{"id":"W2548378115","doi":"10.1177/0739456x16675930","title":"Evaluation Theory and Practice: Comparing Program Evaluation and Evaluation in Planning","year":2016,"lang":"en","type":"article","venue":"Journal of Planning Education and Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Program evaluation; Evaluation methods; Outcome (game theory); Management science; Impact evaluation; Theory of change; Process management; Political science; Computer science; Business; Engineering; Public administration; Economics; Management; Medicine","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2270684,0.0001001195,0.0002066872,0.001244786,0.0002647672,0.0004352937,0.0001609255,0.0000825408,0.0002052202],"category_scores_gemma":[0.03962864,0.00006119938,0.00002160638,0.0005898369,0.0001543567,0.001419228,0.00006866404,0.0003286509,0.000006344019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003129304,"about_ca_system_score_gemma":0.002221317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000939084,"about_ca_topic_score_gemma":0.000008265448,"domain_scores_codex":[0.9835698,0.0083188,0.000885952,0.0003343568,0.006641762,0.0002493528],"domain_scores_gemma":[0.9860083,0.006449745,0.0005583122,0.0001768829,0.006651406,0.0001553418],"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":[0.0002255056,0.0001629819,0.09130771,0.000008905349,0.00001858783,7.379317e-7,0.008856738,0.0004814627,0.0005880463,0.0005374738,0.0009843089,0.8968275],"study_design_scores_gemma":[0.002702998,0.0004727411,0.8192401,0.000729217,0.0001092634,0.0001792341,0.03278574,0.09441547,0.00008058509,0.04055252,0.008591017,0.000141108],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829497,0.005780747,0.0003217213,0.004335065,0.0003807462,0.001030886,4.817376e-7,0.000005034085,0.005195671],"genre_scores_gemma":[0.9980395,0.0002144447,0.001236262,0.00006585731,0.000184137,0.0001086261,0.000002765039,0.000006683579,0.0001416953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8966864,"threshold_uncertainty_score":0.968461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6508698838348513,"score_gpt":0.7143752125896877,"score_spread":0.06350532875483639,"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."}}