{"id":"W3109011900","doi":"10.1177/1356389020969721","title":"How to normalize reflexive evaluation? Navigating between legitimacy and integrity","year":2020,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athena Sustainable Materials Institute","funders":"","keywords":"Reflexivity; Normalization (sociology); Legitimacy; Epistemology; Process management; Political science; Sociology; Computer science; Knowledge management; Business; Social science; Politics","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02138962,0.0001893298,0.0003003823,0.0001226058,0.0003133693,0.0008232196,0.0003897599,0.00008834487,0.001828954],"category_scores_gemma":[0.01535159,0.000154412,0.0000683358,0.001059041,0.0000556606,0.001333311,0.0001709034,0.0003546777,0.0004867101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870501,"about_ca_system_score_gemma":0.0005249704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002365569,"about_ca_topic_score_gemma":0.00003437324,"domain_scores_codex":[0.9912395,0.001345419,0.0007007883,0.0007060523,0.005751748,0.0002564658],"domain_scores_gemma":[0.9953752,0.0008398407,0.0003654601,0.0003980434,0.002697147,0.0003242723],"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":[0.00003586663,0.00001736448,0.0557517,0.000008186939,0.00002423217,3.705863e-7,0.007895164,0.00165991,0.0008266566,0.0006424487,0.004811895,0.9283262],"study_design_scores_gemma":[0.00196778,0.0004507978,0.2979124,0.00006506221,0.0001886019,0.000002531093,0.00581123,0.6530857,0.001911576,0.01989806,0.01827625,0.0004299731],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8759401,0.0001231576,0.01538944,0.09956587,0.0002719458,0.001756077,0.00002425095,0.00006296101,0.006866134],"genre_scores_gemma":[0.9910709,0.00000512286,0.005475741,0.00252878,0.000520779,0.0001672044,0.00007833718,0.00001275232,0.0001403547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9278963,"threshold_uncertainty_score":0.9990835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4709169939777773,"score_gpt":0.5835940233142233,"score_spread":0.112677029336446,"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."}}