{"id":"https://openalex.org/W4379390538","doi":"https://doi.org/10.1145/3555041.3589682","title":"Proactively Screening Machine Learning Pipelines with ARGUSEYES","display_name":"Proactively Screening Machine Learning Pipelines with ARGUSEYES","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4379390538","doi":"https://doi.org/10.1145/3555041.3589682"},"language":"en","primary_location":{"id":"doi:10.1145/3555041.3589682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3555041.3589682","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589682","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","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/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":"https://orcid.org/0000-0002-9884-9517","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/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":"Shubha Guha","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9156-1561","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/A5025073517","display_name":"Bojan Karla\u0161","orcid":"https://orcid.org/0000-0002-6462-3579"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bojan Karlas","raw_affiliation_strings":["Harvard University, Boston, MA, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6462-3579","affiliations":[{"raw_affiliation_string":"Harvard University, Boston, MA, Switzerland","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8105-7505","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8312,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9237333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9930999875068665,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9926999807357788,"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/pipeline-transport","display_name":"Pipeline transport","score":0.8366249799728394},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.8192577362060547},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7942132353782654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7581110596656799},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6619188189506531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5284362435340881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47821399569511414},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4300106167793274},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3873451352119446},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2470584213733673},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15787273645401},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14589840173721313}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.8366249799728394},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.8192577362060547},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7942132353782654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581110596656799},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6619188189506531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5284362435340881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47821399569511414},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4300106167793274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3873451352119446},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2470584213733673},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15787273645401},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14589840173721313},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3555041.3589682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3555041.3589682","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589682","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/f69b84fe-5b7e-4c80-b8f3-72f6bb25e9f7","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/proactively-screening-machine-learning-pipelines-with-arguseyes(f69b84fe-5b7e-4c80-b8f3-72f6bb25e9f7).html","pdf_url":"https://pure.uva.nl/ws/files/142715153/3555041.3589682.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Schelter, S, Grafberger, S, Guha, S, Karla\u0161, B & Zhang, C 2023, Proactively Screening Machine Learning Pipelines with ArgusEyes. in SIGMOD '23 Companion : Companion of the 2023 ACM/SIGMOD International Conference on Management of Data : June 18-23, 2023, Seattle, WA, USA. Association for Computing Machinery, New York, NY, pp. 91\u201394, 2023 ACM/SIGMOD International Conference on Management of Data, Seattle, Washington, United States, 18/06/23. https://doi.org/10.1145/3555041.3589682","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/620202","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/620202","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGMOD '23: Companion of the 2023 International Conference on Management of Data","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.3929/ethz-b-000620202","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000620202","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3555041.3589682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3555041.3589682","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3555041.3589682","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379390538.pdf","grobid_xml":"https://content.openalex.org/works/W4379390538.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2132862423","https://openalex.org/W2293299776","https://openalex.org/W2613597870","https://openalex.org/W2970773487","https://openalex.org/W3166319166","https://openalex.org/W3173683037"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Software":[0],"systems":[1],"that":[2],"learn":[3],"from":[4,19],"data":[5,27,68,98,128],"with":[6],"machine":[7],"learning":[8],"(ML)":[9],"are":[10,47],"ubiquitous.":[11],"ML":[12,74,89],"pipelines":[13,75,90],"in":[14,51,59,122,130,139],"these":[15],"applications":[16],"often":[17],"suffer":[18],"a":[20,64,123,131,140],"variety":[21],"of":[22,81],"data-related":[23,77],"issues,":[24,95],"such":[25],"as":[26,79],"leakage,":[28],"label":[29],"errors":[30],"or":[31],"fairness":[32,137],"violations,":[33],"which":[34,66],"require":[35],"reasoning":[36],"about":[37],"complex":[38],"dependencies":[39],"between":[40],"their":[41,73,101],"inputs":[42],"and":[43,87,96,100,135],"outputs.":[44],"These":[45],"issues":[46,78],"usually":[48],"only":[49],"detected":[50],"hindsight":[52],"after":[53,55],"deployment,":[54],"they":[56],"caused":[57],"harm":[58],"production.":[60,111],"We":[61,112],"demonstrate":[62,113],"ArgusEyes,":[63],"system":[65,115],"enables":[67],"scientists":[69],"to":[70,103,110],"proactively":[71],"screen":[72],"for":[76,91,116],"part":[80],"continuous":[82],"integration.":[83],"ArgusEyes":[84],"instruments,":[85],"executes":[86],"screens":[88],"declaratively":[92],"specified":[93],"pipeline":[94],"analyzes":[97],"artifacts":[99],"provenance":[102],"catch":[104],"potential":[105],"problems":[106],"early":[107],"before":[108],"deployment":[109],"our":[114],"three":[117],"scenarios:":[118],"detecting":[119],"mislabeled":[120],"images":[121],"computer":[124],"vision":[125],"pipeline,":[126,134],"spotting":[127],"leakage":[129],"price":[132],"prediction":[133],"addressing":[136],"violations":[138],"credit":[141],"scoring":[142],"pipeline.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}