{"id":"https://openalex.org/W1973266211","doi":"https://doi.org/10.1145/1247480.1247513","title":"Sketching probabilistic data streams","display_name":"Sketching probabilistic data streams","publication_year":2007,"publication_date":"2007-06-11","ids":{"openalex":"https://openalex.org/W1973266211","doi":"https://doi.org/10.1145/1247480.1247513","mag":"1973266211"},"language":"en","primary_location":{"id":"doi:10.1145/1247480.1247513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"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":true,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["AT&amp;T Labs-Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023079617","display_name":"Minos Garofalakis","orcid":"https://orcid.org/0000-0003-0285-3907"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minos Garofalakis","raw_affiliation_strings":["Yahoo! Research and UC Berkeley, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research and UC Berkeley, Santa Clara, CA","institution_ids":["https://openalex.org/I4210134091","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031896681"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":17.0062,"has_fulltext":false,"cited_by_count":156,"citation_normalized_percentile":{"value":0.99293839,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"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"}},{"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9922999739646912,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.8546233773231506},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.8483688831329346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943490743637085},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.750643253326416},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.596203088760376},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.5904037952423096},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48077529668807983},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47347819805145264},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4730343520641327},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3569427728652954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20821556448936462},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.20706763863563538},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.18440264463424683},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15176931023597717}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.8546233773231506},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.8483688831329346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943490743637085},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.750643253326416},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.596203088760376},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.5904037952423096},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48077529668807983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47347819805145264},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4730343520641327},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3569427728652954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20821556448936462},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.20706763863563538},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.18440264463424683},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15176931023597717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1247480.1247513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1553409264","https://openalex.org/W1564015926","https://openalex.org/W1575805590","https://openalex.org/W1785933978","https://openalex.org/W1998783890","https://openalex.org/W2001474264","https://openalex.org/W2006355640","https://openalex.org/W2013092187","https://openalex.org/W2025051251","https://openalex.org/W2050290319","https://openalex.org/W2064379477","https://openalex.org/W2069980026","https://openalex.org/W2075567379","https://openalex.org/W2078686663","https://openalex.org/W2080234606","https://openalex.org/W2083613374","https://openalex.org/W2106163100","https://openalex.org/W2112452856","https://openalex.org/W2129035130","https://openalex.org/W2138729760","https://openalex.org/W2148706674","https://openalex.org/W2156943642","https://openalex.org/W2161118867","https://openalex.org/W2166916904","https://openalex.org/W2170963089","https://openalex.org/W6637957267","https://openalex.org/W6652043732","https://openalex.org/W6684648153"],"related_works":["https://openalex.org/W2151831402","https://openalex.org/W2157032266","https://openalex.org/W2949310134","https://openalex.org/W4253061173","https://openalex.org/W2118924829","https://openalex.org/W2113053869","https://openalex.org/W1496794085","https://openalex.org/W2118370002","https://openalex.org/W2147835952","https://openalex.org/W2595974764"],"abstract_inverted_index":{"The":[0],"management":[1],"of":[2,19,39,50,118,133],"uncertain,":[3],"probabilistic":[4,40,72,93,124,127],"data":[5,25,35,94,128],"has":[6],"recently":[7],"emerged":[8],"as":[9],"a":[10,37,43,103,122,131],"useful":[11],"paradigm":[12],"for":[13,61,71,137],"dealing":[14],"with":[15],"the":[16,116],"inherent":[17],"unreliabilities":[18],"several":[20],"real-world":[21],"application":[22],"domains,":[23],"including":[24],"cleaning,":[26],"information":[27],"integration,":[28],"and":[29,86,97,111,114],"pervasive,":[30],"multi-sensor":[31],"computing.":[32],"Unlike":[33],"conventional":[34],"sets,":[36],"set":[38],"tuples":[41,95],"defines":[42],"probability":[44],"distribution":[45],"over":[46,121],"an":[47],"exponential":[48],"number":[49],"possible":[51],"worlds":[52],"(i.e.,":[53],"\"grounded\",":[54],"deterministic":[55],"databases).":[56],"This":[57],"\"possibleworlds\"":[58],"interpretation":[59],"allows":[60],"clean":[62],"query":[63,74],"semantics":[64],"but":[65],"also":[66],"raises":[67],"hard":[68],"computational":[69],"problems":[70],"database":[73],"processors.":[75],"To":[76],"further":[77],"complicate":[78],"matters,":[79],"in":[80,102],"many":[81],"scenarios":[82],"(e.g.,":[83],"large-scale":[84],"process":[85],"environmental":[87],"monitoring":[88],"using":[89,108],"multiple":[90,119],"sensor":[91],"modalities),":[92],"arrive":[96],"need":[98],"to":[99,141],"be":[100],"processed":[101],"streaming":[104],"fashion;":[105],"that":[106],"is,":[107],"limited":[109],"memory":[110],"CPU":[112],"resources":[113],"without":[115],"benefit":[117],"passes":[120],"static":[123],"database.":[125],"Such":[126],"streams":[129],"raise":[130],"host":[132],"new":[134],"research":[135],"challenges":[136],"stream-processing":[138],"engines":[139],"that,":[140],"date,":[142],"remain":[143],"largely":[144],"unaddressed.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
