{"id":"W7130342024","doi":"10.48448/6sjk-xw45","title":"The Visual Counter Turing Test (VCT²): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (V_AI)","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Overfitting; Benchmark (surveying); Metric (unit); Context (archaeology); Pattern recognition (psychology); Turing test; Generalization; Image (mathematics); Noise (video); Perception","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006001123,0.003323823,0.001101703,0.003061402,0.0009721395,0.00331536,0.003381009,0.002721626,0.004782876],"category_scores_gemma":[0.0400178,0.0006059934,0.001421031,0.001354265,0.001697042,0.003223443,0.003691348,0.002648414,0.003601741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002200204,"about_ca_system_score_gemma":0.001235359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006949634,"about_ca_topic_score_gemma":0.006729947,"domain_scores_codex":[0.9933257,0.002259621,0.000579586,0.001433325,0.002000938,0.000400678],"domain_scores_gemma":[0.9807463,0.01158566,0.001104422,0.002919581,0.002593843,0.001050308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004202458,0.002035576,0.03596861,0.007403541,0.00141135,0.001060514,0.001686159,0.1757254,0.03699096,0.01202791,0.1722629,0.5492247],"study_design_scores_gemma":[0.0005168645,0.003780846,0.02127041,0.0005297878,0.0002647057,0.001413199,0.001040033,0.8370762,0.06760047,0.0168207,0.04939887,0.0002878208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6119601,0.01819017,0.2145116,0.003022571,0.003851685,0.004229825,0.02883106,0.05977515,0.0556279],"genre_scores_gemma":[0.785489,0.001481176,0.1494784,0.001314988,0.0004172267,0.001592945,0.04697035,0.003350332,0.009905538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006949634,"threshold_uncertainty_score":0.03173739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02162384936217195,"score_gpt":0.3797472068194221,"score_spread":0.3581233574572502,"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."}}