{"id":"https://openalex.org/W2022942700","doi":"https://doi.org/10.1145/1007568.1007603","title":"Online maintenance of very large random samples","display_name":"Online maintenance of very large random samples","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2022942700","doi":"https://doi.org/10.1145/1007568.1007603","mag":"2022942700"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 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, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2419,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.94541956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9979000091552734,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.5653528571128845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5653528571128845}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1007568.1007603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.165","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.165","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/JermaineCR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1513100972","https://openalex.org/W1577912117","https://openalex.org/W1595687138","https://openalex.org/W1597561788","https://openalex.org/W1992023276","https://openalex.org/W1998244781","https://openalex.org/W2011679994","https://openalex.org/W2020147322","https://openalex.org/W2020584928","https://openalex.org/W2037701287","https://openalex.org/W2040793975","https://openalex.org/W2068625010","https://openalex.org/W2078907037","https://openalex.org/W2081189989","https://openalex.org/W2082553115","https://openalex.org/W2090403603","https://openalex.org/W2113046370","https://openalex.org/W2117348908","https://openalex.org/W2118924829","https://openalex.org/W2119885577","https://openalex.org/W2145385038","https://openalex.org/W2148706674","https://openalex.org/W2154165046","https://openalex.org/W2169982181","https://openalex.org/W2199389590","https://openalex.org/W2296677182","https://openalex.org/W4229903866","https://openalex.org/W4231287357","https://openalex.org/W4234667859","https://openalex.org/W4241185933","https://openalex.org/W4250212406","https://openalex.org/W4251258520","https://openalex.org/W6630749417","https://openalex.org/W6635637936","https://openalex.org/W6845883598"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Random":[0],"sampling":[1,17],"is":[2,36,40,46],"one":[3],"of":[4,21,64,83,174,176],"the":[5,19,81,159,163,177],"most":[6,13],"fundamental":[7],"data":[8,43,51,91,154,178],"management":[9,92],"tools":[10],"available.":[11],"However,":[12],"current":[14],"research":[15],"involving":[16],"considers":[18],"problem":[20,82],"how":[22,29],"to":[23,30,73],"use":[24],"a":[25,38,41,90,141,149,153,167],"sample,":[26],"and":[27,94],"not":[28],"compute":[31],"one.":[32],"The":[33,129,156],"implicit":[34],"assumption":[35],"that":[37,45,60,122,162],"\"sample\"":[39],"small":[42],"structure":[44],"easily":[47],"maintained":[48,146],"as":[49],"new":[50],"are":[52,123,131,184],"encountered,":[53],"even":[54],"though":[55],"simple":[56],"statistical":[57],"arguments":[58],"demonstrate":[59],"very":[61,85,101],"large":[62,102,142],"samples":[63,88,103,121],"gigabytes":[65,124],"or":[66,125,136,189],"terabytes":[67,126],"in":[68,104,127,148],"size":[69],"can":[70],"be":[71,145,166],"necessary":[72],"provide":[74],"high":[75],"accuracy.":[76],"No":[77],"existing":[78],"work":[79],"tackles":[80],"maintaining":[84,100,119],"large,":[86],"disk-based":[87],"from":[89,108],"perspective,":[93],"no":[95],"techniques":[96],"now":[97],"exist":[98],"for":[99,118,133,137,187],"an":[105],"online":[106,116,147],"manner":[107],"streaming":[109,134],"data.":[110],"In":[111],"this":[112],"paper,":[113],"we":[114],"present":[115],"algorithms":[117,130,157,183],"on-disk":[120],"size.":[128],"designed":[132],"data,":[135],"any":[138],"environment":[139],"where":[140],"sample":[143,164,171],"must":[144],"single":[150],"pass":[151],"through":[152],"set.":[155],"meet":[158],"strict":[160],"requirement":[161],"always":[165],"true,":[168],"statistically":[169],"random":[170],"(without":[172],"replacement)":[173],"all":[175],"processed":[179],"thus":[180],"far.":[181],"Our":[182],"also":[185],"suitable":[186],"biased":[188],"unequal":[190],"probability":[191],"sampling.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
