{"id":"W3158142982","doi":"10.1101/2021.04.25.21256069","title":"Reliability of COVID-19 data: An evaluation and reflection","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Temple University; George Washington University","keywords":"Coronavirus disease 2019 (COVID-19); Reliability (semiconductor); Statistics; 2019-20 coronavirus outbreak; Case fatality rate; Medicine; Outbreak; Demography; Geography; Environmental health; Computer science; Mathematics; Disease","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":[],"consensus_categories":[],"category_scores_codex":[0.003727271,0.0001779163,0.0004972345,0.0001010442,0.00004151305,0.00002845412,0.0002544395,0.0001915137,0.0002802004],"category_scores_gemma":[0.008021256,0.000170787,0.00005496575,0.0001688976,0.0001355981,0.0001781027,0.0008183856,0.0003467721,0.00000336861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002084886,"about_ca_system_score_gemma":0.001527984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004084732,"about_ca_topic_score_gemma":0.0003934632,"domain_scores_codex":[0.9970535,0.0006818929,0.0004391289,0.0010285,0.0006629999,0.0001339526],"domain_scores_gemma":[0.9956182,0.000114272,0.0002712611,0.003136103,0.0005445846,0.0003155986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004733211,0.0006020759,0.9755642,0.004333647,0.0001553861,0.00004575604,0.0005868457,0.0004522472,0.006829758,0.00001437388,0.001849404,0.00909292],"study_design_scores_gemma":[0.001186424,0.0001395325,0.9739236,0.000234259,0.0005789426,0.0000251073,0.0001611182,0.01581826,0.0005167251,0.0006550435,0.006533258,0.0002277431],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949511,0.001049882,0.0009151594,0.0005943828,0.0004548119,0.0008450329,0.0006951245,0.00009619733,0.0003983058],"genre_scores_gemma":[0.9854562,0.0003433935,0.002005652,0.0002388368,0.0001675185,0.00004602638,0.01167887,0.00002222243,0.00004123827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01536601,"threshold_uncertainty_score":0.9602772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1335382003001439,"score_gpt":0.430648855130127,"score_spread":0.2971106548299831,"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."}}