{"id":"W2601091369","doi":"","title":"Do multiple true-false items beat the commonly used one-best-answers questions regarding to the Ottawa Criteria for Good Assessment? Results of a literature review","year":2015,"lang":"en","type":"review","venue":"Bern Open Repository and Information System (University of Bern)","topic":"Innovations in Medical Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Equivalence (formal languages); Psychology; Test (biology); Medicine; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003890436,0.0002585526,0.00133335,0.0002695972,0.0005641456,0.0001942896,0.0007517695,0.0002817263,0.000005400783],"category_scores_gemma":[0.0004196978,0.0001815451,0.0002605822,0.0008624732,0.0001245878,0.001359677,0.0002480427,0.0003933275,0.00001103872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000349261,"about_ca_system_score_gemma":0.0005562067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002482095,"about_ca_topic_score_gemma":0.00001561833,"domain_scores_codex":[0.9973086,0.0004914221,0.001271422,0.0002446633,0.0005178134,0.0001661242],"domain_scores_gemma":[0.9952316,0.0003032036,0.001826732,0.0009654784,0.001562481,0.0001105058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006119948,0.0003181608,0.0001963878,0.2653766,0.001456752,0.00001128683,0.02142847,0.00000642752,0.000008172345,0.01364317,0.2053472,0.4915954],"study_design_scores_gemma":[0.001178767,0.0001767342,0.00007431142,0.1134709,0.001328712,0.0001699628,0.005820369,0.000111146,0.000001015988,0.000002081642,0.8775087,0.0001572917],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005005594,0.929231,0.002893676,0.005534514,0.00186477,0.01993477,0.001550426,0.00007473367,0.03841548],"genre_scores_gemma":[0.006249047,0.9698139,0.01101476,0.0006979967,0.0004474537,0.0002488586,0.004084572,0.00005675822,0.007386623],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6721615,"threshold_uncertainty_score":0.7403194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05756069446982031,"score_gpt":0.3621638707093862,"score_spread":0.3046031762395658,"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."}}