","display_name":"CAREER: Querying Evolving Graphs","funder_award_id":"1916505","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1545590260","https://openalex.org/W1906647448","https://openalex.org/W2030433745","https://openalex.org/W2101565274","https://openalex.org/W2133986470","https://openalex.org/W2143102052","https://openalex.org/W2157814900","https://openalex.org/W2167541073","https://openalex.org/W2293299776","https://openalex.org/W2302501749","https://openalex.org/W2547386789","https://openalex.org/W2612758631","https://openalex.org/W2613597870","https://openalex.org/W2614986686","https://openalex.org/W2616028256","https://openalex.org/W2705062272","https://openalex.org/W2730550703","https://openalex.org/W2752857821","https://openalex.org/W2766945679","https://openalex.org/W2798497570","https://openalex.org/W2889249015","https://openalex.org/W2895471314","https://openalex.org/W2896331720","https://openalex.org/W2897042519","https://openalex.org/W2910185446","https://openalex.org/W2913771223","https://openalex.org/W2948234719","https://openalex.org/W3032244227","https://openalex.org/W3033733989","https://openalex.org/W3082494217","https://openalex.org/W3086663505","https://openalex.org/W3100279624","https://openalex.org/W3104279192","https://openalex.org/W4206220710","https://openalex.org/W4249285655","https://openalex.org/W4365786623","https://openalex.org/W6614148910","https://openalex.org/W6675354045","https://openalex.org/W6749630143"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
