{"id":"W1547906511","doi":"10.3138/cjpe.0028.008","title":"Evaluator Competencies: The South African Government Experience","year":2014,"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":"Government (linguistics); Presidency; Context (archaeology); Institution; Process (computing); Political science; Computer science; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02677136,0.0001388394,0.0002324846,0.0001869687,0.0004526747,0.0005932868,0.0009982089,0.00005217805,0.003009556],"category_scores_gemma":[0.007263319,0.00008091856,0.0001518722,0.0007221343,0.0002281765,0.0004497525,0.00002336152,0.0002141725,0.000140736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005617798,"about_ca_system_score_gemma":0.002961766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002065372,"about_ca_topic_score_gemma":0.005722884,"domain_scores_codex":[0.9917259,0.001130759,0.0009748143,0.00022737,0.005608813,0.0003323861],"domain_scores_gemma":[0.99527,0.0005202429,0.0009428757,0.0005296713,0.002240296,0.0004969074],"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":[0.00001761194,0.0000316987,0.03293435,0.000002144368,0.00002421597,0.00000139483,0.01580688,0.003931116,0.00004900346,0.001637073,0.002954001,0.9426105],"study_design_scores_gemma":[0.001183997,0.0009564426,0.1614405,0.00004551733,0.000122165,0.00004344007,0.03366141,0.2984102,0.0001653873,0.008112582,0.4955974,0.0002610025],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9661425,0.0003491083,0.005624685,0.00732088,0.002023287,0.00160007,0.00001124818,0.00001443902,0.0169138],"genre_scores_gemma":[0.9968649,0.000002610285,0.001937886,0.0005800732,0.0002811376,0.0001038722,0.000001698867,0.000008658168,0.0002191518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9423495,"threshold_uncertainty_score":0.9979019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2717111550388943,"score_gpt":0.4784742502509596,"score_spread":0.2067630952120653,"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."}}