{"id":"W4410799851","doi":"10.56645/jmde.v21i50.1173","title":"Ray Rist: An Evaluator at the Government Accountability Office (GAO)","year":2025,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Government (linguistics); Political science; Linguistics; Philosophy; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.06662107,0.0002136739,0.0003777148,0.0001927315,0.0007771644,0.0002695251,0.001090944,0.0001086592,0.00446426],"category_scores_gemma":[0.004558153,0.0001196668,0.00027426,0.0007931192,0.0001589779,0.001332089,0.0003618407,0.0003465454,0.00021617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001685854,"about_ca_system_score_gemma":0.001360232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009952273,"about_ca_topic_score_gemma":0.0003206205,"domain_scores_codex":[0.9852862,0.002657589,0.001963623,0.0004378628,0.009398041,0.0002566641],"domain_scores_gemma":[0.9919024,0.002160104,0.001616896,0.001051389,0.003134367,0.0001348178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004106932,0.001992282,0.2631027,0.00003827945,0.0002664955,0.000007588613,0.01024732,0.1808396,0.01105302,0.0004406705,0.04728979,0.4806154],"study_design_scores_gemma":[0.001842622,0.0003092866,0.7232678,0.00004317644,0.0001977452,0.00001251413,0.00509185,0.2562713,0.0006819403,0.004434513,0.007716853,0.0001304188],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805992,0.0004298054,0.003010206,0.008600093,0.001959686,0.0007954471,0.00001765293,0.0000102705,0.004577613],"genre_scores_gemma":[0.9959018,0.00004377319,0.0009545726,0.0002985007,0.0002552443,0.00003699676,0.000008522961,0.000009408245,0.002491231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.480485,"threshold_uncertainty_score":0.9964458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.164309754456958,"score_gpt":0.5301316705100111,"score_spread":0.3658219160530531,"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."}}