{"id":"https://openalex.org/W2136014429","doi":"https://doi.org/10.1145/1189769.1189775","title":"The Sort-Merge-Shrink join","display_name":"The Sort-Merge-Shrink join","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2136014429","doi":"https://doi.org/10.1145/1189769.1189775","mag":"2136014429"},"language":"en","primary_location":{"id":"doi:10.1145/1189769.1189775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189769.1189775","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/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":true,"raw_author_name":"Christopher Jermaine","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","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, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","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, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","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, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","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, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109437922"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":1.89,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.8777089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":"4","first_page":"1382","last_page":"1416"},"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":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8690083622932434},{"id":"https://openalex.org/keywords/sort-merge-join","display_name":"Sort-merge join","score":0.8518286943435669},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8310102224349976},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.7274049520492554},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.550078272819519},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.542336642742157},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5183090567588806},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4145805537700653},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3688824772834778},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3455778956413269},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.34159690141677856},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28775882720947266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.19806265830993652},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16514727473258972},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.15468737483024597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09294828772544861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08739626407623291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690083622932434},{"id":"https://openalex.org/C203570394","wikidata":"https://www.wikidata.org/wiki/Q4060688","display_name":"Sort-merge join","level":3,"score":0.8518286943435669},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8310102224349976},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.7274049520492554},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.550078272819519},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.542336642742157},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5183090567588806},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4145805537700653},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3688824772834778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3455778956413269},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.34159690141677856},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28775882720947266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19806265830993652},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16514727473258972},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.15468737483024597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09294828772544861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08739626407623291},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1189769.1189775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189769.1189775","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.5133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.5133","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/~apol/i/smstods.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.7688","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.7688","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/smsRev2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W150801922","https://openalex.org/W1594122454","https://openalex.org/W1858414509","https://openalex.org/W1964857063","https://openalex.org/W1968829657","https://openalex.org/W1972223681","https://openalex.org/W1980417906","https://openalex.org/W1988144572","https://openalex.org/W2013092187","https://openalex.org/W2020147322","https://openalex.org/W2020584928","https://openalex.org/W2034401457","https://openalex.org/W2040063291","https://openalex.org/W2041500280","https://openalex.org/W2073479529","https://openalex.org/W2090403603","https://openalex.org/W2095891890","https://openalex.org/W2099580433","https://openalex.org/W2107422095","https://openalex.org/W2108717033","https://openalex.org/W2132808937","https://openalex.org/W2148706674","https://openalex.org/W2151203234","https://openalex.org/W2151663987","https://openalex.org/W2153834102","https://openalex.org/W2167811976","https://openalex.org/W2169486917","https://openalex.org/W2197881366","https://openalex.org/W2201552871","https://openalex.org/W2296677182","https://openalex.org/W4229903866","https://openalex.org/W4237172715","https://openalex.org/W4241185933","https://openalex.org/W4246899237","https://openalex.org/W4251258520","https://openalex.org/W4253103473","https://openalex.org/W6845883598"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W4234452035","https://openalex.org/W2469706965","https://openalex.org/W4205996836","https://openalex.org/W1866159721","https://openalex.org/W1589496614","https://openalex.org/W3033055359","https://openalex.org/W1989231289","https://openalex.org/W1525319740"],"abstract_inverted_index":{"One":[0],"of":[1,13,20,49,99,133],"the":[2,11,18,29,35,50,56,72,80,84,97,100,107,112,117,161],"most":[3],"common":[4,135],"operations":[5],"in":[6,61],"analytic":[7],"query":[8,40,85],"processing":[9],"is":[10,53,127],"application":[12],"an":[14,26,75],"aggregate":[15],"function":[16],"to":[17,37,83,119],"result":[19],"a":[21,39,62,93,122],"relational":[22],"join.":[23],"We":[24],"describe":[25],"algorithm":[27,118],"called":[28],"Sort-Merge-Shrink":[30],"(SMS)":[31],"Join":[32],"for":[33,79],"computing":[34],"answer":[36,82],"such":[38,150],"over":[41],"large,":[42],"disk-based":[43],"input":[44,57,162],"tables.":[45],"The":[46],"key":[47],"innovation":[48],"SMS":[51],"join":[52,73,101,108,136,143],"that":[54,126,132],"if":[55],"data":[58,163],"are":[59],"clustered":[60],"statistically":[63],"random":[64],"fashion":[65],"on":[66],"disk,":[67],"then":[68],"at":[69],"all":[70],"times,":[71],"provides":[74],"online,":[76],"statistical":[77,151],"estimator":[78],"eventual":[81],"as":[86,88,160],"well":[87],"probabilistic":[89],"confidence":[90],"bounds.":[91],"Thus,":[92],"user":[94],"can":[95,154,164],"monitor":[96],"progress":[98],"throughout":[102],"its":[103],"execution":[104],"and":[105],"stop":[106],"when":[109],"satisfied":[110],"with":[111,121,140],"estimate's":[113],"accuracy":[114],"or":[115,153],"run":[116],"completion":[120],"total":[123],"time":[124],"requirement":[125],"not":[128,148],"much":[129],"longer":[130],"than":[131],"other":[134,141],"algorithms.":[137],"This":[138],"contrasts":[139],"online":[142],"algorithms,":[144],"which":[145],"either":[146],"do":[147],"offer":[149,156],"guarantees":[152,157],"only":[155],"so":[158],"long":[159],"fit":[165],"into":[166],"main":[167],"memory.":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
