{"id":"W3033487789","doi":"10.1186/s41039-020-00134-8","title":"Can automated item generation be used to develop high quality MCQs that assess application of knowledge?","year":2020,"lang":"en","type":"article","venue":"Research and Practice in Technology Enhanced Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Ottawa; Ottawa Hospital; Medical Council of Canada","funders":"","keywords":"Quality (philosophy); Multiple choice; Cognition; Recall; Item analysis; Wilcoxon signed-rank test; Sample (material); Computer science; Test (biology); Modalities; Psychology; Psychometrics; Significant difference; Statistics; Clinical psychology; Mathematics; Cognitive psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003981415,0.00008826551,0.0002068758,0.0003209316,0.0004225516,0.00007467996,0.0002879224,0.0002391882,0.00001887993],"category_scores_gemma":[0.02218572,0.00009526653,0.00001060341,0.003016035,0.0002695814,0.0003070484,0.0001857837,0.0007175058,0.00001608314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001339965,"about_ca_system_score_gemma":0.0003657951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00107261,"about_ca_topic_score_gemma":0.00407297,"domain_scores_codex":[0.9971117,0.00135717,0.0002595819,0.0003595626,0.0005286425,0.0003833771],"domain_scores_gemma":[0.9960719,0.002777051,0.0001664781,0.0001260219,0.0007502103,0.0001083103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003102785,0.0003285569,0.115474,0.0001040537,0.00008115801,0.000008692599,0.1052999,0.0001399013,0.5690476,0.04643561,0.000909178,0.161861],"study_design_scores_gemma":[0.002921801,0.001816231,0.08137865,0.0001851662,0.0000449309,0.000003396424,0.455408,0.007267222,0.2632423,0.003869704,0.1827301,0.001132495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9283825,0.0001455401,0.00248046,0.05950367,0.0000425679,0.0006257017,0.000001633181,0.0003376905,0.008480248],"genre_scores_gemma":[0.9959963,0.0002726961,0.003266623,0.00006661401,0.00006936661,0.0001155118,0.00001575167,0.00001021267,0.0001869429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3501081,"threshold_uncertainty_score":0.9860508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2606414184306209,"score_gpt":0.5297904732686232,"score_spread":0.2691490548380023,"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."}}