{"id":"W2967863356","doi":"10.4102/aej.v7i1.400","title":"Evaluation2 – Evaluating the national evaluation system in South Africa: What has been achieved in the first 5 years?","year":2019,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Department for International Development","keywords":"Mandate; Cabinet (room); Benchmarking; Government (linguistics); Monitoring and evaluation; Legislation; Business; Political science; Economic growth; Public administration; Geography; Economics; Marketing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.336648,0.001242222,0.001822853,0.004010301,0.004023605,0.0130208,0.00306891,0.002694348,0.008404044],"category_scores_gemma":[0.3160079,0.0006444671,0.001502082,0.005370826,0.00479534,0.0122801,0.006787196,0.003489314,0.00136277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03657812,"about_ca_system_score_gemma":0.1009827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03204485,"about_ca_topic_score_gemma":0.02727994,"domain_scores_codex":[0.7039132,0.2413447,0.0128975,0.003994267,0.02767122,0.01017901],"domain_scores_gemma":[0.6418645,0.137911,0.02209825,0.01550752,0.1684903,0.01412843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001410861,0.0009910017,0.02757073,0.02279442,0.0005553092,0.0003848801,0.01831634,0.004143118,0.001207023,0.05486948,0.07175566,0.7960013],"study_design_scores_gemma":[0.0008066955,0.004472093,0.1121385,0.122865,0.0007238202,0.00097425,0.05796925,0.006817732,0.00779403,0.02870524,0.6562603,0.000473103],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2128996,0.169879,0.05510821,0.2725255,0.005902534,0.01420627,0.003627436,0.0009049051,0.2649466],"genre_scores_gemma":[0.8522779,0.03786676,0.07020642,0.01401702,0.0005521488,0.006321024,0.002924251,0.000407056,0.01542732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.336648,"threshold_uncertainty_score":0.8180312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3913963728434102,"score_gpt":0.4863411167715641,"score_spread":0.09494474392815389,"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."}}