{"id":"https://openalex.org/W2265048516","doi":"https://doi.org/10.14778/2777598.2777601","title":"Schema management for document stores","display_name":"Schema management for document stores","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W2265048516","doi":"https://doi.org/10.14778/2777598.2777601","mag":"2265048516"},"language":"en","primary_location":{"id":"doi:10.14778/2777598.2777601","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2777598.2777601","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/A5025153128","display_name":"Lanjun Wang","orcid":"https://orcid.org/0000-0002-7696-5330"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lanjun Wang","raw_affiliation_strings":["IBM Research - China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450365","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0002-2824-618X"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["IBM Research - China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112007116","display_name":"Juwei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juwei Shi","raw_affiliation_strings":["IBM Research - China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076440257","display_name":"Limei Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limei Jiao","raw_affiliation_strings":["IBM Research - China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068065546","display_name":"Oktie Hassanzadeh","orcid":"https://orcid.org/0000-0001-5307-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oktie Hassanzadeh","raw_affiliation_strings":["IBM T.J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013735333","display_name":"Jia Zou","orcid":"https://orcid.org/0000-0001-9849-0711"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zou","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055366986","display_name":"Chen Wangz","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wangz","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025153128"],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":8.6533,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97952005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"8","issue":"9","first_page":"922","last_page":"933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9976000189781189,"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":0.7811182141304016},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.7260539531707764},{"id":"https://openalex.org/keywords/schema-migration","display_name":"Schema migration","score":0.6345393061637878},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6297243237495422},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6078977584838867},{"id":"https://openalex.org/keywords/schema-evolution","display_name":"Schema evolution","score":0.5859699845314026},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.5750921964645386},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.5538952946662903},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5309079885482788},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.46214210987091064},{"id":"https://openalex.org/keywords/information-schema","display_name":"Information schema","score":0.4579566419124603},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4528248906135559},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.4177706241607666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3248320519924164},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.19726303219795227},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17678511142730713},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.100677490234375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811182141304016},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.7260539531707764},{"id":"https://openalex.org/C153440673","wikidata":"https://www.wikidata.org/wiki/Q7431119","display_name":"Schema migration","level":5,"score":0.6345393061637878},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6297243237495422},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6078977584838867},{"id":"https://openalex.org/C2780660560","wikidata":"https://www.wikidata.org/wiki/Q3951893","display_name":"Schema evolution","level":4,"score":0.5859699845314026},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.5750921964645386},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.5538952946662903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5309079885482788},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.46214210987091064},{"id":"https://openalex.org/C150012506","wikidata":"https://www.wikidata.org/wiki/Q6031185","display_name":"Information schema","level":5,"score":0.4579566419124603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4528248906135559},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4177706241607666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3248320519924164},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.19726303219795227},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17678511142730713},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.100677490234375},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C165611974","wikidata":"https://www.wikidata.org/wiki/Q5531015","display_name":"Gender schema theory","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2777598.2777601","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2777598.2777601","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1121883017","https://openalex.org/W1426690399","https://openalex.org/W1520566981","https://openalex.org/W1535469659","https://openalex.org/W1981578383","https://openalex.org/W1987748328","https://openalex.org/W2008896880","https://openalex.org/W2030766291","https://openalex.org/W2041140023","https://openalex.org/W2100305431","https://openalex.org/W2108350934","https://openalex.org/W2116493296","https://openalex.org/W2124391840","https://openalex.org/W2124654683","https://openalex.org/W2137692226","https://openalex.org/W2153233077","https://openalex.org/W2154475850","https://openalex.org/W2293253366","https://openalex.org/W2294859229","https://openalex.org/W3086391940","https://openalex.org/W3121289605","https://openalex.org/W6678679552"],"related_works":["https://openalex.org/W2103472145","https://openalex.org/W1513459549","https://openalex.org/W1992271858","https://openalex.org/W1591654213","https://openalex.org/W2105315220","https://openalex.org/W2137027610","https://openalex.org/W2069015212","https://openalex.org/W2561775104","https://openalex.org/W609927457","https://openalex.org/W1485634545"],"abstract_inverted_index":{"Document":[0],"stores":[1],"that":[2],"provide":[3],"the":[4,21,81,89,114,144,158,177,200],"efficiency":[5,178],"of":[6,35,56,77,146,157,165,179,202],"a":[7,36,43,60,94,118,133,154,162],"schema-less":[8,82],"interface":[9],"are":[10,196],"widely":[11],"used":[12],"by":[13,80],"developers":[14,23],"in":[15,59,140,189,205],"mobile":[16],"and":[17,53,62,66,85,99,126,148,185,193],"cloud":[18],"applications.":[19,207],"However,":[20],"simplicity":[22],"achieved":[24],"controversially":[25],"leads":[26],"to":[27,33,107,123,131,150,198],"complexity":[28],"for":[29,47,137],"data":[30,83,120,174,191],"management":[31,45],"due":[32],"lack":[34],"schema.":[37],"In":[38,88,129],"this":[39],"paper,":[40],"we":[41,92,116,142],"present":[42,132],"schema":[44,67,86,182],"framework":[46,51],"document":[48],"stores.":[49],"This":[50],"discovers":[52],"persists":[54],"schemas":[55,110,125,139],"JSON":[57],"records":[58,78],"repository,":[61],"also":[63],"supports":[64],"queries":[65],"summarization.":[68],"The":[69],"major":[70],"technical":[71],"challenge":[72],"comes":[73],"from":[74],"varied":[75],"structures":[76],"caused":[79],"model":[84],"evolution.":[87],"discovery":[90,183],"phase,":[91],"apply":[93],"canonical":[95],"form":[96,156],"based":[97,103,171],"method":[98],"propose":[100,117,149],"an":[101],"algorithm":[102],"on":[104,172],"equivalent":[105,109],"sub-trees":[106],"group":[108],"efficiently.":[111],"Together":[112],"with":[113],"algorithm,":[115],"new":[119],"structure,":[121],"eSiBu-Tree,":[122],"store":[124],"support":[127],"queries.":[128],"order":[130],"single":[134],"summarized":[135],"representation":[136],"heterogenous":[138],"records,":[141],"introduce":[143],"concept":[145],"\"skeleton\",":[147],"use":[151,187],"it":[152],"as":[153],"relaxed":[155],"schema,":[159],"which":[160],"captures":[161],"small":[163],"set":[164],"core":[166],"attributes.":[167],"Finally,":[168],"extensive":[169],"experiments":[170],"real":[173],"sets":[175],"demonstrate":[176],"our":[180],"proposed":[181],"algorithms,":[184],"practical":[186],"cases":[188],"real-world":[190],"exploration":[192],"integration":[194],"scenarios":[195],"presented":[197],"illustrate":[199],"effectiveness":[201],"using":[203],"skeletons":[204],"these":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}