{"id":"W2116343005","doi":"10.1177/1356389012453289","title":"Towards an evidence base of theory-driven evaluations: Some questions for proponents of theory-driven evaluation","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Management science; Causality (physics); Psychological intervention; Promotion (chess); Development theory; Theory of change; Computer science; Psychology; Engineering ethics; Sociology; Political science; Economics; Economic growth; 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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.104484,0.0002903029,0.0005167416,0.0007531174,0.0003389194,0.0001064515,0.0007910653,0.0001824574,0.005238072],"category_scores_gemma":[0.03549252,0.0002319777,0.0002557637,0.001011653,0.000242577,0.004316744,0.0001069081,0.0001541277,0.0001498588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004366177,"about_ca_system_score_gemma":0.002158929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002832712,"about_ca_topic_score_gemma":0.00004052329,"domain_scores_codex":[0.9801928,0.007960978,0.00206492,0.0006964041,0.00860393,0.0004809391],"domain_scores_gemma":[0.9846474,0.003484014,0.001631229,0.001308321,0.008709921,0.0002191356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007164042,0.001469289,0.02501976,0.0001058918,0.0001709688,6.858654e-8,0.01180279,0.06610368,0.02799929,0.2062729,0.0009374373,0.6594015],"study_design_scores_gemma":[0.001815735,0.0006134178,0.1293074,0.0002126575,0.0007162943,0.000001950991,0.001705944,0.5733773,0.009243588,0.2825362,0.0001966823,0.0002728408],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8696662,0.002029552,0.1168348,0.001105888,0.001635011,0.007055422,0.0001444637,0.00006180904,0.001466905],"genre_scores_gemma":[0.9866602,0.00006766927,0.01094041,0.0001364359,0.0003444816,0.001362784,0.0002268663,0.0000291007,0.0002320082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6591286,"threshold_uncertainty_score":0.9956713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3773650039081808,"score_gpt":0.5722308654359345,"score_spread":0.1948658615277536,"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."}}