{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.182158,0.000946833,0.001792445,0.00506827,0.007684204,0.02924757,0.003552499,0.004426709,0.004201847],"category_scores_gemma":[0.3001159,0.0009048432,0.001138299,0.004463451,0.07757322,0.03781579,0.01524757,0.0100909,0.0009331239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01705588,"about_ca_system_score_gemma":0.03043813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004200486,"about_ca_topic_score_gemma":0.003131203,"domain_scores_codex":[0.7900969,0.144816,0.01011767,0.01162099,0.03788599,0.00546236],"domain_scores_gemma":[0.7119609,0.1775312,0.02122129,0.04621607,0.03878036,0.004290233],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002858155,0.00004458386,0.001306279,0.0001602114,0.00002919492,0.00004434985,0.01385162,0.001003711,0.0003601695,0.930213,0.00125144,0.0517068],"study_design_scores_gemma":[0.00002763244,0.00003774617,0.0005641673,0.0005146074,0.00001854946,0.00005341625,0.005714875,0.00284109,0.001680171,0.9638953,0.02460365,0.00004880587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05000588,0.002781208,0.6376047,0.09111087,0.0008257013,0.0007708202,0.00006464371,0.0007264045,0.2161098],"genre_scores_gemma":[0.8640789,0.0007641182,0.123446,0.003564859,0.0002196991,0.0008569048,0.00003972751,0.000392744,0.006636995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8178419,"threshold_uncertainty_score":0.9633553,"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."}}