{"id":"W1978303279","doi":"10.1002/ev.382","title":"Integrating a new evaluation unit with an old institution: See no evil; hear no evil; speak no evil","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Unit (ring theory); CLARITY; Institution; Evaluation methods; Association (psychology); Psychology; Sociology; Computer science; Mathematics education; Social science; Engineering; Psychotherapist","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01736029,0.0004849081,0.0005230155,0.0008294718,0.001149549,0.0005766048,0.0006473174,0.0002470767,0.02210397],"category_scores_gemma":[0.008323997,0.0003815557,0.0002383757,0.002161334,0.0001301108,0.003536137,0.00007265158,0.0003837197,0.004990346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007844121,"about_ca_system_score_gemma":0.004785973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001702086,"about_ca_topic_score_gemma":0.00627782,"domain_scores_codex":[0.9904591,0.001241245,0.001472267,0.001188561,0.005096246,0.0005425385],"domain_scores_gemma":[0.9869133,0.0006028721,0.0008953673,0.00129666,0.009825579,0.000466192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001556903,0.000812517,0.01233173,0.0000509591,0.0002271055,0.000001092588,0.007395059,0.01233461,0.001220521,0.00660834,0.05166478,0.9057964],"study_design_scores_gemma":[0.006232469,0.002845415,0.03890539,0.000318862,0.00068989,0.00002763184,0.001579132,0.7306747,0.0007128062,0.009590889,0.207605,0.0008177863],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3594787,0.0008401606,0.1223121,0.002521836,0.01261698,0.01383066,0.00009228828,0.0009065377,0.4874008],"genre_scores_gemma":[0.8374768,0.0001774813,0.09508414,0.001319829,0.004451561,0.001798999,0.0008273068,0.0001443221,0.05871948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9049786,"threshold_uncertainty_score":0.9998636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3909805053050648,"score_gpt":0.5034779046174458,"score_spread":0.112497399312381,"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."}}