{"id":"W4224866913","doi":"10.3138/cjpe.72386","title":"Evaluation Utility Metrics (EUMs) in Reflective Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences","keywords":"Quality (philosophy); Negotiation; Computer science; Evaluation methods; Management science; Process management; Risk analysis (engineering); Psychology; Medicine; Business; Reliability engineering; Sociology; Engineering","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1587205,0.0001271916,0.0002625058,0.002237148,0.0004585136,0.0003251662,0.0006225464,0.00006012607,0.009386593],"category_scores_gemma":[0.04460276,0.0001153252,0.0001232477,0.004358707,0.0000629419,0.001344388,0.00003904606,0.0005886337,0.00004069535],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003458961,"about_ca_system_score_gemma":0.01821944,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477244,"about_ca_topic_score_gemma":0.02580027,"domain_scores_codex":[0.9804586,0.007188049,0.001472502,0.0003471607,0.01017669,0.0003570329],"domain_scores_gemma":[0.9869825,0.001086303,0.001342836,0.0003801053,0.009865666,0.0003426037],"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":[0.00005426151,0.0001406246,0.01552068,0.000001283867,0.00002832808,0.000009048811,0.002434058,0.02021365,0.000009387164,0.0002750196,0.002833664,0.95848],"study_design_scores_gemma":[0.002390211,0.001253546,0.1392663,0.00001466354,0.0002986005,0.0001264882,0.01524314,0.5985043,0.00003697706,0.03695818,0.2056863,0.0002213243],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8902088,0.004783796,0.002588208,0.01719393,0.005615852,0.007332687,0.00004312996,0.00002570776,0.0722079],"genre_scores_gemma":[0.9960427,0.000009763326,0.003007479,0.000423136,0.00009734366,0.0003248661,0.00001778664,0.000009402238,0.00006751258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9582587,"threshold_uncertainty_score":0.9919763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5800774051525978,"score_gpt":0.6115541890215195,"score_spread":0.03147678386892172,"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."}}