{"id":"https://openalex.org/W7204927596","doi":"https://doi.org/10.48550/arxiv.2608.30210","title":"Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration","display_name":"Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204927596","doi":"https://doi.org/10.48550/arxiv.2608.30210"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30210","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30210","pdf_url":"https://arxiv.org/pdf/2608.30210","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/2608.30210","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130758179","display_name":"Sunwhi Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Sunwhi","raw_affiliation_strings":["Hwasung Medi-Science University, Dept. of Bio-Healthcare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hwasung Medi-Science University, Dept. of Bio-Healthcare","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005921519","display_name":"S. M. Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Sunyul","raw_affiliation_strings":["Yonsei University, Graduate School of Engineering, Dept. of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Graduate School of Engineering, Dept. of Artificial Intelligence","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069982682","display_name":"Meounggun Jo","orcid":"https://orcid.org/0009-0007-0978-770X","observed_orcids":["https://orcid.org/0009-0007-0978-770X"]},"institutions":[{"id":"https://openalex.org/I162706563","display_name":"Hoseo University","ror":"https://ror.org/01qyd4k24","country_code":"KR","type":"education","lineage":["https://openalex.org/I162706563"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jo, Meounggun","raw_affiliation_strings":["Hoseo University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hoseo University","institution_ids":["https://openalex.org/I162706563"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048441313","display_name":"Jini Tae","orcid":"https://orcid.org/0000-0002-9395-9282","observed_orcids":["https://orcid.org/0000-0002-9395-9282"]},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae, Jini","raw_affiliation_strings":["Gwangju Institute of Science and Technology, School of Humanities and Social Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology, School of Humanities and Social Sciences","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9448000192642212,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9448000192642212,"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/T11448","display_name":"Face recognition and analysis","score":0.01720000058412552,"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/T11094","display_name":"Face Recognition and Perception","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-generated-image-detection","display_name":"AI-generated image detection","score":0.9229999780654907},{"id":"https://openalex.org/keywords/ai-image-generators","display_name":"AI image generators","score":0.5210000276565552},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7540000081062317},{"id":"https://openalex.org/keywords/generative-ai","display_name":"generative AI","score":0.45500001311302185},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.527999997138977},{"id":"https://openalex.org/keywords/trust-in-ai","display_name":"trust in AI","score":0.5809999704360962},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.765999972820282},{"id":"https://openalex.org/keywords/imagen","display_name":"Imagen","score":0.8479999899864197}],"concepts":[{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C2777489069","wikidata":"https://www.wikidata.org/wiki/Q1589822","display_name":"Ceiling (cloud)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406999945640564},{"id":"https://openalex.org/C205545832","wikidata":"https://www.wikidata.org/wiki/Q17156455","display_name":"Young adult","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4334000051021576},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C106347477","wikidata":"https://www.wikidata.org/wiki/Q5384228","display_name":"Equating","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32420000433921814},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C109167261","wikidata":"https://www.wikidata.org/wiki/Q5421955","display_name":"Fell","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30210","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30210","pdf_url":"https://arxiv.org/pdf/2608.30210","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.2608.30210","doi":"https://doi.org/10.48550/arxiv.2608.30210","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30210","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:2608.30210","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30210","pdf_url":"https://arxiv.org/pdf/2608.30210","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/W7204927596.pdf","grobid_xml":"https://content.openalex.org/works/W7204927596.