{"id":"W1505207325","doi":"10.1002/ev.20084","title":"Credible Judgment: Combining Truth, Beauty, and Justice","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Beauty; Argumentation theory; Economic Justice; Process (computing); Variety (cybernetics); Psychology; Social psychology; Public relations; Computer science; Law; Epistemology; Political science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01094448,0.0001180313,0.0001786342,0.0003215816,0.0006095197,0.0003062333,0.0001708434,0.0000681336,0.001058154],"category_scores_gemma":[0.00657607,0.0001013275,0.00006794571,0.000564161,0.0000374132,0.0005508513,0.0000387243,0.00008280047,0.0001587956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001323175,"about_ca_system_score_gemma":0.0002699592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004399345,"about_ca_topic_score_gemma":0.0001139706,"domain_scores_codex":[0.9970622,0.0002961498,0.0004940866,0.0004051151,0.001534101,0.0002083661],"domain_scores_gemma":[0.9965985,0.001933775,0.0002322284,0.0003443847,0.0007485913,0.0001424851],"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":[0.00004769461,0.00007613646,0.002128429,0.0000138024,0.00002460813,2.421048e-8,0.001036736,0.005211268,0.0004672191,0.04055332,0.02721679,0.923224],"study_design_scores_gemma":[0.002476879,0.0002445968,0.01857428,0.00001865377,0.0002529254,0.000004026927,0.0006525713,0.6494474,0.0006561152,0.08997813,0.2375283,0.0001661949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4710881,0.0007191148,0.3404806,0.01009882,0.01175056,0.002778663,0.00002755868,0.000332174,0.1627245],"genre_scores_gemma":[0.988413,0.00004368636,0.00638005,0.0003714717,0.0005321868,0.0001790639,0.00003972977,0.00001387057,0.00402695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9230578,"threshold_uncertainty_score":0.999855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.260603245733291,"score_gpt":0.5132600924299058,"score_spread":0.2526568466966148,"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."}}