{"id":"https://openalex.org/W4406189751","doi":"https://doi.org/10.1007/s10032-025-00563-5","title":"BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations","display_name":"BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4406189751","doi":"https://doi.org/10.1007/s10032-025-00563-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-025-00563-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00563-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00563-5.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00563-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115816502","display_name":"Simone Giovannini","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone Giovannini","raw_affiliation_strings":["DINFO, Universit\u00e1 degli Studi di Firenze, Via di Santa Marta, 3, Florence, 50139, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DINFO, Universit\u00e1 degli Studi di Firenze, Via di Santa Marta, 3, Florence, 50139, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102938658","display_name":"Fabio Coppini","orcid":"https://orcid.org/0000-0002-2699-8636"},"institutions":[{"id":"https://openalex.org/I4210135272","display_name":"H\u00f4pital Paris Saint-Joseph","ror":"https://ror.org/046bx1082","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210135272"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabio Coppini","raw_affiliation_strings":["LETXBE, 229 Rue Saint-Honor\u00e9, Paris, 75001, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LETXBE, 229 Rue Saint-Honor\u00e9, Paris, 75001, France","institution_ids":["https://openalex.org/I4210135272"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043086033","display_name":"Andrea Gemelli","orcid":"https://orcid.org/0000-0002-6149-8282"},"institutions":[{"id":"https://openalex.org/I4210135272","display_name":"H\u00f4pital Paris Saint-Joseph","ror":"https://ror.org/046bx1082","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210135272"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andrea Gemelli","raw_affiliation_strings":["LETXBE, 229 Rue Saint-Honor\u00e9, Paris, 75001, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LETXBE, 229 Rue Saint-Honor\u00e9, Paris, 75001, France","institution_ids":["https://openalex.org/I4210135272"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011511343","display_name":"Simone Marinai","orcid":"https://orcid.org/0000-0002-6702-2277"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Marinai","raw_affiliation_strings":["DINFO, Universit\u00e1 degli Studi di Firenze, Via di Santa Marta, 3, Florence, 50139, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DINFO, Universit\u00e1 degli Studi di Firenze, Via di Santa Marta, 3, Florence, 50139, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115816502"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0016541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"2","first_page":"447","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9925000071525574,"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/question-answering","display_name":"Question answering","score":0.870850682258606},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6008211970329285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5989524126052856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4116348624229431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3480619192123413}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.870850682258606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6008211970329285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989524126052856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4116348624229431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3480619192123413}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10032-025-00563-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00563-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00563-5.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2501.03403","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.03403","pdf_url":"https://arxiv.org/pdf/2501.03403","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:flore.unifi.it:2158/1442852","is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1442852","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2501.03403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.03403","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s10032-025-00563-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00563-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00563-5.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322648","display_name":"Universit\u00e0 degli Studi di Firenze","ror":"https://ror.org/04jr1s763"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406189751.pdf","grobid_xml":"https://content.openalex.org/works/W4406189751.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2963341956","https://openalex.org/W4327810158","https://openalex.org/W2098345386","https://openalex.org/W3132296545","https://openalex.org/W3120043490","https://openalex.org/W4379256266","https://openalex.org/W4402422437","https://openalex.org/W4392926970","https://openalex.org/W4381708538","https://openalex.org/W4390873989","https://openalex.org/W4388926478","https://openalex.org/W4385237494","https://openalex.org/W2986619406","https://openalex.org/W3201693581","https://openalex.org/W3003484198","https://openalex.org/W4285105124","https://openalex.org/W4312554912","https://openalex.org/W4404781508","https://openalex.org/W4405173237","https://openalex.org/W4393027708","https://openalex.org/W3204562006","https://openalex.org/W4402683758","https://openalex.org/W4402671775","https://openalex.org/W3213241618","https://openalex.org/W4312233877","https://openalex.org/W4320481960","https://openalex.org/W4304013646","https://openalex.org/W4213213306","https://openalex.org/W4382202558","https://openalex.org/W3173585224","https://openalex.org/W4387561528","https://openalex.org/W4391631799","https://openalex.org/W4322718191","https://openalex.org/W4395474395","https://openalex.org/W4403853618"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"present":[2],"a":[3,48,53,91],"unified":[4],"dataset":[5],"for":[6,56,122],"document":[7,24,88,123],"Question-Answering":[8,49],"(QA),":[9],"which":[10],"is":[11,30],"obtained":[12],"combining":[13],"several":[14],"public":[15],"datasets":[16],"related":[17],"to":[18,83],"Document":[19,39],"AI":[20,40],"and":[21,58,75],"visually":[22],"rich":[23],"understanding":[25],"(VRDU).":[26],"Our":[27],"main":[28],"contribution":[29],"twofold:":[31],"on":[32,63,111],"the":[33,64,69,73,77,81,87,99,112,118],"one":[34],"hand":[35],"we":[36,67,97],"reformulate":[37],"existing":[38],"tasks,":[41],"such":[42],"as":[43,90],"Information":[44],"Extraction":[45],"(IE),":[46],"into":[47],"task,":[50],"making":[51],"it":[52],"suitable":[54],"resource":[55],"training":[57],"evaluating":[59],"Large":[60],"Language":[61],"Models;":[62],"other":[65],"hand,":[66],"release":[68],"OCR":[70],"of":[71,80,101,114],"all":[72],"documents":[74],"include":[76,107],"exact":[78],"position":[79],"answer":[82],"be":[84],"found":[85],"in":[86],"image":[89],"bounding":[92,108],"box.":[93],"Using":[94],"this":[95],"dataset,":[96],"explore":[98],"impact":[100],"different":[102],"prompting":[103],"techniques":[104],"(that":[105],"might":[106],"box":[109],"information)":[110],"performance":[113],"open-weight":[115],"models,":[116],"identifying":[117],"most":[119],"effective":[120],"approaches":[121],"comprehension.":[124]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-01-09T00:00:00"}