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2020018978","https://openalex.org/W2084413241","https://openalex.org/W2117897510","https://openalex.org/W2164558494","https://openalex.org/W2904367110","https://openalex.org/W3016970897","https://openalex.org/W3034577585","https://openalex.org/W3156470785","https://openalex.org/W3172887788","https://openalex.org/W3208526032","https://openalex.org/W3209972423","https://openalex.org/W4200560037","https://openalex.org/W4210583005","https://openalex.org/W4211017739","https://openalex.org/W4213187648","https://openalex.org/W4285429195","https://openalex.org/W4312933868","https://openalex.org/W4318919287","https://openalex.org/W4375869427","https://openalex.org/W4381851764","https://openalex.org/W4386071953","https://openalex.org/W4387799916","https://openalex.org/W4388631057","https://openalex.org/W4389518686","https://openalex.org/W4393972628","https://openalex.org/W4402264376","https://openalex.org/W4402427382","https://openalex.org/W4402648010","https://openalex.org/W4402683840","https://openalex.org/W4402903971","https://openalex.org/W4402917263","https://openalex.org/W4403570063","https://openalex.org/W4403884296","https://openalex.org/W4404877539","https://openalex.org/W4413443924","https://openalex.org/W4414902235","https://openalex.org/W4416091752","https://openalex.org/W7055216282","https://openalex.org/W7133228402","https://openalex.org/W7140535897","https://openalex.org/W7204533256"],"related_works":["https://openalex.org/W7140535897","https://openalex.org/W7128527411","https://openalex.org/W7204248164","https://openalex.org/W7203677516","https://openalex.org/W7164520719","https://openalex.org/W7207829399","https://openalex.org/W7143516984","https://openalex.org/W7131420539","https://openalex.org/W4415314077","https://openalex.org/W4405623195"],"abstract_inverted_index":{"AI":[0,110],"image":[1,111],"generators":[2],"now":[3,117,185],"create":[4],"face":[5,33],"portraits":[6,34],"that":[7],"are":[8,18,157],"hard":[9],"to":[10,21,124,144],"tell":[11],"from":[12,140],"real":[13,36],"photographs.":[14],"Vision-language":[15],"models":[16,70,166],"(VLMs)":[17],"increasingly":[19],"proposed":[20],"flag":[22],"such":[23],"images.":[24],"We":[25],"benchmarked":[26],"19":[27],"VLMs":[28],"on":[29],"the":[30,47,80,88,168,172,192],"same":[31,48],"198":[32],"--":[35,45],"photographs":[37],"and":[38,41,106,161,197],"identity-matched":[39],"ChatGPT-4o":[40],"Imagen":[42],"3":[43],"versions":[44],"under":[46,87],"task":[49],"as":[50],"our":[51],"earlier":[52],"study":[53],"of":[54,68],"1,667":[55],"adults":[56,73,101,120,188],"(85%":[57],"correct":[58],"overall;":[59],"accuracy":[60,95],"fell":[61],"steeply":[62],"with":[63],"age).":[64],"The":[65,182],"June-2026":[66],"cohort":[67],"14":[69],"only":[71,162],"matched":[72],"in":[74,102,180],"their":[75,103],"20s-30s.":[76],"Four":[77],"weeks":[78],"later":[79],"ceiling":[81],"broke.":[82],"Among":[83],"five":[84],"July-2026":[85],"releases":[86],"identical":[89],"protocol,":[90],"gpt-5.6-sol":[91],"reached":[92],"92.8%":[93],"balanced":[94],"(five-draw":[96],"mean":[97],"92.1%),":[98],"clearly":[99],"above":[100],"20s":[104],"(88.5%),":[105],"claude-fable-5":[107],"detected":[108],"every":[109,152],"while":[112,146],"averaging":[113],"91.9%.":[114],"Model":[115,137],"sensitivity":[116],"exceeds":[118],"young":[119,187],"decisively":[121],"(d'":[122],"up":[123],"3.4":[125],"versus":[126],"~":[127],"2.4).":[128],"What":[129],"has":[130],"not":[131],"been":[132],"overtaken":[133],"is":[134],"human":[135,169,193],"calibration.":[136],"criteria":[138],"spread":[139],"c":[141],"=":[142],"-1.10":[143],"+1.45":[145],"humans":[147],"sit":[148],"near":[149],"zero":[150],"at":[151],"age;":[153],"both":[154],"new":[155],"leaders":[156],"biased":[158],"(+0.44,":[159],"-0.97),":[160],"a":[163],"few":[164],"mid-ranked":[165],"approach":[167],"balance.":[170],"Changing":[171],"labelled":[173],"examples":[174],"still":[175],"flipped":[176],"about":[177],"one":[178],"answer":[179],"four.":[181],"best":[183],"machines":[184],"out-see":[186],"here,":[189],"without":[190],"matching":[191],"balance":[194],"between":[195],"suspicion":[196],"trust.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}