{"id":"W4393902965","doi":"10.3138/cjpe-2024-0004","title":"Developing Evaluation Capacity Building Competencies: Participant Reflections From the Evaluation Capacity Case Challenge","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":"McGill University; University of Waterloo; University of Alberta","funders":"","keywords":"Capacity building; Capacity development; Psychology; Business; Environmental resource management; Environmental science; Economic growth; Economics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.07147564,0.0002795165,0.0003829101,0.0007960739,0.001195796,0.001619231,0.0006117743,0.0001722242,0.003237927],"category_scores_gemma":[0.01126391,0.0001929784,0.0002622924,0.001887365,0.0002306234,0.00156341,0.00003104515,0.0006422185,0.0001230457],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002922289,"about_ca_system_score_gemma":0.01470282,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007024803,"about_ca_topic_score_gemma":0.226203,"domain_scores_codex":[0.9872764,0.003767997,0.001807547,0.0005513091,0.006055476,0.0005412483],"domain_scores_gemma":[0.9878744,0.00169007,0.0008288441,0.000604508,0.008522372,0.0004797849],"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":[0.00001280748,0.00004918832,0.001441958,0.00001311487,0.000214367,0.00003771132,0.01924785,0.01597334,0.0002558626,0.004941018,0.001473371,0.9563394],"study_design_scores_gemma":[0.0008655298,0.0003065201,0.01528825,0.0003197008,0.001189224,0.0005495473,0.01080827,0.8298866,0.0001807876,0.08958665,0.05068807,0.000330925],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.96294,0.003803036,0.01195777,0.01263557,0.004305771,0.003081008,0.00005221737,0.00004606336,0.001178557],"genre_scores_gemma":[0.9875508,0.00003870948,0.01081146,0.0002456793,0.0007874579,0.0004885492,0.00003620865,0.00002294749,0.00001821665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9560085,"threshold_uncertainty_score":0.9995875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8696201595344439,"score_gpt":0.5799551477667225,"score_spread":0.2896650117677214,"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."}}