{"id":"W7116655798","doi":"10.1016/b978-0-443-14109-6.00011-0","title":"Am (A)I hallucinating? Nonrobustness, hallucinations, and unpredictable performance of AI for MR image reconstruction","year":2025,"lang":"en","type":"book-chapter","venue":"Advances in magnetic resonance technology and applications","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Trustworthiness; Image (mathematics); Key (lock); Iterative reconstruction; Range (aeronautics); Medical imaging","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":[0.0002498666,0.0002719133,0.0004298019,0.0006889767,0.000260156,0.00002980662,0.0006250243,0.0004062011,0.000008953863],"category_scores_gemma":[0.0001108554,0.0003028389,0.00003635748,0.0004487972,0.0007751334,0.0005245995,0.0003410356,0.0006070929,0.000001029378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004660212,"about_ca_system_score_gemma":0.00009752956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003069795,"about_ca_topic_score_gemma":0.00001787072,"domain_scores_codex":[0.9983514,0.00001465328,0.0005235997,0.0007357761,0.0001304348,0.0002441552],"domain_scores_gemma":[0.9985533,0.0002636224,0.0003351004,0.000618662,0.0002001284,0.0000291453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005412335,0.000009089682,0.0005766517,0.000165969,0.000002600208,4.078591e-7,0.00001017096,0.0001680237,0.00001697963,0.5261692,0.00001778568,0.4728577],"study_design_scores_gemma":[0.0009945218,0.0002957754,0.0006972051,0.001008672,0.0000527928,0.00005794559,0.00003905209,0.1315117,0.0002060367,0.5968714,0.2677301,0.0005348445],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003378579,0.06889139,0.8764718,0.00200565,0.0001718584,0.001777777,0.00004926724,0.0002718426,0.0500226],"genre_scores_gemma":[0.03447375,0.04804194,0.8640469,0.0001562008,0.0001247612,0.002192289,0.00004038845,0.00006248778,0.05086122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4723228,"threshold_uncertainty_score":0.9999424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003720495113728217,"score_gpt":0.2427824457376022,"score_spread":0.239061950623874,"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."}}