{"id":"W4393862188","doi":"10.3138/cjpe-2024-0012","title":"Strengthening Evaluation Capacity Building Practice Through Competition: The Max Bell School of Public Policy’s 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":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Ottawa; Queen's University; McGill University","funders":"","keywords":"Competition (biology); Capacity building; Political science; Architectural engineering; Economics; Engineering; Economic growth","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07587067,0.0004503823,0.0006475574,0.001390879,0.0319698,0.0200765,0.003433253,0.01279647,0.007744239],"category_scores_gemma":[0.04520979,0.001009617,0.0005935429,0.001663967,0.02210915,0.0109409,0.01737764,0.02468739,0.0008638354],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.05127563,"about_ca_system_score_gemma":0.1359357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.143455,"about_ca_topic_score_gemma":0.3179927,"domain_scores_codex":[0.9493087,0.02987361,0.0008229237,0.002985268,0.006194028,0.0108154],"domain_scores_gemma":[0.9159973,0.0330655,0.001508331,0.002742958,0.0108969,0.03578905],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009990208,0.0006467568,0.003511045,0.0001700966,0.00001723932,0.0007139589,0.035516,0.000742666,0.000604395,0.3481781,0.5427296,0.06707019],"study_design_scores_gemma":[0.0000581545,0.000101125,0.003171746,0.000454933,0.000005257207,0.000148892,0.03618359,0.001306481,0.0007393163,0.04282874,0.9148789,0.0001227958],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01866006,0.003618908,0.003089697,0.9365113,0.001859026,0.0001238179,0.00003342457,0.0000563354,0.03604733],"genre_scores_gemma":[0.7046121,0.00541571,0.02309974,0.1978129,0.00179777,0.0007449627,0.0001138453,0.0003076844,0.06609542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9487244,"threshold_uncertainty_score":0.4012473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6298851995534387,"score_gpt":0.5347281576265688,"score_spread":0.09515704192686991,"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."}}