{"id":"https://openalex.org/W4297119521","doi":"https://doi.org/10.1007/s00778-022-00764-y","title":"Robust and scalable content-and-structure indexing","display_name":"Robust and scalable content-and-structure indexing","publication_year":2022,"publication_date":"2022-10-15","ids":{"openalex":"https://openalex.org/W4297119521","doi":"https://doi.org/10.1007/s00778-022-00764-y"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-022-00764-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-022-00764-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-022-00764-y.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00778-022-00764-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046036667","display_name":"Kevin Wellenzohn","orcid":"https://orcid.org/0000-0001-6511-7101"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kevin Wellenzohn","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017018305","display_name":"Michael H. B\u00f6hlen","orcid":"https://orcid.org/0000-0003-3694-9026"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael H. B\u00f6hlen","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080721885","display_name":"Sven Helmer","orcid":"https://orcid.org/0000-0002-9666-1932"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sven Helmer","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-9666-1932","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074999005","display_name":"Antoine Pietri","orcid":"https://orcid.org/0000-0003-4052-4469"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Pietri","raw_affiliation_strings":["Inria, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006129685","display_name":"Stefano Zacchiroli","orcid":"https://orcid.org/0000-0002-4576-136X"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefano Zacchiroli","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080721885"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.5664,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"4","first_page":"689","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","score":0.9973000288009644,"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":0.8415257930755615},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7444579005241394},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.7181926965713501},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7066781520843506},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5842493772506714},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5404603481292725},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49414828419685364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4120723605155945},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3748575448989868},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2948986291885376},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17055249214172363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415257930755615},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7444579005241394},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.7181926965713501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7066781520843506},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5842493772506714},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5404603481292725},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49414828419685364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4120723605155945},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3748575448989868},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2948986291885376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17055249214172363},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s00778-022-00764-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-022-00764-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-022-00764-y.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-03787268v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03787268","pdf_url":"https://hal.science/hal-03787268v1/file/final.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The VLDB Journal, In press","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:doi:10.5167/uzh-263883","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00778-022-00764-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-022-00764-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-022-00764-y.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297119521.pdf","grobid_xml":"https://content.openalex.org/works/W4297119521.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1515993376","https://openalex.org/W1549939222","https://openalex.org/W1576347849","https://openalex.org/W1600255172","https://openalex.org/W1981420413","https://openalex.org/W1981561414","https://openalex.org/W1991665234","https://openalex.org/W2000182388","https://openalex.org/W2030062409","https://openalex.org/W2038142281","https://openalex.org/W2061895115","https://openalex.org/W2068739275","https://openalex.org/W2070759438","https://openalex.org/W2088116875","https://openalex.org/W2135432866","https://openalex.org/W2155512447","https://openalex.org/W2230830246","https://openalex.org/W2303394219","https://openalex.org/W2729439724","https://openalex.org/W2756982556","https://openalex.org/W2798891709","https://openalex.org/W2893990175","https://openalex.org/W2963379900","https://openalex.org/W3016632594","https://openalex.org/W3018708672","https://openalex.org/W3021801092","https://openalex.org/W3085111528","https://openalex.org/W3098583838","https://openalex.org/W3100022177","https://openalex.org/W3193572849","https://openalex.org/W4249823756","https://openalex.org/W4288079288","https://openalex.org/W4297119521","https://openalex.org/W4297971002","https://openalex.org/W6692079994","https://openalex.org/W6765203037"],"related_works":["https://openalex.org/W2046569047","https://openalex.org/W2186419898","https://openalex.org/W2370961680","https://openalex.org/W2278452282","https://openalex.org/W1552925710","https://openalex.org/W207628907","https://openalex.org/W2740229587","https://openalex.org/W1786707430","https://openalex.org/W2159312398","https://openalex.org/W2749971207"],"abstract_inverted_index":{"Abstract":[0],"Frequent":[1],"queries":[2,10,42,55,98],"on":[3,16,43],"semi-structured":[4,45],"hierarchical":[5,21],"data":[6,13,131],"are":[7],"Content-and-Structure":[8,35],"(CAS)":[9],"that":[11,51,65],"filter":[12],"items":[14],"based":[15],"their":[17,24],"location":[18],"in":[19,75,83],"the":[20,31,67,133,140],"structure":[22],"and":[23,33,69,101,127],"value":[25,70],"for":[26],"some":[27],"attribute.":[28],"We":[29,79,104,123],"propose":[30],"Robust":[32],"Scalable":[34],"(RSCAS)":[36],"index":[37,50],"to":[38,112,115],"efficiently":[39,89],"answer":[40],"CAS":[41,95],"big":[44],"data.":[46],"To":[47],"get":[48],"an":[49],"is":[52,139],"robust":[53],"against":[54],"with":[56,99,118],"varying":[57],"selectivities,":[58],"we":[59],"introduce":[60],"a":[61,76,91,108,119],"novel":[62],"dynamic":[63],"interleaving":[64],"merges":[66],"path":[68],"dimensions":[71],"of":[72,94],"composite":[73],"keys":[74,82],"balanced":[77],"manner.":[78],"store":[80],"interleaved":[81],"our":[84],"trie-based":[85],"RSCAS":[86,106],"index,":[87],"which":[88,138],"supports":[90],"wide":[92],"range":[93],"queries,":[96],"including":[97],"wildcards":[100],"descendant":[102],"axes.":[103],"implement":[105],"as":[107],"log-structured":[109],"merge":[110],"tree":[111],"scale":[113],"it":[114],"data-intensive":[116],"applications":[117],"high":[120],"insertion":[121],"rate.":[122],"illustrate":[124],"RSCAS\u2019s":[125],"robustness":[126],"scalability":[128],"by":[129],"indexing":[130],"from":[132],"Software":[134],"Heritage":[135],"(SWH)":[136],"archive,":[137],"world\u2019s":[141],"largest,":[142],"publicly":[143],"available":[144],"source":[145],"code":[146],"archive.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}