{"id":"W2606709931","doi":"10.3138/cjpe.349","title":"Developing the Program Evaluation Utility Standards: Scholarly Foundations and Collaborative Processes","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Task (project management); Task force; Political science; Engineering ethics; Program evaluation; Management science; Computer science; Process management; Knowledge management; Business; Public administration; Engineering; Management; Economics","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","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05108675,0.0001738332,0.0002649247,0.0003963108,0.002843643,0.008061376,0.0009255117,0.00009829291,0.0008040296],"category_scores_gemma":[0.05139507,0.0001130112,0.00006821852,0.0008337854,0.0004747382,0.004497059,0.00004335198,0.0003216254,0.00001596209],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008128458,"about_ca_system_score_gemma":0.04390121,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003516276,"about_ca_topic_score_gemma":0.06403078,"domain_scores_codex":[0.9923038,0.001137042,0.001020086,0.0003200251,0.004904703,0.0003142668],"domain_scores_gemma":[0.9630292,0.0004331091,0.001691227,0.0006147526,0.03388711,0.0003445921],"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":[0.00001989256,0.0000289636,0.03116664,0.00001003027,0.00004078844,0.000001031025,0.002099337,0.0001173813,0.000003140633,0.0008056854,0.0009581433,0.964749],"study_design_scores_gemma":[0.001903198,0.0006878989,0.5436724,0.0001811678,0.0003069609,0.0000365892,0.007164702,0.06043267,0.00009799578,0.05207889,0.3331574,0.0002800353],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9153224,0.004086024,0.006791781,0.0428618,0.002284696,0.01455384,0.0001143497,0.00004252547,0.01394254],"genre_scores_gemma":[0.9899726,0.00006481805,0.008893352,0.0001399143,0.0001811418,0.0006607158,0.00001865287,0.00001031099,0.00005850156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.964469,"threshold_uncertainty_score":0.9984545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5392904759997819,"score_gpt":0.6027993397034421,"score_spread":0.06350886370366027,"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."}}