{"id":"https://openalex.org/W4403824091","doi":"https://doi.org/10.5753/sbbd.2024.240239","title":"Enumeration, Tagged Unions, Tuples, and Collections: A Novel Approach to Extracting JSON Schema","display_name":"Enumeration, Tagged Unions, Tuples, and Collections: A Novel Approach to Extracting JSON Schema","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4403824091","doi":"https://doi.org/10.5753/sbbd.2024.240239"},"language":"en","primary_location":{"id":"doi:10.5753/sbbd.2024.240239","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2024.240239","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/30696/30499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXXIX Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/30696/30499","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091956749","display_name":"Nat\u00e1lia Banhara","orcid":null},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Nat\u00e1lia Banhara","raw_affiliation_strings":["Federal University of the Southern Border (UFFS)"],"affiliations":[{"raw_affiliation_string":"Federal University of the Southern Border (UFFS)","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088745129","display_name":"Geomar A. Schreiner","orcid":"https://orcid.org/0000-0002-6457-8982"},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Geomar A. Schreiner","raw_affiliation_strings":["Federal University of the Southern Border (UFFS)"],"affiliations":[{"raw_affiliation_string":"Federal University of the Southern Border (UFFS)","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008042282","display_name":"Samuel da Silva Feitosa","orcid":"https://orcid.org/0000-0002-9485-4845"},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Samuel da Silva Feitosa","raw_affiliation_strings":["Federal University of the Southern Border (UFFS)"],"affiliations":[{"raw_affiliation_string":"Federal University of the Southern Border (UFFS)","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041239977","display_name":"Denio Duarte","orcid":"https://orcid.org/0000-0003-4936-4748"},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Denio Duarte","raw_affiliation_strings":["Federal University of the Southern Border (UFFS)"],"affiliations":[{"raw_affiliation_string":"Federal University of the Southern Border (UFFS)","institution_ids":["https://openalex.org/I137534880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091956749"],"corresponding_institution_ids":["https://openalex.org/I137534880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2953511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"234","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9962000250816345,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9689000248908997,"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/json","display_name":"JSON","score":0.9194941520690918},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.8678967952728271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512937188148499},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.6992856860160828},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6941516399383545},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4999532699584961},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3656473457813263},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35891419649124146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3273971676826477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14517554640769958},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10817292332649231},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08459040522575378}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.9194941520690918},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8678967952728271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512937188148499},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.6992856860160828},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6941516399383545},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4999532699584961},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3656473457813263},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35891419649124146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3273971676826477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14517554640769958},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10817292332649231},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08459040522575378}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/sbbd.2024.240239","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2024.240239","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/30696/30499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXXIX Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5753/sbbd.2024.240239","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2024.240239","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/30696/30499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXXIX Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403824091.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1586198805","https://openalex.org/W2341844252","https://openalex.org/W2574472735","https://openalex.org/W2887418847","https://openalex.org/W2907544011","https://openalex.org/W2981940068","https://openalex.org/W3164553634","https://openalex.org/W3174369108","https://openalex.org/W3216493580","https://openalex.org/W4293865455"],"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":{"Recently,":[0],"JSON":[1,88,130,146],"became":[2],"a":[3,26,41,76,85,118],"trendy":[4],"data":[5,18,68],"format":[6],"for":[7],"representing":[8],"datasets.":[9],"Its":[10],"success":[11],"is":[12,34,48],"due":[13],"to":[14,50,78],"embodying":[15],"structure":[16,31],"and":[17,63,66,98,112,141],"in":[19,58],"the":[20,30,38,56,81,136],"same":[21],"representation.":[22],"Moreover,":[23],"it":[24,47],"has":[25],"loose":[27],"structure,":[28],"i.e.,":[29],"(aka":[32],"schema)":[33],"not":[35],"rigid.":[36],"While":[37],"absence":[39],"of":[40,54,83],"rigid":[42],"schema":[43,57,86,127],"brings":[44],"several":[45],"advantages,":[46],"impossible":[49],"exploit":[51],"some":[52],"benefits":[53],"knowing":[55],"advance,":[59],"such":[60],"as":[61,107,110,114],"query":[62],"storage":[64],"optimization":[65],"improving":[67],"curation.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74,117],"JFUSE,":[75],"tool":[77],"deal":[79],"with":[80],"problem":[82],"discovering":[84],"from":[87,144],"collections.":[89,147],"Besides":[90],"inferring":[91],"basic":[92],"types":[93],"(e.g.,":[94,129],"atomic":[95],"types,":[96],"arrays,":[97],"objects),":[99],"JFUSE":[100],"also":[101],"discovers":[102],"enumeration,":[103],"tagged":[104],"unions,":[105],"metadata":[106],"data,":[108],"objects":[109],"collections,":[111],"arrays":[113],"tuples.":[115],"We":[116],"metamodel":[119],"that":[120,135],"can":[121],"be":[122],"easily":[123],"transformed":[124],"into":[125],"any":[126],"language":[128],"Schema).":[131],"Our":[132],"experiments":[133],"show":[134],"proposed":[137],"approach":[138],"infers":[139],"concise":[140],"correct":[142],"schemas":[143],"(huge)":[145]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}