{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.377004,0.000792331,0.00105227,0.01244685,0.01234505,0.02678278,0.005688598,0.005127583,0.003135546],"category_scores_gemma":[0.4013061,0.001271714,0.0009233354,0.008752666,0.02468266,0.01348373,0.01822633,0.01488783,0.0008335651],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04228677,"about_ca_system_score_gemma":0.2122281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04564105,"about_ca_topic_score_gemma":0.05240739,"domain_scores_codex":[0.713895,0.172183,0.01831551,0.006876738,0.08422773,0.004501959],"domain_scores_gemma":[0.4682741,0.2569066,0.01628802,0.06379537,0.179148,0.01558788],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002244009,0.0003535495,0.003272113,0.0003630745,0.00003005546,0.0001049448,0.01546347,0.002814199,0.0004281563,0.6738499,0.03266053,0.2706375],"study_design_scores_gemma":[0.00007441109,0.0001873951,0.005495449,0.004798777,0.0000547358,0.0001719874,0.02241772,0.0114009,0.003124798,0.568583,0.3834502,0.0002407055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02242644,0.006258585,0.5160107,0.3237422,0.002941093,0.003262232,0.0001977897,0.0006687089,0.1244923],"genre_scores_gemma":[0.3743337,0.004941309,0.5959925,0.005751702,0.00100763,0.001674258,0.0003183038,0.0004061657,0.01557445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9577132,"threshold_uncertainty_score":0.768265,"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."}}