{"id":"https://openalex.org/W6891802085","doi":"https://doi.org/10.48550/arxiv.2503.19658","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","display_name":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","publication_year":2025,"publication_date":"2025-03-25","ids":{"openalex":"https://openalex.org/W6891802085","doi":"https://doi.org/10.48550/arxiv.2503.19658"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2503.19658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19658","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.2503.19658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Koh\u00fat, Jan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koh\u00fat, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Do\u010dekal, Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Do\u010dekal, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hradi\u0161, Michal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hradi\u0161, Michal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Va\u0161ko, Marek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Va\u0161ko, Marek","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":true,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8942000269889832,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8942000269889832,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.026399999856948853,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.01119999960064888,"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/metadata","display_name":"Metadata","score":0.8097000122070312},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.52920001745224},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.47519999742507935},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.4146000146865845},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.37700000405311584},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.3167000114917755},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.31619998812675476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223000168800354},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8097000122070312},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7422999739646912},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3167000114917755},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C42629822","wikidata":"https://www.wikidata.org/wiki/Q1346408","display_name":"Geocoding","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C65610166","wikidata":"https://www.wikidata.org/wiki/Q5227399","display_name":"Database catalog","level":4,"score":0.2924000024795532},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2994543612","wikidata":"https://www.wikidata.org/wiki/Q22806","display_name":"National library","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2503.19658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19658","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.2503.19658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19658","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":[{"score":0.7465161085128784,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Manual":[0],"digitization":[1],"of":[2,30,47,59,74,105,133,139,146,165],"bibliographic":[3,54,89,174],"metadata":[4,34,175],"is":[5,85],"time":[6],"consuming":[7],"and":[8,14,79,94,123,135,155,184,189],"labor":[9],"intensive,":[10],"especially":[11],"for":[12,33,173],"historical":[13],"real-world":[15,171],"archives":[16],"with":[17,52,87,98,126,157],"highly":[18],"variable":[19],"formatting":[20],"across":[21],"documents.":[22],"Despite":[23],"advances":[24],"in":[25,102],"machine":[26],"learning,":[27],"the":[28,103,144,158],"absence":[29],"dedicated":[31],"datasets":[32],"extraction":[35],"hinders":[36],"automation.":[37],"To":[38,108],"address":[39],"this":[40,113],"gap,":[41],"we":[42,115,142],"introduce":[43],"BiblioPage,":[44],"a":[45,71,130,170],"dataset":[46,57],"scanned":[48],"title":[49,63,83],"pages":[50,64],"annotated":[51,86],"structured":[53,110],"metadata.":[55],"The":[56],"consists":[58],"approximately":[60],"2,000":[61],"monograph":[62],"collected":[65],"from":[66,112],"14":[67],"Czech":[68],"libraries,":[69],"spanning":[70],"wide":[72],"range":[73],"publication":[75,95],"periods,":[76],"typographic":[77],"styles,":[78],"layout":[80],"structures.":[81],"Each":[82],"page":[84],"16":[88],"attributes,":[90],"including":[91,152],"title,":[92],"contributors,":[93],"metadata,":[96],"along":[97],"precise":[99],"positional":[100],"information":[101,111,186],"form":[104],"bounding":[106],"boxes.":[107],"extract":[109],"dataset,":[114],"valuated":[116],"object":[117],"detection":[118],"models":[119],"such":[120],"as":[121,169],"YOLO":[122],"DETR":[124],"combined":[125],"transformer-based":[127],"OCR,":[128],"achieving":[129],"maximum":[131],"mAP":[132],"52":[134],"an":[136,162],"F1":[137,163],"score":[138,164],"59.":[140],"Additionally,":[141],"assess":[143],"performance":[145],"various":[147],"visual":[148],"large":[149],"language":[150],"models,":[151],"LlamA":[153],"3.2-Vision":[154],"GPT-4o,":[156],"best":[159],"model":[160],"reaching":[161],"67.":[166],"BiblioPage":[167],"serves":[168],"benchmark":[172],"extraction,":[176],"contributing":[177],"to":[178],"document":[179,181,185],"understanding,":[180],"question":[182],"answering,":[183],"extraction.":[187],"Dataset":[188],"evaluation":[190],"scripts":[191],"are":[192],"availible":[193],"at:":[194],"https://github.com/DCGM/biblio-dataset":[195]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}