{"id":"W3127292647","doi":"10.1101/2021.02.03.21250974","title":"Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of British Columbia; University of Victoria","funders":"Wellcome Trust","keywords":"Probabilistic logic; Staffing; Geospatial analysis; Actuarial science; Coronavirus disease 2019 (COVID-19); Probabilistic forecasting; Baseline (sea); Forecast skill; Statistical model; Operations research; Computer science; Econometrics; Business; Geography; Meteorology; Economics; Political science; Medicine; Engineering; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0251055,0.0002214526,0.000838012,0.00007365818,0.00004350008,0.00001695714,0.0004099736,0.0002284076,0.00005108595],"category_scores_gemma":[0.09858077,0.0001454042,0.0001343585,0.0002013668,0.000275814,0.00002258615,0.0009282983,0.0003770424,3.380989e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578527,"about_ca_system_score_gemma":0.0004976983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006041907,"about_ca_topic_score_gemma":0.002803958,"domain_scores_codex":[0.994222,0.002956856,0.0009242028,0.0004811824,0.001218395,0.000197401],"domain_scores_gemma":[0.991144,0.007082109,0.000664735,0.0006868506,0.0003677746,0.00005455221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000270571,0.0005860661,0.9631037,0.006551972,0.0004597375,0.0000148028,0.01567775,0.00450933,0.0001027976,0.006215803,0.0003197436,0.002431223],"study_design_scores_gemma":[0.0003184876,0.00004080557,0.5480985,0.0001438592,0.0004800068,0.000002104103,0.0004523227,0.002522382,0.00006476773,0.4477367,0.00002135003,0.0001186899],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957176,0.0009280986,0.0009243274,0.0006587565,0.00008318959,0.001372104,0.00005630289,0.0000155757,0.0002440065],"genre_scores_gemma":[0.9983219,0.00008775058,0.001059495,0.0002076612,0.00002761223,0.0002628452,0.00002023394,0.000009821247,0.000002714838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.441521,"threshold_uncertainty_score":0.9090123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5152404789777729,"score_gpt":0.4828004323958677,"score_spread":0.03244004658190519,"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."}}