{"id":"W7131085793","doi":"10.1109/iccvw69036.2025.00072","title":"Are Medical Image Generative Models Biologically Trustworthy?","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Generative grammar; Generative model; Perception; Trustworthiness; Focus (optics); Computational model; Cognition","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":[0.007652787,0.0007553473,0.000753612,0.000778764,0.0003966111,0.002191821,0.001354787,0.001669877,0.001557214],"category_scores_gemma":[0.03620968,0.0006093206,0.0009696914,0.0003671045,0.001963625,0.001453864,0.001373955,0.001810044,0.0003843947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151676,"about_ca_system_score_gemma":0.0008257653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002695688,"about_ca_topic_score_gemma":0.0032153,"domain_scores_codex":[0.9981835,0.001017736,0.00007277572,0.00027048,0.0003678289,0.00008763747],"domain_scores_gemma":[0.9808493,0.01576818,0.001097437,0.001416271,0.0006027339,0.0002660324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001942425,0.00004537943,0.007561682,0.0001986598,0.0002103571,0.0001984691,0.0002763047,0.9193164,0.004120337,0.02644007,0.001210155,0.04022797],"study_design_scores_gemma":[0.00002201602,0.00007644561,0.001324163,0.00004753107,0.00003347158,0.0002103324,0.00003862274,0.9586555,0.001934729,0.03650381,0.001129903,0.00002342869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1705007,0.001928283,0.8173733,0.003683304,0.0001783799,0.0001623254,0.0006989413,0.0007419024,0.00473277],"genre_scores_gemma":[0.9263933,0.0007165985,0.07002925,0.0006854737,0.00008970402,0.0001060528,0.0006368913,0.0002260559,0.001116757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007652787,"threshold_uncertainty_score":0.04047233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05275318530772239,"score_gpt":0.3201313267330086,"score_spread":0.2673781414252862,"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."}}