{"id":"W4401363543","doi":"10.3138/cjpe-2023-0021","title":"Breaking the Mould? Expanding our Conceptualization of Evaluator Competencies","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Conceptualization; Psychology; Engineering ethics; Sociology; Computer science; Engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.02576674,0.0008074378,0.0006169272,0.006212343,0.004324614,0.01168548,0.002563535,0.00446967,0.005189915],"category_scores_gemma":[0.02947758,0.0003780624,0.0008564236,0.003166345,0.04693924,0.01948817,0.006255181,0.00651124,0.0006193305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01220782,"about_ca_system_score_gemma":0.01791573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02317343,"about_ca_topic_score_gemma":0.01741783,"domain_scores_codex":[0.9801601,0.01416596,0.00065112,0.001066689,0.002417283,0.001538762],"domain_scores_gemma":[0.9681481,0.02132843,0.001988891,0.001929843,0.004511241,0.002093548],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001416363,0.00004309234,0.001947778,0.0001398889,0.000008733217,0.00008225521,0.01719359,0.0006698922,0.0001134462,0.9630542,0.00203978,0.01469325],"study_design_scores_gemma":[0.00003355373,0.0001237302,0.005549936,0.002214022,0.00003486238,0.0003944223,0.02917788,0.005186644,0.0005091361,0.7863842,0.1703021,0.00008959026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06614591,0.02052468,0.19445,0.1642917,0.001117134,0.0005049182,0.0001554535,0.0003108051,0.5524995],"genre_scores_gemma":[0.9308405,0.00568944,0.04082021,0.01232349,0.000244786,0.00044115,0.00006490639,0.0001127639,0.009462711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9742333,"threshold_uncertainty_score":0.1362692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4040203586186757,"score_gpt":0.5589097674439346,"score_spread":0.1548894088252589,"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."}}