{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1304267,0.001959973,0.001761206,0.006274518,0.01072642,0.02360228,0.004102837,0.01052031,0.00811545],"category_scores_gemma":[0.1197926,0.001354031,0.001256087,0.002953863,0.04080501,0.02565445,0.009636141,0.01715313,0.002079432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01721957,"about_ca_system_score_gemma":0.07477427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01376494,"about_ca_topic_score_gemma":0.02076608,"domain_scores_codex":[0.9256029,0.04530158,0.00549295,0.003119341,0.01682279,0.003660304],"domain_scores_gemma":[0.854313,0.08604192,0.00497827,0.01015109,0.03294672,0.01156914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001174332,0.00031485,0.001856137,0.0005496984,0.00007166121,0.00009458126,0.00196257,0.001449562,0.0002602891,0.8365687,0.02663263,0.130122],"study_design_scores_gemma":[0.00004909522,0.00007284992,0.0008525964,0.001057731,0.0000365321,0.00003426571,0.002497841,0.001594979,0.0006565423,0.9523759,0.04070544,0.00006618325],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.01361174,0.01360016,0.3152541,0.4832704,0.003947149,0.001828314,0.0002600689,0.001153546,0.1670746],"genre_scores_gemma":[0.3236467,0.005956029,0.5967139,0.0437917,0.000762845,0.001938943,0.0002342473,0.0003000699,0.02665559],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1304267,"threshold_uncertainty_score":0.6897703,"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."}}