{"id":"W3036747120","doi":"10.1111/medu.14281","title":"Useful to whom? Evaluation utilisation theory and boundaries for programme evaluation scope","year":2020,"lang":"en","type":"review","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research; University of Toronto","funders":"","keywords":"Scope (computer science); Stakeholder; Theory of change; Context (archaeology); Scholarship; Process (computing); Engineering ethics; Management science; Monitoring and evaluation; Diversity (politics); Program evaluation; Participatory evaluation; Psychology; Sociology; Public relations; Political science; Computer science; Social science; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0575327,0.0003867272,0.001042372,0.000569148,0.0006175566,0.001711733,0.0006445749,0.0004115168,0.004293663],"category_scores_gemma":[0.1037939,0.0002806334,0.0002357182,0.001282678,0.0002754056,0.0005313687,0.0001266013,0.000326013,0.0004563992],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006889648,"about_ca_system_score_gemma":0.04285158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001626327,"about_ca_topic_score_gemma":0.0001104514,"domain_scores_codex":[0.9860811,0.003362923,0.001734823,0.001096981,0.007357761,0.0003664176],"domain_scores_gemma":[0.9927074,0.002625953,0.0008580224,0.0006390993,0.002693844,0.0004756745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002498397,0.000099221,0.00002086607,0.0006259426,0.00003163519,5.627416e-8,0.001389325,0.000001846087,6.325124e-8,0.003861057,0.02513968,0.9688053],"study_design_scores_gemma":[0.0004061525,0.0001784512,0.000159264,0.0018905,0.0007655338,0.000007458452,0.000767117,0.007128935,6.277769e-7,0.01684736,0.9715614,0.0002871852],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001411191,0.9689733,0.008139509,0.008810191,0.003313859,0.009424381,0.00002604367,0.00005583918,0.00111571],"genre_scores_gemma":[0.001086182,0.9726617,0.002739867,0.004640721,0.002027914,0.01353408,0.002178969,0.00008372192,0.001046857],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9685181,"threshold_uncertainty_score":0.9999646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.392409528471173,"score_gpt":0.6146912310302682,"score_spread":0.2222817025590952,"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."}}