{"id":"W4377141999","doi":"10.56645/jmde.v19i43.825","title":"The Program Evaluation Standards in Evaluation Scholarship and Practice","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Medical education; Systematic review; Resource (disambiguation); Professional association; Political science; Psychology; Medicine; Sociology; Public relations; MEDLINE; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3790371,0.0001892196,0.0003038074,0.0009145065,0.0006558075,0.0006930978,0.0005136005,0.0001246966,0.0003026288],"category_scores_gemma":[0.09272421,0.0001184993,0.0001200524,0.002301801,0.0001309019,0.003038795,0.0001673053,0.0004701435,0.00007268391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001071092,"about_ca_system_score_gemma":0.003431386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004357917,"about_ca_topic_score_gemma":0.0001828681,"domain_scores_codex":[0.955358,0.0125864,0.002989699,0.0006084908,0.02794649,0.0005108871],"domain_scores_gemma":[0.975273,0.006448465,0.001822502,0.0004998627,0.01582194,0.0001342089],"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":[0.0004974358,0.0001567432,0.0136492,0.000005358968,0.00003124994,0.000003138141,0.003079645,0.03653042,0.0003511346,0.0001264793,0.001263711,0.9443055],"study_design_scores_gemma":[0.00246046,0.0004113656,0.4005967,0.0000632298,0.0001604921,0.00004148816,0.007113128,0.5621546,0.00004350179,0.02296677,0.003887026,0.000101243],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734507,0.001763823,0.0002184273,0.01709392,0.001352734,0.003475526,0.000006582515,0.00002611597,0.002612134],"genre_scores_gemma":[0.9969889,0.000597044,0.001614096,0.00004814541,0.0002328345,0.0003938515,0.00002138741,0.00001541432,0.00008831292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9442043,"threshold_uncertainty_score":0.9149182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4232894218728951,"score_gpt":0.6372998949468092,"score_spread":0.214010473073914,"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."}}