{"id":"W2772681577","doi":"10.1007/s11238-017-9643-7","title":"The wisdom of collective grading and the effects of epistemic and semantic diversity","year":2017,"lang":"en","type":"article","venue":"Theory and Decision","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"York University; Arts and Humanities Research Council; London School of Economics and Political Science","keywords":"Epistemology; Grading (engineering); Diversity (politics); Philosophy; Sociology; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05480854,0.0007507395,0.002534717,0.003467965,0.004719168,0.01102242,0.002956129,0.006662188,0.01429263],"category_scores_gemma":[0.215793,0.0007551713,0.001287884,0.002961446,0.02161236,0.02001643,0.006253381,0.007247224,0.0009987972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004230143,"about_ca_system_score_gemma":0.004115945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003525483,"about_ca_topic_score_gemma":0.005725326,"domain_scores_codex":[0.9611943,0.02169142,0.002050428,0.004584415,0.008809695,0.001669685],"domain_scores_gemma":[0.5275721,0.3952259,0.01712358,0.03526055,0.01788344,0.006934393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005929416,0.0002860349,0.008391159,0.0004058415,0.0003035719,0.0001063029,0.003420763,0.007814836,0.0004988704,0.9226294,0.004604125,0.05094602],"study_design_scores_gemma":[0.00009502199,0.00003265054,0.002199389,0.00004953002,0.00005707997,0.00002319204,0.0004917978,0.003477274,0.0002048394,0.9914933,0.001850205,0.0000256618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4729828,0.007232727,0.127612,0.08529684,0.00102266,0.0001571725,0.0005452061,0.0002494548,0.3049012],"genre_scores_gemma":[0.9875201,0.0004805335,0.007740448,0.001039499,0.0004389854,0.00004337761,0.00005457193,0.00007155157,0.002610938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05480854,"threshold_uncertainty_score":0.2898588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01907395297334286,"score_gpt":0.224318621955457,"score_spread":0.2052446689821141,"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."}}