{"id":"W3131127151","doi":"10.1016/j.media.2021.102009","title":"Predicting future cognitive decline with hyperbolic stochastic coding","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Division of Information and Intelligent Systems; National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute; National Institute on Aging; Canadian Institutes of Health Research","keywords":"Cognition; Coding (social sciences); Computer science; Cognitive decline; Artificial intelligence; Mathematics; Psychology; Statistics; Medicine; Dementia","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008221352,0.0002507419,0.0006075234,0.0002519651,0.0002202415,0.0002861501,0.0008479758,0.0001269864,0.0005233709],"category_scores_gemma":[0.001703708,0.0001976293,0.0002750109,0.004094048,0.0002104342,0.000357606,0.0009714245,0.000495874,0.00003916967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005879581,"about_ca_system_score_gemma":0.0003377927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006911539,"about_ca_topic_score_gemma":0.0003880054,"domain_scores_codex":[0.9963734,0.0002729491,0.0004454096,0.000923555,0.001489384,0.0004953578],"domain_scores_gemma":[0.9972178,0.0008521415,0.0001374396,0.0006744803,0.0006401704,0.0004779148],"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":[0.00009009912,0.002500997,0.21872,0.0002014327,0.00936394,0.01201385,0.006070754,0.005194622,0.0006770692,0.002620974,0.0003332885,0.742213],"study_design_scores_gemma":[0.0007012287,0.00007719069,0.03144124,0.00005701333,0.0009189283,0.0001636553,0.0004247805,0.965153,0.0002744237,0.0004100068,0.00007251521,0.0003059961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09764153,0.0003117622,0.8971352,0.004051581,0.0001719566,0.00008937644,0.000006869307,0.0002245821,0.0003671562],"genre_scores_gemma":[0.9459549,0.00002229855,0.05190365,0.001318083,0.0006580762,0.0000180646,0.00003831311,0.0000143569,0.00007231708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9599584,"threshold_uncertainty_score":0.8059089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008760066034389334,"score_gpt":0.2621183790182851,"score_spread":0.2533583129838957,"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."}}