{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2205196,0.002182913,0.001727632,0.004357683,0.004190004,0.003328521,0.003092085,0.003685422,0.004262615],"category_scores_gemma":[0.4636448,0.001368724,0.001931955,0.003542583,0.002390711,0.002357807,0.00474003,0.003352382,0.002453133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002356213,"about_ca_system_score_gemma":0.005554256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003555404,"about_ca_topic_score_gemma":0.005453062,"domain_scores_codex":[0.6871928,0.2370594,0.02727733,0.009168977,0.03680255,0.002498912],"domain_scores_gemma":[0.65291,0.1943495,0.01303354,0.05152665,0.08533984,0.00284045],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005416466,0.014714,0.2946862,0.002831347,0.001964796,0.001452004,0.04185125,0.007452928,0.02202605,0.05329335,0.02962438,0.5246872],"study_design_scores_gemma":[0.008964125,0.04689282,0.377074,0.003128043,0.003706351,0.005227942,0.02541956,0.1946565,0.09095602,0.0759953,0.1671413,0.0008380184],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2092368,0.0005132849,0.6408706,0.001142256,0.002254481,0.1342577,0.0008897801,0.0007023053,0.0101328],"genre_scores_gemma":[0.348976,0.0003365742,0.4613513,0.003272398,0.0004315397,0.1790786,0.001117766,0.0002355167,0.005200306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7794803,"threshold_uncertainty_score":0.9612381,"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."}}