{"id":"W1562920609","doi":"10.1111/medu.12126","title":"‘What would my classmates say?’ An international study of the prediction‐based method of course evaluation","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Course (navigation); Psychology; Medical education; Computer science; Mathematics education; Medicine; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002178894,0.0001375447,0.0002489931,0.0002419843,0.00008092813,0.00002964692,0.0003747732,0.0002832474,0.004178165],"category_scores_gemma":[0.005919863,0.00009855551,0.00006627187,0.0007731534,0.0001981252,0.0005236216,0.00004219738,0.0005264219,0.00001515044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002222399,"about_ca_system_score_gemma":0.002973969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000255878,"about_ca_topic_score_gemma":0.00001748016,"domain_scores_codex":[0.9958886,0.000386645,0.0008303454,0.0002911992,0.002452989,0.0001502506],"domain_scores_gemma":[0.9963233,0.0001200198,0.0004379504,0.0006974809,0.002327497,0.00009373845],"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":[0.00006997536,0.01796734,0.1590131,0.0001621584,0.0001666,1.97757e-7,0.006229762,0.0001439971,0.001713565,0.0005376418,0.04216852,0.7718271],"study_design_scores_gemma":[0.002413238,0.0005876548,0.8462104,0.0006356475,0.0004147237,0.00001886937,0.02379015,0.1210673,0.001617672,0.0006157101,0.002507051,0.0001215772],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9593806,0.00005277718,0.001395012,0.03081135,0.005718363,0.001900731,0.000002630469,0.00003306242,0.0007055191],"genre_scores_gemma":[0.9886225,0.00001484541,0.004826917,0.005015708,0.0004127122,0.0005774889,0.0002408403,0.00001961261,0.0002693204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7717055,"threshold_uncertainty_score":0.9967322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465279114529879,"score_gpt":0.4508843595132042,"score_spread":0.4162315683679054,"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."}}