{"id":"W4366384635","doi":"10.3138/cjpe.0025.014","title":"Reflections Over 25 Years: Evaluation Then, Now, and Into the Future","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02156275,0.0001105244,0.00015385,0.0005075449,0.0003711462,0.0003626491,0.0003968157,0.00008925428,0.004380138],"category_scores_gemma":[0.001189212,0.00006999607,0.00009235975,0.0007801391,0.0001350384,0.0007283259,0.00001606083,0.0002524763,0.00007182585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000316314,"about_ca_system_score_gemma":0.003283673,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006279536,"about_ca_topic_score_gemma":0.08852159,"domain_scores_codex":[0.9957319,0.0008986875,0.0006725783,0.0001975154,0.002294756,0.0002044874],"domain_scores_gemma":[0.9958441,0.0001433958,0.0005617092,0.0003408574,0.002814631,0.0002953543],"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":[0.00001277856,0.00002482437,0.01690041,0.000001367934,0.00002740131,0.000001380155,0.0139273,0.0001025501,0.00002661452,0.0008010091,0.004039551,0.9641348],"study_design_scores_gemma":[0.0008460833,0.0004277351,0.7497673,0.00002510893,0.0002021381,0.000043633,0.00687845,0.02363798,0.00003484989,0.05182253,0.1661803,0.0001339053],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777834,0.002426506,0.0003901281,0.004444669,0.002329188,0.001643083,0.0000034437,0.00001189101,0.01096772],"genre_scores_gemma":[0.9960481,0.00006263136,0.002807558,0.0003581754,0.0004784175,0.00008940808,0.00000548257,0.000009188659,0.0001410713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9640009,"threshold_uncertainty_score":0.99653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.390329876993874,"score_gpt":0.5523569994362977,"score_spread":0.1620271224424237,"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."}}