{"id":"W1700780107","doi":"10.3138/cjpe.0028.006","title":"Evaluator Competencies: The Canadian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Engineering ethics; Context (archaeology); Political science; Psychology; Sociology; Public relations; Management; Engineering; History; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03117493,0.0001441911,0.0002334573,0.0006912653,0.0009627892,0.0009863564,0.001173106,0.00008747546,0.004890842],"category_scores_gemma":[0.00868959,0.00008814901,0.0001453778,0.001000442,0.0002788492,0.0006024689,0.00001293335,0.0002878207,0.0003025729],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008618571,"about_ca_system_score_gemma":0.01588095,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07267068,"about_ca_topic_score_gemma":0.9269716,"domain_scores_codex":[0.9936276,0.001196469,0.0009748701,0.0002254444,0.003518889,0.000456721],"domain_scores_gemma":[0.9925585,0.000485567,0.0006411663,0.0005516667,0.004682443,0.001080674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006124753,0.00001527536,0.04043414,0.000001826146,0.00002004162,0.000002911393,0.005886842,0.00351475,0.00001881497,0.003694285,0.009606996,0.936798],"study_design_scores_gemma":[0.000586992,0.0003709471,0.1408627,0.00002867458,0.00005801668,0.00006105749,0.00340962,0.181893,0.00004260425,0.01154455,0.6609697,0.0001721335],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9165226,0.0008530042,0.002148093,0.02598231,0.004782397,0.002723355,0.00001348318,0.00002222019,0.0469526],"genre_scores_gemma":[0.9963461,0.000003401501,0.001668255,0.001321382,0.0003248088,0.0000882931,0.000005013846,0.000009712614,0.000233065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9366258,"threshold_uncertainty_score":0.9996606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3618976917865132,"score_gpt":0.5260247839748239,"score_spread":0.1641270921883107,"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."}}