{"id":"W4224793496","doi":"10.3138/cjpe.71430","title":"Redesigning a University-Based Evaluator Education Program for Scholarship and Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Premise; Curriculum; Process (computing); Medical education; Pedagogy; Engineering ethics; Sociology; Psychology; Computer science; Engineering; Political science; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0737377,0.0005933359,0.0004988772,0.003873961,0.005547617,0.007637156,0.004589736,0.001407724,0.01047704],"category_scores_gemma":[0.0500954,0.0007789758,0.000611056,0.001419313,0.002151881,0.004171454,0.009152085,0.004383314,0.002723886],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01831189,"about_ca_system_score_gemma":0.07774902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008737567,"about_ca_topic_score_gemma":0.02247573,"domain_scores_codex":[0.9695159,0.01570158,0.001816619,0.003177,0.007029668,0.002759293],"domain_scores_gemma":[0.8967494,0.01497772,0.006231676,0.01021271,0.04052651,0.03130192],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003774654,0.0068078,0.02818218,0.0005870255,0.00006347825,0.0002856907,0.01356791,0.003974351,0.009234049,0.009222301,0.03631281,0.891385],"study_design_scores_gemma":[0.000980981,0.01314783,0.1813195,0.002596882,0.0002441724,0.001225981,0.02938461,0.02350463,0.04056834,0.01544892,0.6909741,0.0006042058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5191848,0.001497625,0.3306459,0.04694204,0.002260854,0.02218783,0.0005469877,0.00995639,0.06677752],"genre_scores_gemma":[0.5187558,0.0005725155,0.4361296,0.004232023,0.0004331083,0.00566693,0.0005178242,0.0006410028,0.03305116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9816881,"threshold_uncertainty_score":0.3899669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4058180102937288,"score_gpt":0.5556122397401135,"score_spread":0.1497942294463847,"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."}}