{"id":"https://openalex.org/W2107422095","doi":"https://doi.org/10.1145/1066157.1066222","title":"A disk-based join with probabilistic guarantees","display_name":"A disk-based join with probabilistic guarantees","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2107422095","doi":"https://doi.org/10.1145/1066157.1066222","mag":"2107422095"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 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/A5109437922","display_name":"Christopher Jermaine","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Jermaine","raw_affiliation_strings":["University of Florida, Gainesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008335723","display_name":"Alin Dobra","orcid":"https://orcid.org/0000-0003-2033-9952"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alin Dobra","raw_affiliation_strings":["University of Florida, Gainesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103467344","display_name":"Subramanian Arumugam","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subramanian Arumugam","raw_affiliation_strings":["University of Florida, Gainesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112000383","display_name":"Shantanu Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shantanu Joshi","raw_affiliation_strings":["University of Florida, Gainesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022320149","display_name":"Abhijit Pol","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhijit Pol","raw_affiliation_strings":["University of Florida, Gainesville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3693,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.84760562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9907000064849854,"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/join","display_name":"Join (topology)","score":0.9115514755249023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7939058542251587},{"id":"https://openalex.org/keywords/sort-merge-join","display_name":"Sort-merge join","score":0.682936429977417},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6637430191040039},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.5025215148925781},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5006358623504639},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4614618420600891},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4569895267486572},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.4342677593231201},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42737945914268494},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4229177236557007},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4146155118942261},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4144338369369507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3728470206260681},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33927905559539795},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.21551969647407532},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1517491638660431},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11343622207641602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10882270336151123},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.10277271270751953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09673085808753967},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.0883888304233551}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.9115514755249023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939058542251587},{"id":"https://openalex.org/C203570394","wikidata":"https://www.wikidata.org/wiki/Q4060688","display_name":"Sort-merge join","level":3,"score":0.682936429977417},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6637430191040039},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.5025215148925781},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5006358623504639},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4614618420600891},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4569895267486572},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.4342677593231201},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42737945914268494},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4229177236557007},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4146155118942261},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4144338369369507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3728470206260681},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33927905559539795},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.21551969647407532},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1517491638660431},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11343622207641602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10882270336151123},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.10277271270751953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09673085808753967},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0883888304233551},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1066157.1066222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.7455","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.7455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cise.ufl.edu/~adobra/Publications/p563-jermaine.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.9616","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.9616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cise.ufl.edu/~cjermain/429.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1513100972","https://openalex.org/W1858414509","https://openalex.org/W1964857063","https://openalex.org/W1988144572","https://openalex.org/W2020147322","https://openalex.org/W2073479529","https://openalex.org/W2090403603","https://openalex.org/W2095891890","https://openalex.org/W2132808937","https://openalex.org/W2151663987","https://openalex.org/W2153834102","https://openalex.org/W2154165046","https://openalex.org/W2167811976","https://openalex.org/W2169486917","https://openalex.org/W2197881366","https://openalex.org/W2296677182","https://openalex.org/W4229903866","https://openalex.org/W4237172715","https://openalex.org/W4246899237","https://openalex.org/W4251258520"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W2469706965","https://openalex.org/W4234452035","https://openalex.org/W1866159721","https://openalex.org/W1589496614","https://openalex.org/W1989231289","https://openalex.org/W3033055359","https://openalex.org/W1525319740","https://openalex.org/W2278647566"],"abstract_inverted_index":{"One":[0],"of":[1,13,20,44,78],"the":[2,11,18,30,59,63,76,79,86,91,96,138],"most":[3],"common":[4,112],"operations":[5],"in":[6],"analytic":[7],"query":[8,35],"processing":[9],"is":[10,47,106],"application":[12],"an":[14,26,54],"aggregate":[15],"function":[16],"to":[17,32,62,98],"result":[19],"a":[21,34,72,101],"relational":[22],"join.":[23],"We":[24],"describe":[25],"algorithm":[27,46,97],"for":[28,58],"computing":[29],"answer":[31,61],"such":[33,127],"over":[36],"large,":[37],"disk-based":[38],"input":[39,139],"tables.":[40],"The":[41],"key":[42],"innovation":[43],"our":[45],"that":[48,105],"at":[49],"all":[50],"times,":[51],"it":[52],"provides":[53],"online,":[55],"statistical":[56,128],"estimator":[57],"eventual":[60],"query,":[64],"as":[65,67,137],"well":[66],"probabilistic":[68],"confidence":[69],"bounds.":[70],"Thus,":[71],"user":[73],"can":[74,131,141],"monitor":[75],"progress":[77],"join":[80,87,113,120],"throughout":[81],"its":[82],"execution":[83],"and":[84],"stop":[85],"when":[88],"satisfied":[89],"with":[90,100,117],"estimate's":[92],"accuracy,":[93],"or":[94,130],"run":[95],"completion":[99],"total":[102],"time":[103],"requirement":[104],"not":[107,125],"much":[108],"longer":[109],"than":[110],"other":[111,118],"algorithms.":[114],"This":[115],"contrasts":[116],"online":[119],"algorithms,":[121],"which":[122],"either":[123],"do":[124],"offer":[126,133],"guarantees":[129,134],"only":[132],"so":[135],"long":[136],"data":[140],"fit":[142],"into":[143],"core":[144],"memory.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
