{"id":"W7132891675","doi":"","title":"Addressing Challenges for Reliable Machine Learning Model Updates","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Forgetting; Set (abstract data type); Artificial neural network; Quality (philosophy); Reduction (mathematics); Sample (material); Training set; 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":[0.009904542,0.001326623,0.001861618,0.0007283342,0.0009981252,0.003451924,0.00395074,0.002685863,0.002038546],"category_scores_gemma":[0.06868906,0.001421396,0.0009822455,0.000927203,0.001720055,0.005803027,0.005062178,0.007598815,0.001594201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001473706,"about_ca_system_score_gemma":0.002902883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006745156,"about_ca_topic_score_gemma":0.005095327,"domain_scores_codex":[0.9927654,0.003052124,0.0004709437,0.001353287,0.001974211,0.000383968],"domain_scores_gemma":[0.9552646,0.02494525,0.002411314,0.01214762,0.004590977,0.0006403127],"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":[0.0003425683,0.0001673231,0.005482329,0.0003392284,0.0001596997,0.000307171,0.0005661627,0.7198491,0.005329685,0.02881967,0.01088925,0.2277479],"study_design_scores_gemma":[0.00001778868,0.00005336372,0.0003604617,0.00003394745,0.00001258909,0.00007164921,0.00006297966,0.9697663,0.002295193,0.02471056,0.002595843,0.00001933574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03565771,0.001797616,0.9477739,0.006470351,0.0003425612,0.0001126079,0.0002780786,0.004661554,0.002905575],"genre_scores_gemma":[0.7277626,0.001168423,0.2639593,0.00153879,0.0004905569,0.0002659276,0.0007459818,0.000876445,0.003191877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009904542,"threshold_uncertainty_score":0.05238086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4193858989770554,"score_gpt":0.532138414163261,"score_spread":0.1127525151862056,"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."}}