{"id":"W7106481835","doi":"10.1609/aaaiss.v7i1.36943","title":"Evaluating Uncertainty in Deep Q-Network Ensembles forTrustworthy Anomaly Detection in Medical Imaging","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Anomaly detection; Trustworthiness; Anomaly (physics); Usability; Medical imaging; Software deployment","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":[0.008636634,0.001343624,0.001054194,0.0009020627,0.0005249871,0.001043222,0.001598343,0.001560581,0.0008410167],"category_scores_gemma":[0.0331188,0.0005742552,0.0004620437,0.0004471466,0.001480464,0.002087309,0.00208585,0.002197087,0.0001287133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001761202,"about_ca_system_score_gemma":0.001222039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007575179,"about_ca_topic_score_gemma":0.007928541,"domain_scores_codex":[0.9978825,0.001009217,0.00009978138,0.0004266347,0.0003860029,0.0001957366],"domain_scores_gemma":[0.9778998,0.01796698,0.001204862,0.0009452433,0.001461212,0.0005217708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002087278,0.00007013509,0.008260443,0.00004484598,0.00007325875,0.00005896917,0.00006937123,0.954915,0.0009550274,0.001700489,0.0005100216,0.0331337],"study_design_scores_gemma":[0.000003346969,0.00002787148,0.0002778469,0.000003520523,0.000003698033,0.000006851397,0.0000054032,0.9970318,0.00036073,0.002235105,0.00004099222,0.000002914013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4169115,0.0009706094,0.5781452,0.001510256,0.00008771197,0.00009919883,0.0002045137,0.0008695638,0.00120146],"genre_scores_gemma":[0.9713274,0.0001059526,0.02768737,0.0001857639,0.00004103056,0.0000402775,0.0001805627,0.00004360331,0.0003880708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008636634,"threshold_uncertainty_score":0.04567546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009250932867616976,"score_gpt":0.2786904353518325,"score_spread":0.2694395024842155,"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."}}