{"id":"W2036552474","doi":"10.1007/s10459-005-2327-z","title":"Using a Sampling Strategy to Address Psychometric Challenges in Tutorial-Based Assessments","year":2006,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sampling (signal processing); Medical education; Computer science; Educational measurement; Medical physics; Psychology; Data science; Medicine; Curriculum; Pedagogy","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":[],"consensus_categories":[],"category_scores_codex":[0.003055021,0.000130471,0.0002128557,0.00105989,0.0005118737,0.0001504202,0.0004280843,0.00006107033,0.00003145406],"category_scores_gemma":[0.0001511107,0.0001365883,0.0000253724,0.003988095,0.0001618607,0.0009872658,0.00002130616,0.0001262788,0.0000058051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409286,"about_ca_system_score_gemma":0.00247006,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0144778,"about_ca_topic_score_gemma":0.02863886,"domain_scores_codex":[0.9972848,0.000297901,0.0005134509,0.0005068111,0.0007589438,0.0006381443],"domain_scores_gemma":[0.9990983,0.0003086654,0.0002460541,0.0001354575,0.00008530826,0.000126224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002647965,0.0009040429,0.6548269,0.000146916,0.000001338906,4.088809e-7,0.004290981,0.04230682,0.00003550334,0.05795266,0.00008241313,0.2394255],"study_design_scores_gemma":[0.001153762,0.0007379159,0.8142114,0.001126147,0.000005843536,6.543168e-7,0.06156416,0.002584984,0.00001876784,0.02788076,0.08987594,0.0008396562],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8867594,0.03304899,0.001905738,0.00549378,0.0100663,0.002296202,0.000004300486,0.00009543548,0.06032989],"genre_scores_gemma":[0.9790921,0.0028439,0.01700677,0.0002219659,0.0006690136,0.00009833502,0.000003919416,0.000007249985,0.00005673556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2385858,"threshold_uncertainty_score":0.9920849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2266352479572664,"score_gpt":0.5530907750885159,"score_spread":0.3264555271312495,"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."}}