{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4346581,0.0006394461,0.001713843,0.01272003,0.005185829,0.01443608,0.003407177,0.005363639,0.002051639],"category_scores_gemma":[0.583756,0.001037556,0.001708227,0.01284168,0.02698115,0.0124098,0.01196522,0.008647631,0.0005673298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02089394,"about_ca_system_score_gemma":0.141306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0128774,"about_ca_topic_score_gemma":0.01224258,"domain_scores_codex":[0.4085834,0.3868751,0.07522758,0.0109711,0.1139505,0.004392351],"domain_scores_gemma":[0.1877012,0.5196266,0.07969655,0.03798237,0.1644551,0.01053813],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001711996,0.0003903165,0.04269581,0.02159264,0.0003028905,0.0001759078,0.02021442,0.001525729,0.0007819448,0.3325015,0.05727337,0.5223743],"study_design_scores_gemma":[0.0002003601,0.0008126503,0.07158183,0.1208389,0.0004867852,0.001088359,0.01902476,0.002604226,0.002474982,0.2234705,0.5570782,0.0003385371],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.05458299,0.2053642,0.2203055,0.377593,0.009996478,0.005427288,0.001078209,0.0007076192,0.1249447],"genre_scores_gemma":[0.6718757,0.07122224,0.197795,0.04025433,0.003751412,0.009920941,0.001006011,0.000351124,0.003823212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5653419,"threshold_uncertainty_score":0.6971673,"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."}}