{"id":"W4412785599","doi":"","title":"Monitoring morphometric drift in lifelong learning segmentation of the spinal cord.","year":2025,"lang":"en","type":"preprint","venue":"PubMed","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Canadian Institute for Advanced Research; University of British Columbia; Mila - Quebec Artificial Intelligence Institute; University of Toronto; University Health Network; Université de Montréal; Praxis Spinal Cord Institute; St. Michael's Hospital; Polytechnique Montréal","funders":"","keywords":"Spinal cord; Segmentation; Lifelong learning; Artificial intelligence; Computer science; Cartography; Psychology; Geography; Neuroscience; Pedagogy","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":[],"consensus_categories":[],"category_scores_codex":[0.000392628,0.0001379786,0.0002661602,0.0004969874,0.00002703613,0.00003164227,0.0002639924,0.0001065581,0.000004041129],"category_scores_gemma":[0.0003678398,0.0001183719,0.0001188093,0.0009659128,0.00002454982,0.00003127598,0.0001892219,0.0008047397,9.603406e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001293306,"about_ca_system_score_gemma":0.00002189408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001542491,"about_ca_topic_score_gemma":0.00000268104,"domain_scores_codex":[0.9989243,0.00006047095,0.0003277368,0.0001787395,0.0002789194,0.0002299028],"domain_scores_gemma":[0.99957,0.00005037275,0.00008651998,0.0002106871,0.00002976978,0.00005267744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000003643832,0.00001373005,0.2697335,0.0005583066,0.00009540765,0.000002437349,0.00007160208,0.1180452,0.00005649301,0.000002257942,0.00005392106,0.6113634],"study_design_scores_gemma":[0.0002119762,0.000003562665,0.9686152,0.0006540528,0.0001082378,5.115822e-7,0.0001214271,0.02502872,0.004864834,0.0000483795,0.0001676238,0.0001754526],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883475,0.00339322,0.003645105,0.0001370109,0.002080567,0.000403967,0.000004345201,0.0001398965,0.001848397],"genre_scores_gemma":[0.998367,0.0003992022,0.0002425688,0.000007432828,0.0001496906,0.0003853351,0.000004084816,0.00001173272,0.0004329178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6988817,"threshold_uncertainty_score":0.4827064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02273503713183497,"score_gpt":0.2548911094055117,"score_spread":0.2321560722736767,"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."}}