{"id":"https://openalex.org/W2083966857","doi":"https://doi.org/10.1145/1562764.1562787","title":"Distinct-value synopses for multiset operations","display_name":"Distinct-value synopses for multiset operations","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2083966857","doi":"https://doi.org/10.1145/1562764.1562787","mag":"2083966857"},"language":"en","primary_location":{"id":"doi:10.1145/1562764.1562787","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1562764.1562787","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"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":"Communications of the ACM","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/A5104043964","display_name":"Kevin Beyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Beyer","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227178","display_name":"Rainer Gemulla","orcid":"https://orcid.org/0000-0003-2762-0050"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rainer Gemulla","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Haas","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036119025","display_name":"Berthold Reinwald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berthold Reinwald","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Sismanis","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104043964"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":6.7744,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.96709416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"52","issue":"10","first_page":"87","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.992900013923645,"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":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiset","display_name":"Multiset","score":0.9307612776756287},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.8220863342285156},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.7396073937416077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6971316933631897},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4883589446544647},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.45998209714889526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2330559492111206},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20498767495155334},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.13217398524284363},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12800046801567078}],"concepts":[{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.9307612776756287},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8220863342285156},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7396073937416077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971316933631897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4883589446544647},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.45998209714889526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2330559492111206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20498767495155334},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.13217398524284363},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12800046801567078},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1562764.1562787","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1562764.1562787","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"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":"Communications of the ACM","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.230.8474","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.8474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mpi-sb.mpg.de/%7Ergemulla/publications/beyer09distinct.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.577.7020","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.577.7020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.almaden.ibm.com/cs/people/peterh/cacm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522055873","https://openalex.org/W1593605342","https://openalex.org/W1785933978","https://openalex.org/W1972074692","https://openalex.org/W1984566373","https://openalex.org/W1992363839","https://openalex.org/W1995437102","https://openalex.org/W2008365755","https://openalex.org/W2025051251","https://openalex.org/W2036035006","https://openalex.org/W2036304306","https://openalex.org/W2047061289","https://openalex.org/W2085845250","https://openalex.org/W2099480861","https://openalex.org/W2111806841","https://openalex.org/W2115215982","https://openalex.org/W2120074607","https://openalex.org/W2123061032","https://openalex.org/W2154324327","https://openalex.org/W2295428206","https://openalex.org/W2500232297","https://openalex.org/W2797333853","https://openalex.org/W2914354916","https://openalex.org/W4231916799"],"related_works":["https://openalex.org/W4300455649","https://openalex.org/W2296588302","https://openalex.org/W4252409532","https://openalex.org/W4328119206","https://openalex.org/W2033245919","https://openalex.org/W2006067547","https://openalex.org/W9228044","https://openalex.org/W4319719380","https://openalex.org/W3025714394","https://openalex.org/W259623631"],"abstract_inverted_index":{"The":[0,83],"task":[1],"of":[2,6,19,38,59,70,125],"estimating":[3],"the":[4,32,36,57,62,73,108],"number":[5,58,69],"distinct":[7],"values":[8],"(DVs)":[9],"in":[10,15,21,34,61,72,88,147],"a":[11,16,49,68,151],"large":[12],"dataset":[13,37],"arises":[14],"wide":[17],"variety":[18],"settings":[20],"computer":[22],"science":[23],"and":[24,66,80,90,98,140,156,162,169],"elsewhere.":[25],"We":[26,44,129],"provide":[27,137],"DV":[28,81,99,133,172],"estimation":[29,153],"techniques":[30],"for":[31,46,101],"case":[33],"which":[35],"interest":[39],"is":[40],"split":[41],"into":[42],"partitions.":[43],"create":[45],"each":[47],"partition":[48,127],"synopsis":[50,145],"that":[51,104,131,159],"can":[52,85,91,121],"be":[53,86,92],"used":[54],"to":[55,95,143,149,165],"estimate":[56],"DVs":[60],"partition.":[63],"By":[64],"combining":[65],"extending":[67],"results":[71],"literature,":[74],"we":[75],"obtain":[76],"both":[77],"suitable":[78],"synopses":[79,84,97,120,161],"estimators.":[82],"created":[87,106],"parallel,":[89],"easily":[93],"combined":[94],"yield":[96],"estimates":[100,173],"\"compound\"":[102],"partitions":[103,110],"are":[105,135],"from":[107],"base":[109],"via":[111],"arbitrary":[112],"multiset":[113],"union,":[114],"intersection,":[115],"or":[116],"difference":[117],"operations.":[118],"Our":[119],"also":[122],"handle":[123],"deletions":[124],"individual":[126],"elements.":[128],"prove":[130],"our":[132,160],"estimators":[134,163],"unbiased,":[136],"error":[138],"bounds,":[139],"show":[141],"how":[142],"select":[144],"sizes":[146],"order":[148],"achieve":[150],"desired":[152],"accuracy.":[154],"Experiments":[155],"theory":[157],"indicate":[158],"lead":[164],"lower":[166],"computational":[167],"costs":[168],"more":[170],"accurate":[171],"than":[174],"previous":[175],"approaches.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}