{"id":"https://openalex.org/W2154707336","doi":"https://doi.org/10.1145/1183614.1183699","title":"Estimating corpus size via queries","display_name":"Estimating corpus size via queries","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2154707336","doi":"https://doi.org/10.1145/1183614.1183699","mag":"2154707336"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","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/A5108541542","display_name":"Andrei Broder","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Broder","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004492569","display_name":"Marcus Fontura","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcus Fontura","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103723876","display_name":"Ravi Kumar","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Kumar","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112649653","display_name":"Rajeev Motwani","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajeev Motwani","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084411242","display_name":"Shubha U. Nabar","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubha Nabar","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085651536","display_name":"Rina Panigrahy\u200e","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rina Panigrahy","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068021191","display_name":"Andrew Tomkins","orcid":"https://orcid.org/0000-0002-1611-9255"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Tomkins","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075489504","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-2881-7093"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.9525,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98239748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"594","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.996399998664856,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7335265874862671},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7026814818382263},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6591420769691467},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6104720830917358},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.51481693983078},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47712278366088867},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47315630316734314},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4517797529697418},{"id":"https://openalex.org/keywords/degree","display_name":"Degree (music)","score":0.4110088348388672},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37396425008773804},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33984923362731934},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32036328315734863},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23094701766967773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21431589126586914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335265874862671},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7026814818382263},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6591420769691467},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6104720830917358},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.51481693983078},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47712278366088867},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47315630316734314},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4517797529697418},{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.4110088348388672},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37396425008773804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33984923362731934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32036328315734863},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23094701766967773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21431589126586914},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1183614.1183699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.515.864","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.515.864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://fontoura.org/papers/cikm2006.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.8688","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.8688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/~sunabar/app/samplePaper3.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":14,"referenced_works":["https://openalex.org/W1510634602","https://openalex.org/W1594076980","https://openalex.org/W1605217017","https://openalex.org/W1983416950","https://openalex.org/W1986828474","https://openalex.org/W1997438973","https://openalex.org/W2028716813","https://openalex.org/W2060088491","https://openalex.org/W2080676333","https://openalex.org/W2087303323","https://openalex.org/W2107252390","https://openalex.org/W2128941908","https://openalex.org/W2147164982","https://openalex.org/W2155711776"],"related_works":["https://openalex.org/W3161230432","https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W1487201914","https://openalex.org/W3122602933","https://openalex.org/W2950038056","https://openalex.org/W1544940847","https://openalex.org/W2289285490","https://openalex.org/W2221502901"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,6,34,50,92,116,119,124,129,146],"problem":[3],"of":[4,8,11,36,39,64,89,111,118,126,132,148],"estimating":[5,78],"size":[7,35],"a":[9,15,59,85,135],"collection":[10,138],"documents":[12,40,90],"using":[13],"only":[14],"standard":[16],"query":[17,57,62,114],"interface.":[18],"Our":[19],"main":[20],"idea":[21],"is":[22],"to":[23,77],"construct":[24],"an":[25],"unbiased":[26],"and":[27,104,139],"low-variance":[28],"estimator":[29],"that":[30,46],"can":[31],"closely":[32],"approximate":[33],"any":[37],"set":[38,51],"defined":[41],"by":[42],"certain":[43],"conditions,":[44],"including":[45],"each":[47],"document":[48],"in":[49,68],"must":[52],"match":[53],"at":[54],"least":[55],"one":[56],"from":[58,91],"uniformly":[60],"sampleable":[61],"pool":[63],"known":[65],"size,":[66],"fixed":[67],"advance.Using":[69],"this":[70,98],"basic":[71],"estimator,":[72],"we":[73],"propose":[74],"two":[75,107,130],"approaches":[76],"corpus":[79],"size.":[80],"The":[81,94],"first":[82],"approach":[83,96,121],"requires":[84],"uniform":[86],"random":[87],"sample":[88,101],"corpus.":[93],"second":[95,120],"avoids":[97],"notoriously":[99],"difficult":[100],"generation":[102],"problem,":[103],"instead":[105],"uses":[106],"fairly":[108],"uncorrelated":[109],"sets":[110,131],"terms":[112],"as":[113],"pools;":[115],"accuracy":[117],"depends":[122],"on":[123,134,140],"degree":[125],"correlation":[127],"among":[128],"terms.Experiments":[133],"large":[136],"TREC":[137],"three":[141],"major":[142],"search":[143],"engines":[144],"demonstrates":[145],"effectiveness":[147],"our":[149],"algorithms.":[150]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}