{"id":"https://openalex.org/W4281720128","doi":"https://doi.org/10.1145/3514221.3517850","title":"JEDI: These aren't the JSON documents you're looking for...","display_name":"JEDI: These aren't the JSON documents you're looking for...","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281720128","doi":"https://doi.org/10.1145/3514221.3517850"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517850","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517850","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517850","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060455340","display_name":"Thomas H\u00fctter","orcid":"https://orcid.org/0000-0002-7190-6825"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Thomas H\u00fctter","raw_affiliation_strings":["University of Salzburg, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089328860","display_name":"Nikolaus Augsten","orcid":"https://orcid.org/0000-0002-3036-6201"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Nikolaus Augsten","raw_affiliation_strings":["University of Salzburg, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102985234","display_name":"Christoph Kirsch","orcid":"https://orcid.org/0000-0002-3515-6203"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christoph M. Kirsch","raw_affiliation_strings":["University of Salzburg &amp; Czech Technical University, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg &amp; Czech Technical University, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011512061","display_name":"Michael J. Carey","orcid":"https://orcid.org/0000-0003-1561-4059"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Carey","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060455340"],"corresponding_institution_ids":["https://openalex.org/I182212641"],"apc_list":null,"apc_paid":null,"fwci":1.1479,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79708532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1584","last_page":"1597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.9759922027587891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912789583206177},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5163982510566711},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5095760822296143},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4641628861427307},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3261907398700714},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30072614550590515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1524192988872528},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13732397556304932},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1251773238182068},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09821823239326477}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.9759922027587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912789583206177},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5163982510566711},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5095760822296143},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4641628861427307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3261907398700714},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30072614550590515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1524192988872528},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13732397556304932},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1251773238182068},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09821823239326477}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517850","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517850","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3514221.3517850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517850","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517850","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1016752955","display_name":null,"funder_award_id":"P 29859, P 34962","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G1645810744","display_name":null,"funder_award_id":"P 34962","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G3622461675","display_name":null,"funder_award_id":"CZ.02.1.01","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G535846211","display_name":null,"funder_award_id":"P 29859","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G6492659061","display_name":"Evolving Language Ecosystems","funder_award_id":"695412","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7935790356","display_name":null,"funder_award_id":"695412","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320310426","display_name":"Marshallplan-Jubil\u00e4umsstiftung","ror":"https://ror.org/01ar4tp47"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281720128.pdf","grobid_xml":"https://content.openalex.org/works/W4281720128.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1513400187","https://openalex.org/W1967541846","https://openalex.org/W1975009259","https://openalex.org/W1983681808","https://openalex.org/W1998067572","https://openalex.org/W2018206665","https://openalex.org/W2022979132","https://openalex.org/W2024797550","https://openalex.org/W2056708848","https://openalex.org/W2092057784","https://openalex.org/W2107412086","https://openalex.org/W2136393336","https://openalex.org/W2165654401","https://openalex.org/W2256384365","https://openalex.org/W2265297126","https://openalex.org/W2396588571","https://openalex.org/W2435376278","https://openalex.org/W2461474581","https://openalex.org/W2493109812","https://openalex.org/W2521506077","https://openalex.org/W2562696781","https://openalex.org/W2574472735","https://openalex.org/W2614224126","https://openalex.org/W2795954267","https://openalex.org/W2806779957","https://openalex.org/W2907544011","https://openalex.org/W2948082807","https://openalex.org/W2949562252","https://openalex.org/W2954108003","https://openalex.org/W2971196067","https://openalex.org/W2980716463","https://openalex.org/W3099138433","https://openalex.org/W3136558723","https://openalex.org/W3173993340","https://openalex.org/W4211160472","https://openalex.org/W4300782170","https://openalex.org/W6969167732","https://openalex.org/W6969222764"],"related_works":["https://openalex.org/W2577820972","https://openalex.org/W4323776979","https://openalex.org/W2380368790","https://openalex.org/W2559176074","https://openalex.org/W4281677580","https://openalex.org/W2367643486","https://openalex.org/W4281778737","https://openalex.org/W2391941239","https://openalex.org/W4281893301","https://openalex.org/W2354762837"],"abstract_inverted_index":{"The":[0],"JavaScript":[1],"Object":[2],"Notation":[3],"(JSON)":[4],"is":[5,191],"a":[6,32,36,68,73,87,118,128],"popular":[7],"data":[8],"format":[9],"used":[10],"in":[11,136,166],"document":[12,34,70],"stores":[13],"to":[14,76,121,203],"natively":[15],"support":[16],"semi-structured":[17],"data.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,146],"address":[23],"the":[24,48,77,96,101,140,177,192],"problem":[25],"of":[26,91,134,142,181,207,214,216],"JSON":[27,59,85,92,97,143,210],"similarity":[28,144],"lookup":[29],"queries:":[30],"given":[31],"query":[33,49],"and":[35,63,80,94,152,169,184,209],"distance":[37,81,104],"threshold":[38],"\u03c4,":[39],"retrieve":[40],"all":[41],"documents":[42,208],"that":[43,113,199],"are":[44],"within":[45,67],"\u03c4":[46],"from":[47,52],"document.":[50],"Different":[51],"other":[53],"hierarchical":[54],"formats":[55],"such":[56],"as":[57],"XML,":[58],"supports":[60],"both":[61],"ordered":[62],"unordered":[64],"sibling":[65,124],"collections":[66],"single":[69],"which":[71,174],"poses":[72],"new":[74,119],"challenge":[75],"tree":[78,89,159,193],"model":[79],"computation.":[82],"We":[83,108],"propose":[84],"tree,":[86],"lossless":[88],"representation":[90],"documents,":[93],"define":[95],"Edit":[98],"Distance":[99],"(JEDI),":[100],"first":[102],"edit-based":[103],"measure":[105],"for":[106],"JSON.":[107],"develop":[109],"QuickJEDI,":[110],"an":[111,132,148,153],"algorithm":[112,130,164],"computes":[114],"JEDI":[115],"by":[116,131],"leveraging":[117],"technique":[120],"prune":[122],"expensive":[123],"matchings.":[125],"It":[126],"outperforms":[127],"baseline":[129],"order":[133],"magnitude":[135],"runtime.":[137],"To":[138],"boost":[139],"performance":[141],"queries,":[145],"introduce":[147],"index":[149],"called":[150],"JSIM":[151],"effective":[154],"upper":[155,162],"bound":[156,163,180],"based":[157],"on":[158],"sorting.":[160],"Our":[161,195],"runs":[165],"O(n\u03c4)":[167],"time":[168,183],"O(n+\u03c4":[170],"log":[171,186],"n)":[172,187],"space,":[173],"substantially":[175],"improves":[176],"previous":[178],"best":[179],"O(n2)":[182],"O(n":[185],"space":[188],"(where":[189],"n":[190],"size).":[194],"experimental":[196],"evaluation":[197],"shows":[198],"our":[200],"solution":[201],"scales":[202],"databases":[204],"with":[205,212],"millions":[206],"trees":[211],"tens":[213],"thousands":[215],"nodes.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
