{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.353658,0.000822185,0.00256768,0.005222904,0.008942256,0.02903541,0.004399808,0.01067907,0.003920452],"category_scores_gemma":[0.4488707,0.001151497,0.001260362,0.0033596,0.07728098,0.04439994,0.01873572,0.02637104,0.0007883733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01847551,"about_ca_system_score_gemma":0.065648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007013655,"about_ca_topic_score_gemma":0.007928526,"domain_scores_codex":[0.6066589,0.3052572,0.02256578,0.006812635,0.05378854,0.004916838],"domain_scores_gemma":[0.2291865,0.6286788,0.01387563,0.05303248,0.06294917,0.01227745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001230188,0.0002863307,0.002890466,0.001875647,0.00007767027,0.0002956429,0.02781392,0.0005019939,0.0003370977,0.7152585,0.08077608,0.1697636],"study_design_scores_gemma":[0.0001437118,0.0001769016,0.001776298,0.006042819,0.00006623693,0.0003442288,0.03014342,0.0008729195,0.0005523886,0.7162625,0.2435249,0.00009366114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.003914469,0.01624174,0.0166572,0.9329439,0.005094341,0.0002547494,0.0000519847,0.0001205609,0.02472104],"genre_scores_gemma":[0.6092291,0.01696663,0.05618177,0.3018836,0.007619272,0.001798696,0.0001198341,0.0002738036,0.005927234],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.353658,"threshold_uncertainty_score":0.7970548,"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."}}