{"id":"W3217770674","doi":"10.3138/cjpe.69191","title":"Toward an Evidence-Based Approach to Building Evaluation Capacity","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Children's Hospital Foundation; Stollery Children’s Hospital Foundation; Women and Children's Health Research Institute; Social Sciences and Humanities Research Council of Canada; Children's Health Research Institute","keywords":"Work (physics); Accountability; Process management; Capacity building; Computer science; Knowledge management; Management science; Risk analysis (engineering); Business; Political science; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04746416,0.0001772392,0.0003257267,0.0009435455,0.0003069454,0.001047431,0.0006645575,0.0001165943,0.002380023],"category_scores_gemma":[0.01809813,0.0001502939,0.0001792796,0.00192932,0.00006953898,0.00182426,0.00001732523,0.0002760678,0.00006494322],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220083,"about_ca_system_score_gemma":0.01938278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004819517,"about_ca_topic_score_gemma":0.006202808,"domain_scores_codex":[0.9896759,0.002537025,0.001191207,0.0004576092,0.005745034,0.0003932213],"domain_scores_gemma":[0.9836304,0.0003839954,0.0006716311,0.0005762192,0.01365391,0.001083809],"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":[0.00002397833,0.0001266858,0.008591261,0.000009613138,0.00002355364,0.000004699953,0.001859264,0.1176933,0.0006878712,0.0007262862,0.001362386,0.8688911],"study_design_scores_gemma":[0.001387186,0.0008111352,0.07735214,0.0002184432,0.000266407,0.00008834276,0.002642807,0.8873598,0.002547458,0.01044622,0.0165401,0.0003399846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.92625,0.0008857236,0.06025214,0.005912967,0.001478246,0.002121676,0.000009255888,0.00001842693,0.003071548],"genre_scores_gemma":[0.9302196,0.000004072482,0.0684367,0.0007910401,0.0003129798,0.0001630008,0.00002265101,0.00001301354,0.00003696992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8685511,"threshold_uncertainty_score":0.9999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8095482787308166,"score_gpt":0.5628469968990902,"score_spread":0.2467012818317263,"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."}}