{"id":"https://openalex.org/W2047182010","doi":"https://doi.org/10.14778/2536354.2536356","title":"Scorpion","display_name":"Scorpion","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2047182010","doi":"https://doi.org/10.14778/2536354.2536356","mag":"2047182010"},"language":"en","primary_location":{"id":"doi:10.14778/2536354.2536356","is_oa":true,"landing_page_url":"https://doi.org/10.14778/2536354.2536356","pdf_url":"https://dl.acm.org/doi/pdf/10.14778/2536354.2536356","source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.14778/2536354.2536356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":20.0519,"has_fulltext":true,"cited_by_count":242,"citation_normalized_percentile":{"value":0.99228357,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"6","issue":"8","first_page":"553","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9940999746322632,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9811000227928162,"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/outlier","display_name":"Outlier","score":0.807948887348175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7452291250228882},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6529773473739624},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5576733350753784},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5568768978118896},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5046714544296265},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.50393146276474},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4501195549964905},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4354035258293152},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3721885085105896},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3310166895389557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21649304032325745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16609284281730652}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.807948887348175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452291250228882},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6529773473739624},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5576733350753784},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5568768978118896},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5046714544296265},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.50393146276474},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4501195549964905},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4354035258293152},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3721885085105896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3310166895389557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21649304032325745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16609284281730652},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2536354.2536356","is_oa":true,"landing_page_url":"https://doi.org/10.14778/2536354.2536356","pdf_url":"https://dl.acm.org/doi/pdf/10.14778/2536354.2536356","source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/89076","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/89076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.14778/2536354.2536356","is_oa":true,"landing_page_url":"https://doi.org/10.14778/2536354.2536356","pdf_url":"https://dl.acm.org/doi/pdf/10.14778/2536354.2536356","source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4101552011","display_name":"III: Large: Collaborative Research: SciDB - An Array Oriented Data Management System for Massive Scale Scientific Data","funder_award_id":"1110370","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2047182010.pdf","grobid_xml":"https://content.openalex.org/works/W2047182010.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1491318920","https://openalex.org/W1562570268","https://openalex.org/W1565838812","https://openalex.org/W1977496278","https://openalex.org/W1983178058","https://openalex.org/W2018978908","https://openalex.org/W2044547639","https://openalex.org/W2074663022","https://openalex.org/W2103201239","https://openalex.org/W2113411758","https://openalex.org/W2115010808","https://openalex.org/W2118370002","https://openalex.org/W2119387367","https://openalex.org/W2122885251","https://openalex.org/W2124278683","https://openalex.org/W2125806118","https://openalex.org/W2173213060","https://openalex.org/W2625773614","https://openalex.org/W2749745318","https://openalex.org/W2949588900","https://openalex.org/W2950416404","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2154338319","https://openalex.org/W2136814519","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729","https://openalex.org/W4390662392","https://openalex.org/W71955863","https://openalex.org/W2359185137"],"abstract_inverted_index":{"Database":[0],"users":[1],"commonly":[2],"explore":[3],"large":[4],"data":[5,14,44,187,197,217],"sets":[6,188],"by":[7],"running":[8],"aggregate":[9,94],"queries":[10],"that":[11,34,74,77,84,102,114,164,177],"project":[12],"the":[13,26,42,64,68,104,111,119,132,136,141,172],"down":[15],"to":[16,36,56,63,76,117,131,138],"a":[17,54,82,86,149,154,157,190,194,206,215],"smaller":[18],"number":[19],"of":[20,41,67,88,108,110,151,153,202],"points":[21,91],"and":[22,24,48,99,160,193,199],"dimensions,":[23],"visualizing":[25],"results.":[27,122],"Often,":[28],"such":[29,145],"visualizations":[30],"will":[31],"reveal":[32],"outliers":[33,105,137,183],"correspond":[35,75],"errors":[37],"or":[38],"surprising":[39],"features":[40],"input":[43,72,98,112,133,173],"set.":[45,218],"Unfortunately,":[46],"databases":[47],"visualization":[49],"systems":[50],"do":[51],"not":[52],"provide":[53],"way":[55],"work":[57],"backwards":[58],"from":[59,140],"an":[60,93],"outlier":[61,90,121],"point":[62],"common":[65],"properties":[66,109],"(possibly":[69],"many)":[70],"unaggregated":[71],"tuples":[73,113],"outlier.":[78],"We":[79,175],"propose":[80],"Scorpion,":[81],"system":[83],"takes":[85],"set":[87],"user-specified":[89],"in":[92,106,184],"query":[95],"result":[96],"as":[97],"finds":[100],"predicates":[101,127,170],"explain":[103],"terms":[107],"are":[115],"used":[116],"compute":[118],"selected":[120],"Specifically,":[123],"this":[124],"explanation":[125],"identifies":[126],"that,":[128],"when":[129],"applied":[130],"data,":[134],"cause":[135],"disappear":[139],"output.":[142],"To":[143],"find":[144,182],"predicates,":[146],"we":[147],"develop":[148],"notion":[150],"influence":[152,169],"predicate":[155],"on":[156,214],"given":[158],"output,":[159],"design":[161],"several":[162],"algorithms":[163,179],"efficiently":[165],"search":[166,208],"for":[167],"maximum":[168],"over":[171],"data.":[174],"show":[176],"these":[178],"can":[180],"quickly":[181],"two":[185],"real":[186],"(from":[189],"sensor":[191],"deployment":[192],"campaign":[195],"finance":[196],"set),":[198],"run":[200],"orders":[201],"magnitude":[203],"faster":[204],"than":[205],"naive":[207],"algorithm":[209],"while":[210],"providing":[211],"comparable":[212],"quality":[213],"synthetic":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":43},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2016-06-24T00:00:00"}