{"id":"W4396707487","doi":"10.3138/cjpe-2024-0013","title":"Concluding Remarks: A Bright Future for 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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Engineering ethics; Management science; Capacity building; Computer science; Political science; Engineering; Law","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04824236,0.0001687318,0.0002859178,0.001096359,0.000387673,0.001306932,0.00044111,0.0001379537,0.002352552],"category_scores_gemma":[0.004999172,0.0001281898,0.0002700766,0.00112419,0.00007861318,0.001290068,0.00001041998,0.0002857222,0.00004257833],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214637,"about_ca_system_score_gemma":0.008695615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001628309,"about_ca_topic_score_gemma":0.006344135,"domain_scores_codex":[0.9940431,0.0007384848,0.001166037,0.0003493571,0.003340472,0.0003625102],"domain_scores_gemma":[0.9921042,0.0006291146,0.0005422503,0.0002810498,0.006000883,0.0004424446],"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":[0.00001545246,0.00001360387,0.001052334,0.00002092947,0.00005660998,0.000003015699,0.001403871,0.002099902,0.0001753102,0.004017292,0.01357733,0.9775643],"study_design_scores_gemma":[0.001051416,0.0003070602,0.00738551,0.0002038026,0.0002937847,0.00007712246,0.001096774,0.5994358,0.0002863772,0.04880568,0.3408733,0.0001834016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8842792,0.01027053,0.05553475,0.01973956,0.01683417,0.007507346,0.00007108438,0.00007293783,0.005690439],"genre_scores_gemma":[0.9826702,0.00001714282,0.0150439,0.0001753322,0.001669475,0.000246458,0.00002507529,0.00001907983,0.0001332728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9773809,"threshold_uncertainty_score":0.9997298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4634754320822916,"score_gpt":0.5450116204168327,"score_spread":0.08153618833454113,"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."}}