{"id":"W2945587103","doi":"10.3138/cjpe.42190","title":"Evaluation Literacy: Perspectives of Internal Evaluators in Non-Government Organizations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Context (archaeology); Conversation; Narrative; Literacy; Public relations; Psychology; Knowledge management; Sociology; Political science; Pedagogy; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03273753,0.0001561126,0.0003470908,0.0009645036,0.00007138366,0.0002020236,0.0005638409,0.00009066147,0.01383499],"category_scores_gemma":[0.006326363,0.0001297231,0.0001269458,0.001875706,0.00007851945,0.001103741,0.00002421308,0.0002389864,0.0001132538],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001686054,"about_ca_system_score_gemma":0.007404455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005865979,"about_ca_topic_score_gemma":0.006461604,"domain_scores_codex":[0.9906327,0.001088445,0.001513011,0.0002904479,0.006213699,0.0002617654],"domain_scores_gemma":[0.9866698,0.0002277279,0.001289473,0.0003903839,0.01114837,0.0002742887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004263855,0.0001976794,0.354305,0.000008992573,0.00007144702,0.000002043431,0.02465465,0.014929,0.0004200722,0.0004715461,0.0004549385,0.604442],"study_design_scores_gemma":[0.002378138,0.0008505872,0.6150318,0.0001550162,0.0001872203,0.00001861289,0.01551965,0.356939,0.0004990225,0.006571633,0.001661348,0.0001880129],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988338,0.0005250182,0.0009673468,0.0003672165,0.0007274098,0.00190316,0.00001009254,0.000003711532,0.007158021],"genre_scores_gemma":[0.997655,0.00001188824,0.001982821,0.00005511622,0.00008194984,0.00005663615,0.000008067348,0.00001428551,0.0001342282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.604254,"threshold_uncertainty_score":0.9982226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1121734083055392,"score_gpt":0.4916620196187995,"score_spread":0.3794886113132602,"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."}}