{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007103704,0.0002099536,0.0002678482,0.000154488,0.000196359,0.00007872386,0.0001325454,0.00009461307,0.0002794019],"category_scores_gemma":[0.00002756793,0.0001802078,0.00003752685,0.0003448714,0.00005033796,0.00006753777,0.00006403707,0.000106379,0.000176077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005093612,"about_ca_system_score_gemma":0.0001072965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009547983,"about_ca_topic_score_gemma":0.000007849392,"domain_scores_codex":[0.9981609,0.0002741789,0.00035411,0.0005436104,0.000325618,0.0003415564],"domain_scores_gemma":[0.9989749,0.000403652,0.0001429055,0.0001628145,0.0002175555,0.00009814961],"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":[0.0007888438,0.007088899,0.142207,0.0001427971,0.002018631,0.00005505788,0.05370907,0.00003188712,0.0007828464,0.001446758,0.07032757,0.7214006],"study_design_scores_gemma":[0.00361745,0.0006330285,0.9782171,0.00003257242,0.00005728934,0.000009173331,0.006826896,0.001913632,0.00001367807,0.0003727679,0.008070389,0.0002360707],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919755,0.00007077234,0.00007636319,0.0005036843,0.001051189,0.003189329,0.00003176695,0.0006155272,0.002485897],"genre_scores_gemma":[0.9909072,0.000004291097,0.0014597,0.0002888429,0.0001165644,0.005097319,0.0002785432,0.00002471703,0.001822848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.83601,"threshold_uncertainty_score":0.734866,"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."}}