{"id":"W4366449629","doi":"10.3138/cjpe.0021.006","title":"Studies Are Not Enough: The Necessary Transformation of Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"GRASP; Public sector; Business; Knowledge management; Profit (economics); Public relations; Not for profit; Political science; Economics; Computer 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07960297,0.0001369451,0.0003114922,0.0007803059,0.0003314114,0.0001714244,0.0004454855,0.00008525326,0.0007678888],"category_scores_gemma":[0.006037403,0.00008464888,0.0001728983,0.001162417,0.0001931782,0.001029379,0.000009335649,0.000227835,0.00002801048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005279353,"about_ca_system_score_gemma":0.003415695,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001845018,"about_ca_topic_score_gemma":0.02437774,"domain_scores_codex":[0.9918206,0.0009551927,0.001796158,0.000170025,0.004964783,0.0002932744],"domain_scores_gemma":[0.9865968,0.0008069305,0.001796986,0.0003287498,0.01024012,0.0002304428],"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":[0.00004888551,0.0000439499,0.006318354,0.00001262062,0.00007524605,0.000001893069,0.009665096,0.005878947,0.0001267158,0.0007180395,0.001822944,0.9752873],"study_design_scores_gemma":[0.004272938,0.001498361,0.6412517,0.0003516647,0.0009702812,0.0001272313,0.09883677,0.1498227,0.006340445,0.03036771,0.06570961,0.0004506217],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9739197,0.003103955,0.003092745,0.0111721,0.001776417,0.002412696,0.00001104049,0.000008873436,0.004502467],"genre_scores_gemma":[0.9985262,0.00004516835,0.0008227323,0.0002820731,0.0002094443,0.00004655704,0.00001027814,0.000007774967,0.00004972646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9748367,"threshold_uncertainty_score":0.9934248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.55640313541793,"score_gpt":0.5856812041578379,"score_spread":0.0292780687399079,"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."}}