{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1189736,0.0007265395,0.00130439,0.008952597,0.007388193,0.02302246,0.002538121,0.004100107,0.004495417],"category_scores_gemma":[0.2210006,0.0007243973,0.0008584923,0.004382047,0.0783371,0.02508212,0.01331009,0.005729364,0.0003369363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01092107,"about_ca_system_score_gemma":0.01215063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004262019,"about_ca_topic_score_gemma":0.003921961,"domain_scores_codex":[0.7759113,0.1790424,0.00599333,0.005239694,0.02934019,0.00447292],"domain_scores_gemma":[0.6437319,0.2928107,0.0207436,0.01406476,0.02432401,0.004325105],"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":[0.00009596281,0.00009165511,0.004904528,0.0004253691,0.000061307,0.0002552707,0.04351084,0.001406487,0.0002490439,0.9062387,0.002382814,0.0403781],"study_design_scores_gemma":[0.00003025347,0.00009619659,0.003013087,0.001081767,0.00005169944,0.0002008428,0.02414166,0.003951899,0.0007675989,0.9486142,0.0179804,0.00007034934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.193831,0.006128235,0.2472817,0.05574869,0.000607064,0.0008945283,0.0001147745,0.0002170994,0.495177],"genre_scores_gemma":[0.9811183,0.0004208016,0.0165526,0.0007280466,0.00008407191,0.0000983205,0.00001624026,0.00002801632,0.0009535404],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8810264,"threshold_uncertainty_score":0.6291998,"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."}}