{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009225665,0.000456498,0.001019254,0.001359974,0.00029733,0.0003203867,0.00403278,0.0003547035,0.00005247762],"category_scores_gemma":[0.02499498,0.0003591681,0.0001632508,0.002577491,0.0001975092,0.0008748331,0.001891775,0.0005692003,0.00001643392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002715998,"about_ca_system_score_gemma":0.0002596983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003140387,"about_ca_topic_score_gemma":0.0002696217,"domain_scores_codex":[0.9931418,0.001188099,0.001591793,0.001590949,0.001771416,0.0007159397],"domain_scores_gemma":[0.9819166,0.01171465,0.0009939566,0.004614501,0.0003324274,0.0004278719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003053452,0.0006778254,0.284214,0.00006451685,0.0001262245,0.000008266512,0.001183516,0.004076728,0.00562719,0.004697795,0.003362094,0.6956565],"study_design_scores_gemma":[0.0003233445,0.0007969025,0.3408565,0.0002562294,0.00006243114,0.00001644373,0.0004273865,0.6244044,0.01633141,0.01384682,0.002149425,0.0005287221],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4289213,0.0001901545,0.5628542,0.0005106266,0.0001802996,0.0008815085,0.0001639039,0.000428804,0.005869213],"genre_scores_gemma":[0.5924266,0.0001216015,0.4067353,0.0002653012,0.0001015781,0.0001808239,0.0000354135,0.00003366302,0.00009966402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6951278,"threshold_uncertainty_score":0.999886,"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."}}