{"id":"W2614587327","doi":"10.2196/games.7033","title":"Medical Student Evaluation With a Serious Game Compared to Multiple Choice Questions Assessment","year":2017,"lang":"en","type":"article","venue":"JMIR Serious Games","topic":"Educational Games and Gamification","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multiple choice; Test (biology); Clinical endpoint; Medicine; Randomized controlled trial; Medical education; Medical school; Correlation; Variance (accounting); Psychology; Internal medicine; Significant difference; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000660403,0.0002389874,0.0002886745,0.0001176753,0.0003632654,0.0002615438,0.0006947776,0.0001435327,0.001368989],"category_scores_gemma":[0.0003529191,0.0002075382,0.00006455911,0.0001202677,0.0001411847,0.0001693697,0.0001052126,0.000259599,0.0003566346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002417902,"about_ca_system_score_gemma":0.0003702677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001058918,"about_ca_topic_score_gemma":0.002993311,"domain_scores_codex":[0.9973671,0.0002183903,0.0003736702,0.00059101,0.001067095,0.0003827541],"domain_scores_gemma":[0.9974513,0.0002090125,0.0003131688,0.001265146,0.0004022393,0.0003591477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002317484,0.002804163,0.7087793,0.00003931727,0.000396397,0.00002869461,0.01630364,0.0004480087,0.0005327991,0.004390239,0.01353797,0.2525078],"study_design_scores_gemma":[0.00159602,0.000245106,0.9288333,0.00008267662,0.00005468431,0.00002971411,0.001382875,0.001057344,0.00001001918,0.00007174958,0.0663832,0.0002533346],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754871,0.0001489211,0.0006502506,0.01259537,0.001159528,0.002005027,0.0000214351,0.0001239761,0.007808433],"genre_scores_gemma":[0.9919462,0.00001203791,0.0009175265,0.0007414997,0.0004161073,0.002972821,0.00009078489,0.00003854189,0.002864486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2522544,"threshold_uncertainty_score":0.9995439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04195865251939022,"score_gpt":0.4608609860364374,"score_spread":0.4189023335170471,"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."}}