{"id":"https://openalex.org/W7117134008","doi":"https://doi.org/10.1016/j.engappai.2025.113504","title":"HaiNougat: An academic document parser that preserves formulas and tables for high-energy physics","display_name":"HaiNougat: An academic document parser that preserves formulas and tables for high-energy physics","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117134008","doi":"https://doi.org/10.1016/j.engappai.2025.113504"},"language":"en","primary_location":{"id":"doi:10.1016/j.engappai.2025.113504","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.engappai.2025.113504","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jianwen Luo","orcid":"https://orcid.org/0009-0005-2871-881X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwen Luo","raw_affiliation_strings":["Institute of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100000, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100000, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113178970","display_name":"Zhengde Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210129701","display_name":"Institute of High Energy Physics","ror":"https://ror.org/039shy520","country_code":"AT","type":"facility","lineage":["https://openalex.org/I138211613","https://openalex.org/I4210129701"]},{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["AT","CN"],"is_corresponding":true,"raw_author_name":"Zhengde Zhang","raw_affiliation_strings":["Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China"],"affiliations":[{"raw_affiliation_string":"Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China","institution_ids":["https://openalex.org/I4210137180","https://openalex.org/I4210129701","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121217089","display_name":"Fazhi Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210129701","display_name":"Institute of High Energy Physics","ror":"https://ror.org/039shy520","country_code":"AT","type":"facility","lineage":["https://openalex.org/I138211613","https://openalex.org/I4210129701"]},{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["AT","CN"],"is_corresponding":false,"raw_author_name":"Fazhi Qi","raw_affiliation_strings":["Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China"],"affiliations":[{"raw_affiliation_string":"Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China","institution_ids":["https://openalex.org/I4210137180","https://openalex.org/I4210129701","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107249999","display_name":"Yiyu Zhang","orcid":"https://orcid.org/0009-0000-7412-5293"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210129701","display_name":"Institute of High Energy Physics","ror":"https://ror.org/039shy520","country_code":"AT","type":"facility","lineage":["https://openalex.org/I138211613","https://openalex.org/I4210129701"]},{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["AT","CN"],"is_corresponding":false,"raw_author_name":"Yiyu Zhang","raw_affiliation_strings":["Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China"],"affiliations":[{"raw_affiliation_string":"Computing Center, The Institute of High Energy Physics of the Chinese Academy of Sciences, Beijing 100000, China","institution_ids":["https://openalex.org/I4210137180","https://openalex.org/I4210129701","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113178970"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210129701","https://openalex.org/I4210137180"],"apc_list":{"value":3170,"currency":"USD","value_usd":3170},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71127228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"166","issue":null,"first_page":"113504","last_page":"113504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7350999712944031,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7350999712944031,"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"}},{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.06390000134706497,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.026799999177455902,"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/parsing","display_name":"Parsing","score":0.8180000185966492},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.7110999822616577},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.679099977016449},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3799999952316284},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349000215530396},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8180000185966492},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.7110999822616577},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.679099977016449},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5212000012397766},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4878000020980835},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.engappai.2025.113504","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.engappai.2025.113504","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8584623070","display_name":null,"funder_award_id":"CAS-WX2022SF-0104","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335641","display_name":"Institute of High Energy Physics","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W4283448848","https://openalex.org/W4389430217"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-24T00:00:00"}
