{"id":"https://openalex.org/W3173683037","doi":"https://doi.org/10.1145/3448016.3452759","title":"MLINSPECT: A Data Distribution Debugger for Machine Learning Pipelines","display_name":"MLINSPECT: A Data Distribution Debugger for Machine Learning Pipelines","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3173683037","doi":"https://doi.org/10.1145/3448016.3452759","mag":"3173683037"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3452759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3452759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3452759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","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/10.1145/3448016.3452759","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":true,"raw_author_name":"Stefan Grafberger","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"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/A5066160649","display_name":"Shubha Guha","orcid":"https://orcid.org/0000-0002-9156-1561"},"institutions":[{"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"]},{"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"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shubha Guha","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"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 City, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, 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":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"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":4,"corresponding_author_ids":["https://openalex.org/A5081322278"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":4.4675,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94707282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2736","last_page":"2739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9927999973297119,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9732000231742859,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/debugger","display_name":"Debugger","score":0.8240336775779724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7788594365119934},{"id":"https://openalex.org/keywords/accountability","display_name":"Accountability","score":0.587540328502655},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5419491529464722},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5064784288406372},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4145132005214691},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3971768915653229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38287171721458435},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38272345066070557},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.3785246014595032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3378940522670746},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.33165794610977173},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2814054489135742},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10982358455657959}],"concepts":[{"id":"https://openalex.org/C2778485113","wikidata":"https://www.wikidata.org/wiki/Q193231","display_name":"Debugger","level":3,"score":0.8240336775779724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788594365119934},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.587540328502655},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5419491529464722},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5064784288406372},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4145132005214691},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3971768915653229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38287171721458435},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38272345066070557},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3785246014595032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3378940522670746},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33165794610977173},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2814054489135742},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10982358455657959},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3448016.3452759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3452759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3452759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/9ac83210-cdf3-4ff3-a16d-bfcf2087ab17","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mlinspect-a-data-distribution-debugger-for-machine-learning-pipelines(9ac83210-cdf3-4ff3-a16d-bfcf2087ab17).html","pdf_url":"https://pure.uva.nl/ws/files/69440449/3448016.3452759.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grafberger, S, Guha, S, Stoyanovich, J & Schelter, S 2021, MLINSPECT: A Data Distribution Debugger for Machine Learning Pipelines. in SIGMOD '21 : proceedings of the 2021 International Conference on the Management of Data : June 20 -25, 2021, virtual event, China. Association for Computing Machinery, New York, NY, pp. 2736\u20132739, 2021 International Conference on the Management of Data, China, 20/06/21. https://doi.org/10.1145/3448016.3452759","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/9ac83210-cdf3-4ff3-a16d-bfcf2087ab17","is_oa":true,"landing_page_url":"http://hdl.handle.net/11245.1/9ac83210-cdf3-4ff3-a16d-bfcf2087ab17","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grafberger, S, Guha, S, Stoyanovich, J & Schelter, S 2021, MLINSPECT: A Data Distribution Debugger for Machine Learning Pipelines. in SIGMOD '21 : proceedings of the 2021 International Conference on the Management of Data : June 20 -25, 2021, virtual event, China. Association for Computing Machinery, New York, NY, pp. 2736\u20132739, 2021 International Conference on the Management of Data, China, 20/06/21. https://doi.org/10.1145/3448016.3452759","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/9ac83210-cdf3-4ff3-a16d-bfcf2087ab17","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/mlinspect-a-data-distribution-debugger-for-machine-learning-pipelines(9ac83210-cdf3-4ff3-a16d-bfcf2087ab17).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGMOD '21: proceedings of the 2021 International Conference on the Management of Data : June 20 -25, 2021, virtual event, China","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.1145/3448016.3452759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3452759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3452759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6785385282","display_name":null,"funder_award_id":"1926250, 1934464, 1922658","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3173683037.pdf","grobid_xml":"https://content.openalex.org/works/W3173683037.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2791094827","https://openalex.org/W2927176210","https://openalex.org/W2964256806","https://openalex.org/W2989755645","https://openalex.org/W2996282314","https://openalex.org/W3033733989","https://openalex.org/W3086663505","https://openalex.org/W3177439614","https://openalex.org/W6783187084"],"related_works":["https://openalex.org/W2800641345","https://openalex.org/W2886673879","https://openalex.org/W564953056","https://openalex.org/W2061184006","https://openalex.org/W2381239448","https://openalex.org/W4236910510","https://openalex.org/W2092932442","https://openalex.org/W2543963479","https://openalex.org/W1751798423","https://openalex.org/W2583000271"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"(ML)":[2],"is":[3],"increasingly":[4],"used":[5],"to":[6,35,41],"automate":[7],"impactful":[8],"decisions,":[9],"and":[10,24,47],"the":[11,25],"risks":[12],"arising":[13],"from":[14,21],"this":[15],"wide-spread":[16],"use":[17],"are":[18,29],"garnering":[19],"attention":[20],"policymakers,":[22],"scientists,":[23],"media.":[26],"ML":[27],"applications":[28],"often":[30],"very":[31],"brittle":[32],"with":[33],"respect":[34],"their":[36,44],"input":[37],"data,":[38],"which":[39],"leads":[40],"concerns":[42],"about":[43],"reliability,":[45],"accountability,":[46],"fairness.":[48],"While":[49],"bias":[50],"detection":[51],"cannot":[52],"be":[53],"fully":[54],"automated,":[55],"computational":[56],"tools":[57],"can":[58],"help":[59],"pinpoint":[60],"particular":[61],"types":[62],"of":[63],"data":[64],"issues.":[65]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}