{"id":"W4412398143","doi":"10.2196/66300","title":"Optimizing the Color Shapes Task for Ambulatory Assessment and Drift Diffusion Modeling: A Factorial Experiment","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging","keywords":"Preprint; Factorial; Task (project management); Factorial experiment; Computer science; Statistics; Artificial intelligence; Mathematics; Engineering; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004367155,0.001422559,0.001002999,0.000297479,0.0005505859,0.0008057277,0.001030702,0.001323111,0.002570865],"category_scores_gemma":[0.01478584,0.0007987561,0.0007887505,0.0002522873,0.0008817884,0.001057838,0.001131525,0.001297432,0.0004969815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004386113,"about_ca_system_score_gemma":0.0009225312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001426208,"about_ca_topic_score_gemma":0.00171442,"domain_scores_codex":[0.9981194,0.0006884455,0.0002693016,0.0004629374,0.0002289693,0.000230982],"domain_scores_gemma":[0.987498,0.008242292,0.001630658,0.001367548,0.0006440467,0.0006174133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.224322,0.1027578,0.04977532,0.001212885,0.000988722,0.0004593879,0.005631881,0.03208655,0.4834239,0.001848852,0.00190526,0.09558745],"study_design_scores_gemma":[0.0336962,0.4558823,0.2040396,0.0001581396,0.001776155,0.0005460953,0.0006970682,0.1392097,0.1474537,0.007891284,0.00776192,0.000888015],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939247,0.00003563196,0.00457796,0.00002771645,0.00001982899,0.001006184,0.0001163738,0.00005353813,0.0002380284],"genre_scores_gemma":[0.9559678,0.00009845343,0.03153021,0.0002104831,0.00006461002,0.01008958,0.0004424445,0.00008889802,0.001507423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004367155,"threshold_uncertainty_score":0.02309602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06285972692728278,"score_gpt":0.4633489676512955,"score_spread":0.4004892407240127,"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."}}