{"id":"W4324119979","doi":"10.2196/40931","title":"Computerized Block Games for Automated Cognitive Assessment: Development and Evaluation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Serious Games","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Computer science; Cognition; Cube (algebra); Usability; Block (permutation group theory); Artificial intelligence; Wechsler Adult Intelligence Scale; Human–computer interaction; Machine learning; Psychology; Mathematics","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":[0.005780496,0.001264827,0.0009235797,0.00145399,0.0002478687,0.0005783836,0.001224928,0.0005329039,0.002925837],"category_scores_gemma":[0.01012908,0.0004382872,0.0006858014,0.000616747,0.0005032734,0.0007296549,0.001003593,0.0005599118,0.001068593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007048908,"about_ca_system_score_gemma":0.001693211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002900889,"about_ca_topic_score_gemma":0.002654734,"domain_scores_codex":[0.9971471,0.001342496,0.0002994856,0.0002287639,0.0008046142,0.0001775854],"domain_scores_gemma":[0.9928929,0.002855295,0.0005097648,0.0005136047,0.002410399,0.0008180639],"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":[0.02227226,0.09296327,0.1275998,0.00185122,0.0007286031,0.001306967,0.003258044,0.01278653,0.02677259,0.001767348,0.006038866,0.7026545],"study_design_scores_gemma":[0.02347354,0.2975359,0.525713,0.000668556,0.001127331,0.002832627,0.001437794,0.09312285,0.02768679,0.001211095,0.02489499,0.0002956949],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9646543,0.0003012379,0.01588753,0.00006152193,0.000044188,0.01549656,0.0008860259,0.0003191899,0.002349439],"genre_scores_gemma":[0.8564186,0.001231653,0.1021607,0.0001353278,0.00005046238,0.03180685,0.003698525,0.0001185177,0.004379404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005780496,"threshold_uncertainty_score":0.03057057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08493108025242485,"score_gpt":0.4792800482877724,"score_spread":0.3943489680353476,"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."}}