{"id":"W4396707874","doi":"10.3138/cjpe-2024-0011","title":"The Science and Practice of Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Capacity building; Architectural engineering; Political science; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1488352,0.00007851487,0.0001275543,0.0007110875,0.0005252634,0.001299487,0.0003779135,0.0000392904,0.0002104704],"category_scores_gemma":[0.05493576,0.00004814404,0.00005342294,0.001809685,0.0005680007,0.00183081,0.00001821395,0.0001910615,0.00001048899],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006180029,"about_ca_system_score_gemma":0.01473612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003321143,"about_ca_topic_score_gemma":0.002290039,"domain_scores_codex":[0.9918771,0.0009609808,0.0008228096,0.0002075871,0.00590534,0.0002261547],"domain_scores_gemma":[0.9839262,0.001963358,0.0005465417,0.0002442768,0.01304303,0.0002766346],"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":[0.000009186798,0.000008628673,0.000382925,0.000004771448,0.00001672695,0.000001232978,0.001402193,0.0008887289,0.0006823216,0.006334784,0.000869901,0.9893986],"study_design_scores_gemma":[0.0004843935,0.0004916078,0.02153473,0.0001472904,0.0002906133,0.0002826749,0.00411173,0.7523365,0.0009838135,0.04317458,0.1760301,0.0001319397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573808,0.007765989,0.001934958,0.01633427,0.003201207,0.001918794,0.000005944863,0.00001172041,0.01144626],"genre_scores_gemma":[0.9952214,0.000042983,0.004493799,0.00006605001,0.0001143083,0.00003183255,5.981329e-7,0.000004673658,0.00002430116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9892666,"threshold_uncertainty_score":0.9997373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5353283803429555,"score_gpt":0.5759095146980391,"score_spread":0.04058113435508359,"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."}}