{"id":"https://openalex.org/W2948985893","doi":"https://doi.org/10.1145/3299869.3300066","title":"Going Beyond Provenance","display_name":"Going Beyond Provenance","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948985893","doi":"https://doi.org/10.1145/3299869.3300066","mag":"2948985893","pmid":"https://pubmed.ncbi.nlm.nih.gov/31983802"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3300066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087858861","display_name":"Zhengjie Miao","orcid":"https://orcid.org/0009-0008-2371-1186"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengjie Miao","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043590893","display_name":"Qitian Zeng","orcid":"https://orcid.org/0009-0001-2969-5614"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qitian Zeng","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061858093","display_name":"Boris Glavic","orcid":"https://orcid.org/0000-0003-2887-2452"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Glavic","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110322079","display_name":"Sudeepa Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudeepa Roy","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087858861"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":5.7328,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96748074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2019","issue":null,"first_page":"485","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"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":0.9988999962806702,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9968000054359436,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.86513352394104},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.8068374395370483},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.7651247978210449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665615439414978},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6603407263755798},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4261326789855957},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41052088141441345},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.391870379447937},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.330846905708313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20507612824440002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17657896876335144},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08542275428771973},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06797707080841064}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.86513352394104},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.8068374395370483},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.7651247978210449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665615439414978},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6603407263755798},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4261326789855957},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41052088141441345},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.391870379447937},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.330846905708313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20507612824440002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17657896876335144},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08542275428771973},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06797707080841064},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3299869.3300066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmid:31983802","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31983802","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. ACM-SIGMOD International Conference on Management of Data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6980245","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6980245","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc ACM SIGMOD Int Conf Manag Data","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3299869.3300066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3300066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3300066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1016153788","display_name":null,"funder_award_id":"IIS-1552538, IIS-1703431, OAC-1541450, OAC- 1640864, SMA-1637155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1091353656","display_name":null,"funder_award_id":"R01EB025021","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1115504830","display_name":null,"funder_award_id":"1R01EB025021- 01","funder_id":"https://openalex.org/F4320337376","funder_display_name":"NIH Clinical Center"},{"id":"https://openalex.org/G2401033971","display_name":null,"funder_award_id":"21-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G254791556","display_name":null,"funder_award_id":"SMA-1637155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3499912885","display_name":null,"funder_award_id":"1703431","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4081764933","display_name":null,"funder_award_id":"1R01EB025021","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4213323792","display_name":null,"funder_award_id":"1552538","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4724187317","display_name":"RIDIR: Collaborative Research: Developing and Deploying SKOPE--A resource for Synthesizing Knowledge of Past Environments","funder_award_id":"1637155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5106706385","display_name":null,"funder_award_id":"1541450","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5456246324","display_name":null,"funder_award_id":"OAC-1640864","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7478733536","display_name":null,"funder_award_id":"1640864","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8302243993","display_name":null,"funder_award_id":"1R01EB025021-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8720393765","display_name":null,"funder_award_id":"IIS-1552538, IIS-1703431","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"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337376","display_name":"NIH Clinical Center","ror":"https://ror.org/04vfsmv21"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948985893.pdf","grobid_xml":"https://content.openalex.org/works/W2948985893.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W335227069","https://openalex.org/W1491318920","https://openalex.org/W1506285740","https://openalex.org/W1552694902","https://openalex.org/W1565838812","https://openalex.org/W1983178058","https://openalex.org/W1989418877","https://openalex.org/W1989783863","https://openalex.org/W2001108980","https://openalex.org/W2008806832","https://openalex.org/W2022171653","https://openalex.org/W2024834471","https://openalex.org/W2031648200","https://openalex.org/W2034562813","https://openalex.org/W2045487373","https://openalex.org/W2047182010","https://openalex.org/W2048372226","https://openalex.org/W2048864522","https://openalex.org/W2061122559","https://openalex.org/W2074663022","https://openalex.org/W2103201239","https://openalex.org/W2118370002","https://openalex.org/W2124026371","https://openalex.org/W2124278683","https://openalex.org/W2131920243","https://openalex.org/W2137130182","https://openalex.org/W2140190241","https://openalex.org/W2143102052","https://openalex.org/W2143401113","https://openalex.org/W2150950420","https://openalex.org/W2160382748","https://openalex.org/W2165727725","https://openalex.org/W2166709576","https://openalex.org/W2167541073","https://openalex.org/W2266772167","https://openalex.org/W2293299776","https://openalex.org/W2294059532","https://openalex.org/W2294212155","https://openalex.org/W2402668406","https://openalex.org/W2504196632","https://openalex.org/W2507345993","https://openalex.org/W2606811865","https://openalex.org/W2610226709","https://openalex.org/W2751899011","https://openalex.org/W2789980099","https://openalex.org/W2792917140","https://openalex.org/W2797532987","https://openalex.org/W2963707382","https://openalex.org/W4246215794","https://openalex.org/W4254420769","https://openalex.org/W6684420323"],"related_works":["https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613","https://openalex.org/W2380057024"],"abstract_inverted_index":{"Provenance":[0],"and":[1,49,124,127,132],"intervention-based":[2],"techniques":[3,19],"have":[4],"been":[5],"used":[6],"to":[7,119,122],"explain":[8],"surprisingly":[9],"high":[10],"or":[11],"low":[12,37],"outcomes":[13],"of":[14,39,41,58,89,92,134],"aggregation":[15,76],"queries.":[16],"However,":[17],"such":[18,112],"may":[20],"miss":[21],"interesting":[22],"explanations":[23,82],"emerging":[24],"from":[25],"data":[26,103],"that":[27,99],"is":[28],"<i>not</i>":[29],"in":[30,45,60,63,75,85,104],"the":[31,64,86,90,102,130],"provenance.":[32],"For":[33],"instance,":[34],"an":[35,55],"unusually":[36],"number":[38,57],"publications":[40,59],"a":[42,46,69],"prolific":[43],"researcher":[44],"certain":[47],"venue":[48,62],"year":[50],"can":[51],"be":[52],"explained":[53],"by":[54],"increased":[56],"another":[61],"same":[65],"year.":[66],"We":[67,106],"present":[68,107],"novel":[70],"approach":[71],"for":[72,110],"explaining":[73],"outliers":[74,84],"queries":[77],"through":[78],"<i>counter-balancing</i>.":[79],"That":[80],"is,":[81],"are":[83,95],"opposite":[87],"direction":[88],"outlier":[91],"interest.":[93],"Outliers":[94],"defined":[96],"w.r.t.":[97],"patterns":[98],"hold":[100],"over":[101],"aggregate.":[105],"efficient":[108],"methods":[109],"mining":[111],"<i>aggregate":[113],"regression":[114],"patterns</i>":[115],"(<i>ARPs</i>),":[116],"discuss":[117],"how":[118],"use":[120],"ARPs":[121],"generate":[123],"rank":[125],"explanations,":[126],"experimentally":[128],"demonstrate":[129],"efficiency":[131],"effectiveness":[133],"our":[135],"approach.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-06-14T00:00:00"}