{"id":"https://openalex.org/W7204188905","doi":"https://doi.org/10.48550/arxiv.2608.22842","title":"FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks","display_name":"FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204188905","doi":"https://doi.org/10.48550/arxiv.2608.22842"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22842","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22842","pdf_url":"https://arxiv.org/pdf/2608.22842","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135258538","display_name":"Hang Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hang","raw_affiliation_strings":["Equal contribution"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148046409","display_name":"Jin Zhang","orcid":"https://orcid.org/0009-0000-9325-8251","observed_orcids":["https://orcid.org/0009-0000-9325-8251"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jin","raw_affiliation_strings":["Equal contribution"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148045377","display_name":"Guoliang Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Guoliang","raw_affiliation_strings":["Equal contribution"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148075248","display_name":"Pengyue Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Pengyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148117177","display_name":"Yao Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024715914","display_name":"Zijiao Zhang","orcid":"https://orcid.org/0000-0001-8079-1583","observed_orcids":["https://orcid.org/0000-0001-8079-1583"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zijiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124962312","display_name":"Tianyu Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124833487","display_name":"Weiqi Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Weiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148108850","display_name":"Yulong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yulong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148063294","display_name":"Chuqiao Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Chuqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065887901","display_name":"Wenkang Huang","orcid":"https://orcid.org/0000-0002-8028-5047","observed_orcids":["https://orcid.org/0000-0002-8028-5047"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wenkang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148046963","display_name":"Kai Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148146601","display_name":"Yadong Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yadong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148128763","display_name":"Hui Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077180934","display_name":"Xingzhong Xu","orcid":"https://orcid.org/0000-0003-2665-6211","observed_orcids":["https://orcid.org/0000-0003-2665-6211"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Xingzhong","raw_affiliation_strings":["Team leader . Corresponding author. Ant Group , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Team leader . Corresponding author. Ant Group , Hangzhou , China","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134117868","display_name":"Xiao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Xiao","raw_affiliation_strings":["Team leader . Corresponding author. Ant Group , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Team leader . Corresponding author. Ant Group , Hangzhou , China","institution_ids":["https://openalex.org/I4405270328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818999886512756},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7423999905586243},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5063999891281128},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45260000228881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4348999857902527},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.26179999113082886},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22842","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22842","pdf_url":"https://arxiv.org/pdf/2608.22842","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,"listed_in":[],"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":"doi:10.48550/arxiv.2608.22842","doi":"https://doi.org/10.48550/arxiv.2608.22842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22842","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22842","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22842","pdf_url":"https://arxiv.org/pdf/2608.22842","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204188905.pdf","grobid_xml":"https://content.openalex.org/works/W7204188905.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4386228584","https://openalex.org/W4391505377","https://openalex.org/W4391631327","https://openalex.org/W4404354175","https://openalex.org/W4407794264","https://openalex.org/W4414281281","https://openalex.org/W4415844479","https://openalex.org/W4415854763","https://openalex.org/W4416060568","https://openalex.org/W4416780398","https://openalex.org/W4417006752","https://openalex.org/W4417157581","https://openalex.org/W4417250113","https://openalex.org/W6891822422","https://openalex.org/W7126026301","https://openalex.org/W7126074094","https://openalex.org/W7126256595","https://openalex.org/W7127380112","https://openalex.org/W7133331632","https://openalex.org/W7135036919","https://openalex.org/W7166845830"],"related_works":["https://openalex.org/W7135119398","https://openalex.org/W4417296427","https://openalex.org/W7163174105","https://openalex.org/W4413145313","https://openalex.org/W7128724747","https://openalex.org/W7101715815","https://openalex.org/W7160871715","https://openalex.org/W7163921921","https://openalex.org/W7127910948","https://openalex.org/W7155467491"],"abstract_inverted_index":{"Financial":[0],"document":[1,65],"parsing":[2,22],"requires":[3],"accuracy,":[4],"structural":[5],"consistency,":[6],"and":[7,47,64,82,100,131],"verifiability":[8],"that":[9],"current":[10],"benchmarks":[11],"often":[12],"fail":[13],"to":[14],"reflect.":[15],"We":[16],"present":[17],"FinixDoc,":[18],"an":[19],"end-to-end":[20],"agentic":[21],"system":[23],"for":[24],"real-world":[25],"financial":[26,171],"documents,":[27],"with":[28,74,86,114,134,165],"FinixDoc-VL,":[29],"a":[30,52,75,109,123,135],"4B-scale":[31],"vision-language":[32],"model":[33,161],"built":[34],"on":[35,169],"Qwen3-VL-4B,":[36],"as":[37],"its":[38,144],"core":[39],"parser.":[40],"To":[41,90],"characterize":[42],"the":[43,149,158,166],"gap":[44],"between":[45],"benchmark":[46],"deployment":[48],"performance,":[49],"we":[50,106,120],"introduce":[51],"Document":[53],"Parsing":[54],"Capability":[55],"Matrix":[56],"organized":[57],"along":[58],"two":[59],"practical":[60],"axes:":[61],"visual":[62],"quality":[63],"scale.":[66],"Guided":[67],"by":[68,162],"this":[69,140],"matrix,":[70],"FinixDoc-VL":[71,147],"is":[72],"trained":[73],"domain-adapted":[76],"recipe":[77],"combining":[78],"homoglyph-aware":[79],"contrastive":[80],"learning":[81,85],"multi-stage":[83],"reinforcement":[84],"composite":[87],"domain-specific":[88],"rewards.":[89],"better":[91],"leverage":[92],"our":[93],"accumulated":[94],"advantage":[95],"in":[96],"low-quality":[97],"financial-document":[98],"data":[99,104],"support":[101],"large-scale,":[102],"high-quality":[103],"production,":[105],"further":[107],"build":[108],"human-in-the-loop":[110],"Data":[111],"Factory":[112],"pipeline":[113],"confidence-aware":[115],"expert":[116],"review.":[117],"For":[118],"evaluation,":[119],"construct":[121],"FinixDocBench,":[122],"financial-domain":[124],"evaluation":[125],"suite":[126],"covering":[127],"digital-native,":[128],"camera-captured,":[129],"ultra-large-page,":[130],"internal-workflow":[132],"scenarios,":[133],"compliance-reviewed":[136],"subset":[137],"released":[138],"alongside":[139],"technical":[141],"report.":[142],"On":[143],"main":[145],"subsets,":[146],"achieves":[148],"highest":[150],"overall":[151],"score":[152],"(81.43)":[153],"among":[154],"evaluated":[155],"baselines,":[156],"outperforming":[157],"next-best":[159],"open-source":[160],"5.13":[163],"points,":[164],"largest":[167],"gains":[168],"internal":[170],"workflows":[172],"(FinixInner:":[173],"84.08":[174],"vs.":[175],"78.73).":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}