{"id":"https://openalex.org/W7204177265","doi":"https://doi.org/10.48550/arxiv.2608.22183","title":"VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR","display_name":"VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204177265","doi":"https://doi.org/10.48550/arxiv.2608.22183"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22183","pdf_url":"https://arxiv.org/pdf/2608.22183","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035781997","display_name":"Yani Guan","orcid":"https://orcid.org/0009-0005-2729-0217","observed_orcids":["https://orcid.org/0009-0005-2729-0217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yani","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063522359","display_name":"Dengpan Dong","orcid":"https://orcid.org/0000-0002-3381-3425","observed_orcids":["https://orcid.org/0000-0002-3381-3425"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Dengpan","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146449621","display_name":"Shuang Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Shuang","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146477105","display_name":"Zi Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zi","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031800830","display_name":"Joah Han","orcid":"https://orcid.org/0000-0002-8982-3788","observed_orcids":["https://orcid.org/0000-0002-8982-3788"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Joah","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032908754","display_name":"Dan Hannah","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hannah, Dan","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146554541","display_name":"Yumin Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yumin","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112847736","display_name":"Qichao Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Qichao","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148168333","display_name":"Kang Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Kang","raw_affiliation_strings":["SES AI Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SES AI Corporation","institution_ids":[]}]}],"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":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":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6420999765396118,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.6420999765396118,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.15360000729560852,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0272000003606081,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-chemical-structure-recognition","display_name":"optical chemical structure recognition","score":0.9800000190734863},{"id":"https://openalex.org/keywords/model-confidence","display_name":"model confidence","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C2776213154","wikidata":"https://www.wikidata.org/wiki/Q13370881","display_name":"Verdict","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C204434341","wikidata":"https://www.wikidata.org/wiki/Q357789","display_name":"Adjudication","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53329998254776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4025999903678894},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C50151734","wikidata":"https://www.wikidata.org/wiki/Q1759577","display_name":"Matched filter","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C2776127325","wikidata":"https://www.wikidata.org/wiki/Q1424662","display_name":"Omniscience","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28220000863075256}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22183","pdf_url":"https://arxiv.org/pdf/2608.22183","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22183","doi":"https://doi.org/10.48550/arxiv.2608.22183","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22183","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22183","pdf_url":"https://arxiv.org/pdf/2608.22183","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/W7204177265.pdf","grobid_xml":"https://content.openalex.org/works/W7204177265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160662709","https://openalex.org/W4391430657","https://openalex.org/W4388850177","https://openalex.org/W7160222958","https://openalex.org/W7214733821","https://openalex.org/W3092396754","https://openalex.org/W7157203628","https://openalex.org/W7202165684","https://openalex.org/W7138059347","https://openalex.org/W4402963172"],"abstract_inverted_index":{"Optical":[0],"Chemical":[1],"Structure":[2],"Recognition":[3],"(OCSR)":[4],"converts":[5],"2D":[6],"molecular":[7,210,237],"depictions":[8,50],"in":[9,33,185],"the":[10,34,113,156,194,200],"published":[11],"literature":[12],"into":[13],"SMILES,":[14],"and":[15,59,75,126,151,197,217,235],"is":[16,130],"increasingly":[17],"important":[18],"for":[19,176,193,199,208,233],"constructing":[20],"large-scale":[21],"chemical":[22],"training":[23],"datasets.":[24],"Automation":[25],"at":[26,110,117],"that":[27],"scale":[28],"requires":[29],"identifying":[30],"unreliable":[31],"predictions":[32,137],"absence":[35],"of":[36,41,100,108,181,191],"ground":[37,53],"truth.":[38],"Three":[39],"families":[40],"label-free":[42],"signals":[43],"were":[44],"compared":[45],"on":[46,79,123,132,149],"$263$":[47],"ACS":[48],"journal":[49],"with":[51],"verified":[52],"truth:":[54],"model":[55],"confidence,":[56],"re-rendering":[57,64],"similarity,":[58],"agreement":[60],"among":[61,91],"recognizers.":[62],"Pixel-space":[63],"performed":[65],"little":[66],"better":[67],"than":[68],"chance":[69],"(AUROC":[70],"$0.547$,":[71],"$95\\%$":[72],"CI":[73],"$[0.465,0.629]$),":[74],"an":[76,98,230],"oracle-tuned":[77],"threshold":[78],"it":[80],"reduced":[81],"correct":[82],"labels":[83,175,184,207],"per":[84],"image":[85],"from":[86],"$0.745$":[87],"to":[88,168],"$0.205$.":[89],"Agreement":[90],"four":[92],"architecturally":[93],"distinct":[94],"recognizers":[95],"instead":[96],"reached":[97],"AUROC":[99],"$0.916$":[101],"($[0.880,0.952]$).":[102],"The":[103,119],"two-of-four":[104,201],"rule":[105,115,158],"accepted":[106],"$81.7\\%$":[107],"images":[109],"$88.8\\%$":[111],"precision,":[112],"three-of-four":[114,157,195],"$52.1\\%$":[116],"$98.5\\%$.":[118],"same":[120],"pattern":[121],"held":[122],"CLEF-IP,":[124],"UOB,":[125],"USPTO.":[127],"This":[128],"distinction":[129],"obscured":[131],"synthetic":[133],"benchmarks,":[134],"where":[135],"re-rendered":[136],"naturally":[138],"resemble":[139],"their":[140],"inputs.":[141],"A":[142],"substance":[143],"filter":[144],"removed":[145],"$2{,}193$":[146],"false":[147],"agreements":[148],"wildcards":[150],"R-group":[152],"fragments,":[153],"after":[154],"which":[155],"rejected":[159],"all":[160],"$68$":[161],"generic":[162],"depictions.":[163],"VERDICT":[164,203,226],"was":[165],"then":[166],"applied":[167],"PMC":[169],"Open":[170],"Access,":[171],"producing":[172],"$6{,}146$":[173],"structure":[174,213],"$4{,}833$":[177],"molecules;":[178],"chemist":[179],"adjudication":[180],"$400$":[182],"released":[183],"two":[186],"independent":[187],"samples":[188],"yielded":[189],"precisions":[190],"$0.995$":[192],"tier":[196],"$0.958$":[198],"tier.":[202],"therefore":[204],"enables":[205],"validated":[206],"multimodal":[209],"databases":[211],"linking":[212],"images,":[214],"machine-readable":[215],"representations,":[216],"source-publication":[218],"information.":[219],"In":[220],"SES":[221],"AI's":[222],"Molecular":[223],"Universe":[224],"platform,":[225],"further":[227],"serves":[228],"as":[229],"image-based":[231],"interface":[232],"searching":[234],"retrieving":[236],"records.":[238]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}