{"id":"W4401363982","doi":"10.3138/cjpe-2023-0025","title":"E-Eval: Learnings from a Community-Based Evaluation Capacity Building Initiative","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Capacity building; Geography; Forestry; Political science","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":[0.05627129,0.0001965804,0.0003152913,0.001342487,0.0005847486,0.001405557,0.0006446693,0.0001386883,0.004928251],"category_scores_gemma":[0.008720417,0.0001608037,0.0002263044,0.001472116,0.0001682343,0.001318325,0.00001826127,0.0009795686,0.0001793152],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001342239,"about_ca_system_score_gemma":0.01195828,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003125861,"about_ca_topic_score_gemma":0.0196664,"domain_scores_codex":[0.9889382,0.004841674,0.001179279,0.0002782177,0.004432439,0.0003301952],"domain_scores_gemma":[0.9910043,0.001797515,0.0007019207,0.0004130599,0.005601824,0.0004813388],"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":[0.00002124307,0.00005416423,0.007000408,0.00001397194,0.00008634123,0.00000698333,0.007055054,0.01891145,0.0002930355,0.000467183,0.003440223,0.9626499],"study_design_scores_gemma":[0.001172757,0.0006237567,0.04475627,0.0003538695,0.0003835688,0.00001713254,0.003409346,0.8254181,0.0005444987,0.05290965,0.07016111,0.0002500121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784968,0.0008422321,0.01096641,0.003471186,0.001918764,0.001360869,0.00004211113,0.00004100137,0.002860566],"genre_scores_gemma":[0.9914756,0.000004165105,0.007441659,0.0005237056,0.0003002019,0.0001184968,0.00008671355,0.00002075575,0.00002870822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9623999,"threshold_uncertainty_score":0.9996311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6622962955102082,"score_gpt":0.5664147753741403,"score_spread":0.09588152013606788,"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."}}