{"id":"W4252185406","doi":"10.31219/osf.io/vk3bf","title":"Uncertainty quantification with experts: present status and research needs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Judgement; Expert elicitation; Quality (philosophy); Management science; Computer science; Knowledge management; Investment decisions; Data science; Business; Engineering; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003665396,0.0001886839,0.0003073316,0.0005604226,0.0003066466,0.001556586,0.0008219399,0.0002140239,0.0003858349],"category_scores_gemma":[0.001135982,0.0001197779,0.00006150971,0.001339658,0.0003960621,0.0001168789,0.001695491,0.0005582914,0.00001866233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008750113,"about_ca_system_score_gemma":0.0003985713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002758936,"about_ca_topic_score_gemma":0.0003925891,"domain_scores_codex":[0.9957609,0.0003515354,0.000553554,0.000972836,0.001965014,0.0003961833],"domain_scores_gemma":[0.9945005,0.001390804,0.0002018997,0.001911001,0.001796342,0.0001994177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002345393,0.0008605478,0.01934532,0.0001760792,0.000149148,0.0000236861,0.01703189,0.01109378,0.00270279,0.1975003,0.3895166,0.3613653],"study_design_scores_gemma":[0.0005009262,0.0003716778,0.009397489,0.000574057,0.00003815621,0.00003451539,0.06332164,0.1137128,0.007016689,0.2171849,0.5866107,0.001236423],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8426948,0.001045411,0.1112711,0.01047141,0.0001696917,0.001828404,0.00005598628,0.0003478642,0.0321154],"genre_scores_gemma":[0.9662856,0.0002909076,0.02646649,0.00005124195,0.00008687327,0.0004997383,0.00007938575,0.00002019587,0.006219543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3601289,"threshold_uncertainty_score":0.9994799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4136745382433872,"score_gpt":0.5054459191427827,"score_spread":0.09177138089939552,"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."}}