{"id":"W4367030244","doi":"10.3138/cjpe.0015.012","title":"Reflections on Program Evaluation, 35 Years on","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Psychology; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[],"category_scores_codex":[0.02127247,0.0001894917,0.000272568,0.001503404,0.0004012424,0.0006674807,0.000557304,0.0001316164,0.006446948],"category_scores_gemma":[0.004653381,0.0001545653,0.0002051773,0.001872531,0.0001068573,0.0005861836,0.00000935938,0.0004026068,0.000634736],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095,"about_ca_system_score_gemma":0.00621278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002450892,"about_ca_topic_score_gemma":0.01590385,"domain_scores_codex":[0.991796,0.001105365,0.001137085,0.0003578149,0.005181741,0.000422061],"domain_scores_gemma":[0.9930512,0.0003149335,0.0008130829,0.000534385,0.00464212,0.0006442788],"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":[0.00004446663,0.0001891805,0.003337582,0.000001024103,0.00003047574,0.000008942214,0.0007013088,0.0111094,0.00001598299,0.0008089805,0.009322418,0.9744303],"study_design_scores_gemma":[0.00231496,0.004467501,0.2149608,0.000121473,0.0001984517,0.0001073337,0.001488177,0.07536236,0.00005833198,0.01847489,0.6821283,0.000317492],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8817617,0.0003477429,0.0004382475,0.007690133,0.003818102,0.006744652,0.00001237891,0.00006935975,0.09911762],"genre_scores_gemma":[0.9950123,0.00002361881,0.002540412,0.0007125222,0.0005096702,0.00054245,0.00002774747,0.0000198841,0.0006114027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9741127,"threshold_uncertainty_score":0.9994211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6401574684201251,"score_gpt":0.6365197505771939,"score_spread":0.00363771784293121,"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."}}