{"id":"W1986224130","doi":"10.1002/ev.133","title":"Background and history of the Joint Committee's Program Evaluation Standards","year":2004,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Joint (building); Context (archaeology); Political science; Library science; Engineering ethics; Computer science; Engineering; History; Archaeology; Civil engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01762353,0.0001271088,0.0002012131,0.000237916,0.0002751182,0.00009502291,0.0002082025,0.00007783092,0.001156578],"category_scores_gemma":[0.003021478,0.00008801436,0.0001446085,0.0005635328,0.0001428297,0.0004717207,0.00004642344,0.0001040393,0.00001289038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002188554,"about_ca_system_score_gemma":0.004614126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001835624,"about_ca_topic_score_gemma":0.001072916,"domain_scores_codex":[0.99417,0.0004632364,0.0006914855,0.0003459838,0.004174207,0.000155136],"domain_scores_gemma":[0.9952222,0.0002799276,0.0004795327,0.0005274784,0.003416728,0.00007418441],"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":[0.00004260381,0.0001734349,0.001050797,0.00001069643,0.00003149766,1.315229e-8,0.00177708,0.007806424,0.0006823186,0.003472627,0.03258309,0.9523694],"study_design_scores_gemma":[0.006239746,0.0005079239,0.1398679,0.00007369381,0.0004004885,0.000006804413,0.00137479,0.1302083,0.001559522,0.1020565,0.617464,0.0002404066],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8635142,0.00509544,0.03123543,0.01374022,0.009536527,0.01705874,0.00009849425,0.0001950927,0.05952581],"genre_scores_gemma":[0.9904878,0.0000488538,0.004656688,0.0001779834,0.0001726649,0.001021408,0.0000296342,0.00001538944,0.003389539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.952129,"threshold_uncertainty_score":0.9997565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3548191126107928,"score_gpt":0.5240969201650518,"score_spread":0.169277807554259,"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."}}