{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002488175,0.0004074045,0.0005666458,0.000458245,0.000558749,0.0003009027,0.001838469,0.0002814427,0.00002741422],"category_scores_gemma":[0.0003630029,0.000367675,0.0002327959,0.004102075,0.0004179449,0.001122204,0.00139412,0.0007455755,0.000002403884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003598328,"about_ca_system_score_gemma":0.0003471811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006866702,"about_ca_topic_score_gemma":0.001180118,"domain_scores_codex":[0.9961337,0.0000724272,0.001381698,0.000895033,0.0007667335,0.0007503447],"domain_scores_gemma":[0.9981098,0.0001618487,0.0007051034,0.000431754,0.0004909118,0.0001006354],"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":[0.0006935923,0.0006661234,0.2699611,0.0015328,0.0001426865,0.000007883132,0.006046887,0.01284753,0.08821591,0.1432507,0.0005516803,0.4760831],"study_design_scores_gemma":[0.0009161683,0.0002289993,0.02581513,0.002237471,0.00008248002,0.00008342775,0.0009739186,0.8485138,0.08080447,0.03812883,0.001592738,0.0006225606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9352047,0.001809365,0.02774665,0.02024515,0.00135277,0.002378874,0.000004510337,0.0003222144,0.01093576],"genre_scores_gemma":[0.9946119,0.0005043043,0.003532573,0.0003819372,0.0001507316,0.0003658036,6.574934e-7,0.00002411282,0.0004280254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8356663,"threshold_uncertainty_score":0.9998775,"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."}}