{"id":"https://openalex.org/W2271831620","doi":"https://doi.org/10.14778/2732232.2732233","title":"Online ordering of overlapping data sources","display_name":"Online ordering of overlapping data sources","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2271831620","doi":"https://doi.org/10.14778/2732232.2732233","mag":"2271831620"},"language":"en","primary_location":{"id":"doi:10.14778/2732232.2732233","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2732232.2732233","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034687136","display_name":"Mariam Salloum","orcid":"https://orcid.org/0000-0002-8438-339X"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mariam Salloum","raw_affiliation_strings":["UC Riverside"],"affiliations":[{"raw_affiliation_string":"UC Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000947547","display_name":"Vassilis J. Tsotras","orcid":"https://orcid.org/0000-0001-5462-9451"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vassilis J. Tsotras","raw_affiliation_strings":["UC Riverside"],"affiliations":[{"raw_affiliation_string":"UC Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034687136"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":2.2509,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89178438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"3","first_page":"133","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.728049635887146},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5926774144172668},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5888237953186035},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5576415657997131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5258979201316833},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.439119428396225},{"id":"https://openalex.org/keywords/summary-statistics","display_name":"Summary statistics","score":0.43352892994880676},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.41676419973373413},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3688296675682068},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2762313783168793},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1785661280155182},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13496625423431396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728049635887146},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5926774144172668},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5888237953186035},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5576415657997131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5258979201316833},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.439119428396225},{"id":"https://openalex.org/C32792767","wikidata":"https://www.wikidata.org/wiki/Q1370484","display_name":"Summary statistics","level":2,"score":0.43352892994880676},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.41676419973373413},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3688296675682068},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2762313783168793},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1785661280155182},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13496625423431396},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2732232.2732233","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2732232.2732233","pdf_url":null,"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:CiteSeerX.psu:10.1.1.401.1454","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.1454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol7/p133-salloum.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W15637906","https://openalex.org/W45458114","https://openalex.org/W1504025001","https://openalex.org/W1524520778","https://openalex.org/W1602083203","https://openalex.org/W1881594620","https://openalex.org/W1982124942","https://openalex.org/W2026754652","https://openalex.org/W2083293881","https://openalex.org/W2127332265","https://openalex.org/W2157595172","https://openalex.org/W2169753664","https://openalex.org/W2278337674","https://openalex.org/W2989260611"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W4321353421"],"abstract_inverted_index":{"Data":[0,88],"integration":[1],"systems":[2],"offer":[3],"a":[4,9,37,100,106,121],"uniform":[5],"interface":[6],"for":[7,48,145,155],"querying":[8],"large":[10],"number":[11],"of":[12,72,103,115,231],"autonomous":[13],"and":[14,26,79,194,223,229],"heterogeneous":[15],"data":[16,104,112,128,225],"sources.":[17,129],"Ideally,":[18],"answers":[19,34,54],"are":[20,24,44,55,190],"returned":[21],"as":[22,32,76],"sources":[23,43,166,183],"queried":[25,45],"the":[27,42,50,73,86,159,172,177,182,186,196,206],"answer":[28],"list":[29],"is":[30,46,60,82,91,119],"updated":[31],"more":[33],"arrive.":[35],"Choosing":[36],"good":[38],"ordering":[39,197],"in":[40,85,95,105,124],"which":[41,53,90],"critical":[47,211],"increasing":[49],"rate":[51],"at":[52,216],"returned.":[56],"However,":[57],"this":[58,131],"problem":[59],"challenging":[61],"since":[62],"we":[63,133],"often":[64,109,120],"do":[65],"not":[66],"have":[67],"complete":[68],"or":[69],"precise":[70],"statistics":[71,170,200,213],"sources,":[74],"such":[75],"their":[77],"coverage":[78,102],"overlap.":[80],"It":[81],"further":[83],"exacerbated":[84],"Big":[87],"era,":[89],"witnessing":[92],"two":[93],"trends":[94],"Deep-Web":[96],"data:":[97],"first,":[98],"obtaining":[99],"full":[101],"particular":[107],"domain":[108],"requires":[110],"extracting":[111],"from":[113],"thousands":[114],"sources;":[116],"second,":[117],"there":[118],"big":[122],"variation":[123],"overlap":[125],"between":[126,165],"different":[127],"In":[130],"paper":[132],"present":[134],"OASIS":[135,150],",":[136],"an":[137],"O":[138],"nline":[139],"query":[140,203],"A":[141],"nswering":[142],"S":[143],"ystem":[144],"overlapp":[146],"I":[147],"ng":[148],"Sources.":[149],"has":[151],"three":[152],"key":[153],"components":[154],"source":[156],"ordering.":[157],"First,":[158],"Overlap":[160],"Estimation":[161],"component":[162,180,209],"estimates":[163],"overlaps":[164],"according":[167,184],"to":[168,185,192,214],"available":[169],"under":[171],"Maximum":[173],"Entropy":[174],"principle.":[175],"Second,":[176],"Source":[178],"Ordering":[179],"orders":[181],"new":[187],"contribution":[188],"they":[189],"expected":[191],"provide,":[193],"adjusts":[195],"based":[198],"on":[199,220],"collected":[201],"during":[202],"answering.":[204],"Third,":[205],"Statistics":[207],"Enrichment":[208],"selects":[210],"missing":[212],"enrich":[215],"runtime.":[217],"Experimental":[218],"results":[219],"both":[221],"real":[222],"synthetic":[224],"show":[226],"high":[227],"efficiency":[228],"scalability":[230],"our":[232],"algorithm.":[233]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}