{"id":"W4224927296","doi":"10.1002/ev.20494","title":"Evaluation policy and organizational evaluation capacity building: A study of international aid agency evaluation policies","year":2022,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Agency (philosophy); Pace; Evaluation methods; Program evaluation; Policy analysis; Capacity building; Public relations; Management science; Knowledge management; Process management; Business; Political science; Computer science; Public administration; Economics; Sociology; Economic growth","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0702406,0.0003319473,0.0004262672,0.002328449,0.001524308,0.000310774,0.0006565615,0.0001099304,0.01129295],"category_scores_gemma":[0.0273062,0.0003355342,0.0001647515,0.003545425,0.0000897113,0.001202335,0.0002698326,0.0002525375,0.00002023639],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003124144,"about_ca_system_score_gemma":0.005966497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001098213,"about_ca_topic_score_gemma":0.001091184,"domain_scores_codex":[0.9721263,0.004871704,0.001861967,0.001122017,0.01964198,0.0003760186],"domain_scores_gemma":[0.9817331,0.00113395,0.001406007,0.000785499,0.01477206,0.0001693687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002194581,0.001678603,0.02878462,0.00001036467,0.0003688436,7.767655e-8,0.0177446,0.2687704,0.003533458,0.005806412,0.004765143,0.668318],"study_design_scores_gemma":[0.00819758,0.0007128904,0.1400173,0.00001078236,0.001098284,0.00001291398,0.005615712,0.7586678,0.0004194326,0.07785241,0.007091615,0.0003032608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9749468,0.0003991393,0.003908445,0.002609985,0.002569824,0.008554827,0.0001283582,0.00007449843,0.006808142],"genre_scores_gemma":[0.9930107,0.00002960577,0.001449687,0.0001524099,0.000669078,0.003607129,0.0004806008,0.00003867874,0.0005620984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6680148,"threshold_uncertainty_score":0.9999096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3393749749893569,"score_gpt":0.529793832087028,"score_spread":0.1904188570976711,"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."}}