{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.001047309,0.00004753144,0.0001210905,0.00002190999,0.003552817,0.00006347301,0.0001563904,0.00001327873,0.000003997498],"category_scores_gemma":[0.0003263412,0.00002363421,0.00002204947,0.000007549938,0.004264049,0.0001358976,0.000225391,0.00004417913,3.575742e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004303163,"about_ca_system_score_gemma":0.000006542457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004598704,"about_ca_topic_score_gemma":0.00005019854,"domain_scores_codex":[0.9996104,0.00008026623,0.00007792096,0.0000861993,0.00009141849,0.00005374631],"domain_scores_gemma":[0.9972034,0.002474476,0.0001182249,0.0001535105,0.0000307029,0.00001967634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006191507,0.000006744438,0.0002046068,0.00003022315,0.00001066857,8.332645e-7,0.03073418,6.436616e-8,0.0001351231,0.9603176,0.00003571866,0.007905099],"study_design_scores_gemma":[0.0006604573,0.00009382457,0.00466931,0.000100832,0.00002951368,0.000002474221,0.001188573,0.00003004453,0.0001279131,0.9928744,0.0001881293,0.00003446985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869218,0.002114948,0.00003915634,0.0001391737,0.0001717132,0.0001064666,0.000002418318,0.000002576951,0.01050174],"genre_scores_gemma":[0.9991475,0.000349386,0.000005461885,0.00002011651,0.00002597862,8.859637e-7,3.761025e-8,0.0000013807,0.0004492823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03255687,"threshold_uncertainty_score":0.9984457,"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."}}