{"id":"W4402906011","doi":"10.1167/jov.24.10.1245","title":"Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Concordance; Illusion; Lightness; Perception; Optical illusion; Psychology; Cognitive psychology; Artificial intelligence; Medicine; Computer science; Neuroscience; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005372377,0.000130612,0.0002063298,0.0001484621,0.0003124681,0.0009204208,0.0003593948,0.00005967715,0.00003291075],"category_scores_gemma":[0.00003261186,0.00009066742,0.00005665668,0.0003954602,0.0001104918,0.003613552,0.0001275794,0.0003340828,0.00002076338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009192257,"about_ca_system_score_gemma":0.0001205984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000335656,"about_ca_topic_score_gemma":0.0000186114,"domain_scores_codex":[0.9986587,0.00008618458,0.0003973772,0.0002466206,0.0004155486,0.0001956119],"domain_scores_gemma":[0.9991019,0.0001360352,0.0001797953,0.0002127826,0.0002779707,0.00009149108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007125881,0.0003284489,0.001180148,0.0002645685,0.0000961097,0.001571652,0.02391372,0.001528108,0.6929769,0.1187927,0.006389773,0.1528866],"study_design_scores_gemma":[0.002315263,0.01277648,0.09319536,0.01954238,0.0003333869,0.008490632,0.0181399,0.4274688,0.1091993,0.176309,0.1293452,0.002884299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4613758,0.0005937386,0.5337107,0.003186141,0.0004454444,0.00006594183,4.366876e-7,0.00004576919,0.000575977],"genre_scores_gemma":[0.9825916,0.0001482791,0.01658558,0.0003365751,0.0002029936,0.000001084391,4.513048e-7,0.00001212457,0.0001213572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5837776,"threshold_uncertainty_score":0.8875639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02561289469377943,"score_gpt":0.3638951594530557,"score_spread":0.3382822647592763,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}