{"id":"https://openalex.org/W2115457429","doi":"https://doi.org/10.14778/2350229.2350232","title":"Optimal algorithms for crawling a hidden database in the web","display_name":"Optimal algorithms for crawling a hidden database in the web","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2115457429","doi":"https://doi.org/10.14778/2350229.2350232","mag":"2115457429"},"language":"en","primary_location":{"id":"doi:10.14778/2350229.2350232","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350232","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5102846935","display_name":"Cheng Sheng","orcid":"https://orcid.org/0000-0002-2656-6147"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Sheng","raw_affiliation_strings":["Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641132","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0001-9620-5665"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["George Washington University","george Washington University"],"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048609852","display_name":"Yufei Tao","orcid":"https://orcid.org/0000-0003-3883-5452"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN","KR"],"is_corresponding":false,"raw_author_name":"Yufei Tao","raw_affiliation_strings":["Chinese University of Hong Kong and Korea Advanced Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong and Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101882004","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-8741-5847"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["George Washington University","george Washington University"],"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102846935"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":16.8812,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.9890424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"11","first_page":"1112","last_page":"1123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9973000288009644,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8318796157836914},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.797389805316925},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7437992691993713},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5691708326339722},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5330435633659363},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45524024963378906},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45445939898490906},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.44476518034935},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4388894736766815},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3999553918838501},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3911070227622986},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32729196548461914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12109965085983276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318796157836914},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.797389805316925},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7437992691993713},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5691708326339722},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5330435633659363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45524024963378906},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45445939898490906},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.44476518034935},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4388894736766815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3999553918838501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3911070227622986},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32729196548461914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12109965085983276},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/2350229.2350232","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350232","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.3172","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.3172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vldb.org/pvldb/vol5/p1112_chengsheng_vldb2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.753.9591","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.753.9591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1208.0075.pdf","raw_type":"text"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:607303","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1586176254","https://openalex.org/W1601949013","https://openalex.org/W1985079777","https://openalex.org/W1986828474","https://openalex.org/W2024490588","https://openalex.org/W2027780984","https://openalex.org/W2028574166","https://openalex.org/W2038231646","https://openalex.org/W2041771431","https://openalex.org/W2081948558","https://openalex.org/W2108489852","https://openalex.org/W2118356300","https://openalex.org/W2123853152","https://openalex.org/W2125638313","https://openalex.org/W2131006463","https://openalex.org/W2136059419","https://openalex.org/W2139259611","https://openalex.org/W2148738951","https://openalex.org/W2155569834","https://openalex.org/W2164520297","https://openalex.org/W2170188121","https://openalex.org/W6635193281","https://openalex.org/W6682827647","https://openalex.org/W6685116542","https://openalex.org/W6902931378"],"related_works":["https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W4317382653","https://openalex.org/W3119324922","https://openalex.org/W4390135167","https://openalex.org/W4360873893"],"abstract_inverted_index":{"A":[0],"hidden":[1,71,96],"database":[2],"refers":[3],"to":[4,18,89,138],"a":[5,22,32,65,95,111,145],"dataset":[6],"that":[7,127],"an":[8],"organization":[9],"makes":[10],"accessible":[11],"on":[12,176],"the":[13,46,50,61,84,92,106,118,161,164,170,178],"web":[14],"by":[15,36,44,77,86,108,142],"allowing":[16],"users":[17],"issue":[19],"queries":[20],"through":[21],"search":[23,79],"interface.":[24],"In":[25],"other":[26,57],"words,":[27],"data":[28,41],"acquisition":[29],"from":[30,73,94],"such":[31,59],"source":[33],"is":[34,136],"not":[35],"following":[37],"static":[38],"hyper-links.":[39],"Instead,":[40],"are":[42,100,130],"obtained":[43],"querying":[45],"interface,":[47],"and":[48,153],"reading":[49],"result":[51],"page":[52],"dynamically":[53],"generated.":[54],"This,":[55],"with":[56],"facts":[58],"as":[60],"interface":[62],"may":[63],"answer":[64],"query":[66],"only":[67,110],"partially,":[68],"has":[69],"prevented":[70],"databases":[72],"being":[74],"crawled":[75],"effectively":[76],"existing":[78],"engines.":[80],"This":[81],"paper":[82],"remedies":[83],"problem":[85],"giving":[87],"algorithms":[88,99,129],"extract":[90],"all":[91,177],"tuples":[93],"database.":[97],"Our":[98],"provably":[101],"efficient,":[102],"namely,":[103],"they":[104],"accomplish":[105],"task":[107],"performing":[109],"small":[112],"number":[113],"of":[114,150,163],"queries,":[115],"even":[116],"in":[117],"worst":[119],"case.":[120],"We":[121],"also":[122],"establish":[123],"theoretical":[124],"results":[125,156],"indicating":[126],"these":[128],"asymptotically":[131],"optimal":[132],"--":[133],"i.e.,":[134],"it":[135],"impossible":[137],"improve":[139],"their":[140],"efficiency":[141],"more":[143],"than":[144],"constant":[146],"factor.":[147],"The":[148],"derivation":[149],"our":[151],"upper":[152],"lower":[154],"bound":[155],"reveals":[157],"significant":[158],"insight":[159],"into":[160],"characteristics":[162],"underlying":[165],"problem.":[166],"Extensive":[167],"experiments":[168],"confirm":[169],"proposed":[171],"techniques":[172],"work":[173],"very":[174],"well":[175],"real":[179],"datasets":[180],"examined.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}