{"id":"W2011406769","doi":"10.1016/j.evalprogplan.2010.09.003","title":"Ten steps to making evaluation matter","year":2010,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":81,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Program evaluation; Computer science; Program Design Language; Management science; Theory of change; Work (physics); Evaluation methods; Sustainability; Risk analysis (engineering); Process management; Software engineering; Engineering; Political science; Sociology; Business","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02347861,0.0001635045,0.0001886465,0.0004023692,0.0003430694,0.0007978574,0.0002860999,0.0001007807,0.01146296],"category_scores_gemma":[0.002025584,0.0001269483,0.00004952808,0.0006641402,0.00004330777,0.0005342768,0.00009222368,0.0002593825,0.001265091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004589132,"about_ca_system_score_gemma":0.000242365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005870003,"about_ca_topic_score_gemma":0.00004577776,"domain_scores_codex":[0.9943448,0.0004950737,0.0006077205,0.0005349484,0.003733252,0.0002842521],"domain_scores_gemma":[0.9974783,0.0003805068,0.0002373278,0.0004448476,0.00130455,0.0001544366],"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":[0.00002182305,0.00003531803,0.1518332,0.000002863232,0.000008958987,3.572057e-7,0.001980236,0.001401486,0.0004974504,0.0001985193,0.005541462,0.8384783],"study_design_scores_gemma":[0.0007397526,0.000132935,0.5727152,0.00004097949,0.00005357278,0.00001179016,0.001089368,0.3467656,0.00009874941,0.004260594,0.07386751,0.0002238931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9389021,0.0001167196,0.001573088,0.004080735,0.001059392,0.002091978,0.000003948901,0.00008768168,0.05208437],"genre_scores_gemma":[0.9842925,0.000001037381,0.01271059,0.001654076,0.0002095429,0.0004933351,0.00003578522,0.00001292394,0.0005901749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8382545,"threshold_uncertainty_score":0.9995126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3049186399144428,"score_gpt":0.5971294410667453,"score_spread":0.2922108011523025,"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."}}