{"id":"https://openalex.org/W7165388191","doi":"https://doi.org/10.48550/arxiv.2606.20072","title":"Source-Grounded Data Generation for Text-to-JSON Learning","display_name":"Source-Grounded Data Generation for Text-to-JSON Learning","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165388191","doi":"https://doi.org/10.48550/arxiv.2606.20072"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.20072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.20072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139018399","display_name":"Sunghee Ahn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahn, Sunghee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138965121","display_name":"Guijin Son","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Son, Guijin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138979878","display_name":"Youngjae Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Youngjae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.44999998807907104,"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/T10028","display_name":"Topic Modeling","score":0.44999998807907104,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1671999990940094,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.10400000214576721,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.8939999938011169},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6553000211715698},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.43470001220703125},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.37929999828338623},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3727000057697296},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8939999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870000004768372},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3160000145435333},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.20072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.20072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41368812322616577}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"From":[0],"financial":[1],"filings":[2],"to":[3,14,30,35,121,128],"clinical":[4],"records,":[5],"legacy":[6],"industries":[7],"rely":[8],"heavily":[9],"on":[10,94],"long,":[11],"unstructured":[12],"documents":[13],"store":[15],"high-value":[16],"information.":[17],"Reliably":[18],"extracting":[19],"this":[20,59],"information":[21],"into":[22],"structured,":[23],"machine-readable":[24],"representations":[25],"is":[26,39],"a":[27,40,68],"key":[28],"prerequisite":[29],"making":[31],"the":[32,90],"contents":[33],"accessible":[34],"automated":[36],"systems.":[37],"JSON":[38,77],"natural":[41],"target":[42],"for":[43,82],"such":[44],"structured":[45],"extraction,":[46],"yet":[47],"constructing":[48],"reliable":[49],"and":[50,76,123],"scalable":[51,83],"text-to-JSON":[52],"training":[53,109],"data":[54,70,110],"remains":[55],"challenging.":[56],"To":[57],"address":[58],"gap,":[60],"we":[61],"propose":[62],"STAGE":[63,106],"(Spreadsheet-grounded":[64],"Text-to-JSON":[65],"Artifact":[66],"GEneration),":[67],"source-grounded":[69,97],"generation":[71],"pipeline":[72],"that":[73,105],"constructs":[74],"reports":[75],"schema":[78],"by":[79],"using":[80],"LLMs":[81],"synthesis":[84],"while":[85],"validating":[86],"ground-truth":[87],"values":[88],"against":[89],"underlying":[91],"spreadsheet.":[92],"Evaluations":[93],"STAGE-Eval,":[95],"our":[96],"benchmark":[98],"with":[99],"an":[100],"851-example":[101],"test":[102],"set,":[103],"show":[104],"produces":[107],"stronger":[108],"than":[111],"existing":[112],"approaches.":[113],"This":[114],"improves":[115],"Qwen3-4B":[116],"exact":[117],"match":[118],"from":[119,126],"31.37%":[120],"74.27%":[122],"value":[124],"accuracy":[125],"45.46%":[127],"90.69%.":[129]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-20T00:00:00"}