{"id":"https://openalex.org/W4412887686","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1135","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","display_name":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887686","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1135"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1135","pdf_url":"https://aclanthology.org/2025.findings-acl.1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1135.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093925844","display_name":"Ahmed Heakl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Heakl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040264558","display_name":"Muhammad Sohail","orcid":"https://orcid.org/0000-0002-7234-8108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Sohail","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072720344","display_name":"Mukul Ranjan","orcid":"https://orcid.org/0000-0002-6808-5990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukul Ranjan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181195","display_name":"Rania Elbadry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rania Elbadry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104286577","display_name":"Ghazi Shazan Ahmad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghazi Shazan Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025121816","display_name":"Mohamed El-Geish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed El-Geish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075282152","display_name":"Omar Maher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar Maher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066530136","display_name":"Zhiqiang Shen","orcid":"https://orcid.org/0000-0002-4560-5092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090790109","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-8070-6577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salman Khan","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":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22006","last_page":"22024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9498999714851379,"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":0.9498999714851379,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9387000203132629,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9333000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/arabic","display_name":"Arabic","score":0.8309093713760376},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7443368434906006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962827444076538},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6464959383010864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5943456888198853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131750702857971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4797305166721344},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12217062711715698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09045445919036865},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.046688735485076904}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8309093713760376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7443368434906006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962827444076538},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6464959383010864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5943456888198853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131750702857971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4797305166721344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12217062711715698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09045445919036865},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.046688735485076904},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1135","pdf_url":"https://aclanthology.org/2025.findings-acl.1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1135","pdf_url":"https://aclanthology.org/2025.findings-acl.1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887686.pdf","grobid_xml":"https://content.openalex.org/works/W4412887686.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Ahmed":[0],"Heakl,":[1],"Muhammad":[2],"Abdullah":[3],"Sohail,":[4],"Mukul":[5],"Ranjan,":[6],"Rania":[7],"Elbadry,":[8],"Ghazi":[9],"Shazan":[10],"Ahmad,":[11],"Mohamed":[12],"El-Geish,":[13],"Omar":[14],"Maher,":[15],"Zhiqiang":[16],"Shen,":[17],"Fahad":[18],"Shahbaz":[19],"Khan,":[20],"Salman":[21],"Khan.":[22],"Findings":[23],"of":[24],"the":[25],"Association":[26],"for":[27],"Computational":[28],"Linguistics:":[29],"ACL":[30],"2025.":[31,32]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
