{"id":"W2572663707","doi":"","title":"Predictive performance of prevailing approaches to skills assessment techniques: Insights from real vs. synthetic data sets.","year":2014,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Data mining; Artificial intelligence; Machine learning","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":[],"category_scores_codex":[0.02969304,0.0008666806,0.0006045843,0.003429621,0.000491159,0.002375761,0.001317597,0.001215497,0.0009375844],"category_scores_gemma":[0.1280387,0.0002163424,0.0006912259,0.00246499,0.0008645472,0.002002551,0.001577307,0.002135663,0.0004230645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059673,"about_ca_system_score_gemma":0.001233366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005682678,"about_ca_topic_score_gemma":0.00661454,"domain_scores_codex":[0.9868332,0.009371274,0.0005822312,0.001361604,0.001557456,0.0002943036],"domain_scores_gemma":[0.8081961,0.1740977,0.003864576,0.006908708,0.005755838,0.001177032],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001612058,0.001415723,0.3289101,0.0006635138,0.001118784,0.0001591452,0.001754623,0.3529891,0.001512753,0.007833556,0.009124825,0.2929059],"study_design_scores_gemma":[0.00006602535,0.0005234038,0.06070963,0.0002004376,0.00008926613,0.0001451061,0.0006934446,0.92247,0.001442312,0.01188659,0.001719165,0.00005461222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9090413,0.002735694,0.08009666,0.001397898,0.0001391774,0.0002287174,0.002333265,0.0004403332,0.003586939],"genre_scores_gemma":[0.9781651,0.0002952738,0.01874224,0.00007533671,0.00003018549,0.00007662855,0.002300331,0.00003812999,0.0002767863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9703069,"threshold_uncertainty_score":0.1570337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1966317169881965,"score_gpt":0.3636479345042992,"score_spread":0.1670162175161027,"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."}}