{"id":"https://openalex.org/W4380433234","doi":"https://doi.org/10.1145/3588957","title":"dsJSON: A Distributed SQL JSON Processor","display_name":"dsJSON: A Distributed SQL JSON Processor","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433234","doi":"https://doi.org/10.1145/3588957"},"language":"en","primary_location":{"id":"doi:10.1145/3588957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588957","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3588957","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037502508","display_name":"Majid Saeedan","orcid":"https://orcid.org/0000-0002-9202-6894"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majid Saeedan","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9202-6894","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091292625","display_name":"Ahmed Eldawy","orcid":"https://orcid.org/0000-0002-6584-1455"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Eldawy","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6584-1455","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013940261","display_name":"Zhijia Zhao","orcid":"https://orcid.org/0000-0003-2616-4241"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijia Zhao","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2616-4241","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.1877,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47536337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"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":0.998199999332428,"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":0.9965999722480774,"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/T11719","display_name":"Data Quality and Management","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.9515409469604492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8813738822937012},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6672741174697876},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6662565469741821},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4590853750705719},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34477686882019043}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.9515409469604492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813738822937012},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6672741174697876},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6662565469741821},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4590853750705719},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34477686882019043}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588957","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3588957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588957","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G1849604498","display_name":"CAREER: Transducer-Centric Parallelization for Scalable Semi-Structured Data Processing","funder_award_id":"1751392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4491273840","display_name":null,"funder_award_id":"2046236; 1838222; 1924694; 1954644; 1751392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6994161918","display_name":"BIGDATA: F: Collaborative Research: Optimizing Log-Structured-Merge-Based Big Data Management Systems","funder_award_id":"1838222","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7654558890","display_name":"III: Medium: Collaborative Research: Supporting High-Value Analytics on Big Low-Value Data","funder_award_id":"1954644","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7671967541","display_name":"CCRI: ENS: Collaborative Research: Supporting and Sustaining Apache AsterixDB for the CISE Research Community","funder_award_id":"1924694","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G96987679","display_name":"CAREER: Towards Exploratory Data Science on Spatio-temporal Big Data","funder_award_id":"2046236","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W270849871","https://openalex.org/W410850256","https://openalex.org/W1575324001","https://openalex.org/W2038412523","https://openalex.org/W2179349885","https://openalex.org/W2434390175","https://openalex.org/W2619959750","https://openalex.org/W2752005949","https://openalex.org/W2889015391","https://openalex.org/W2907544011","https://openalex.org/W2935423094","https://openalex.org/W2947571256","https://openalex.org/W2952834697","https://openalex.org/W2973476981","https://openalex.org/W2979425006","https://openalex.org/W3100576803","https://openalex.org/W3116734368","https://openalex.org/W3120753775","https://openalex.org/W3131359276","https://openalex.org/W3173993340","https://openalex.org/W3208477850","https://openalex.org/W4214596994","https://openalex.org/W4233118040","https://openalex.org/W6609930034","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W2365783963","https://openalex.org/W3113257914"],"abstract_inverted_index":{"The":[0,43,123],"popularity":[1],"of":[2,13,45,111,126,193],"JSON":[3,46,83,135,167],"as":[4],"a":[5,56,80,103,133,143],"data":[6,24,105,195],"interchange":[7],"format":[8],"resulted":[9],"in":[10,55,88,137],"big":[11,94,134],"amounts":[12],"datasets":[14],"available":[15],"for":[16,120,179],"processing.":[17],"Users":[18],"would":[19],"like":[20],"to":[21,35,51,93,114,131,139,160],"analyze":[22],"this":[23,76],"using":[25],"SQL":[26,121,163],"queries":[27,164],"but":[28],"existing":[29,89,204,217],"distributed":[30,58,82,218],"systems":[31,90],"limit":[32],"their":[33],"users":[34,159],"only":[36],"two":[37,191],"specific":[38],"formats,":[39],"JSONLine":[40],"and":[41,91,95,173,185],"GeoJSON.":[42],"complexity":[44],"schema":[47,65,145],"makes":[48],"it":[49],"challenging":[50],"parse":[52,132,210],"arbitrary":[53,162],"files":[54,213],"modern":[57],"system":[59],"while":[60],"producing":[61],"records":[62,116,141],"with":[63,70,142,150],"unified":[64,144],"that":[66,85,107,117,146,197],"can":[67,147,207],"be":[68,148],"processed":[69,149],"SQL.":[71,151],"To":[72],"address":[73],"these":[74],"challenges,":[75],"paper":[77],"introduces":[78,99],"dsJSON,":[79],"state-of-the-art":[81],"processor":[84],"overcomes":[86],"limitations":[87],"scales":[92],"complex":[96,166],"data.":[97],"dsJSON":[98,152,198],"the":[100,127,177,183,186],"projection":[101,128,172],"tree,":[102],"novel":[104],"structure":[106],"applies":[108],"selective":[109],"parsing":[110],"nested":[112],"attributes":[113],"produce":[115,140],"are":[118],"ready":[119],"processors.":[122],"key":[124],"objective":[125],"tree":[129],"is":[130,153],"file":[136],"parallel":[138],"integrated":[154],"into":[155,176],"SparkSQL":[156],"which":[157],"enables":[158],"run":[161],"on":[165,189],"files.":[168],"It":[169,206],"also":[170,208],"pushes":[171],"filter":[174],"down":[175],"parser":[178,184],"full":[180],"integration":[181],"between":[182],"processor.":[187],"Experiments":[188],"up-to":[190],"terabytes":[192],"real":[194],"show":[196],"performs":[199],"several":[200],"times":[201],"faster":[202],"than":[203],"systems.":[205],"efficiently":[209],"extremely":[211],"large":[212],"not":[214],"supported":[215],"by":[216],"parsers":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}