{"id":"W3048030338","doi":"10.20944/preprints202008.0220.v1","title":"The PHA4GE SARS-CoV-2 Contextual Data Specification for Open Genomic Epidemiology","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Dalhousie University; McMaster University; BC Centre for Disease Control; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Interoperability; Computer science; Openness to experience; Data science; Consistency (knowledge bases); Open science; Open data; Data integration; Reuse; Standardization; World Wide Web; Best practice; Alliance; Knowledge management; Data mining; Engineering; Geography; 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":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002674084,0.0003525091,0.0005842797,0.00002490236,0.0002500413,0.00004909477,0.005511727,0.0007030117,0.00002095798],"category_scores_gemma":[0.005815798,0.0002771857,0.000183003,0.00004749059,0.0005095722,0.000004839276,0.01404541,0.0005559167,0.0002314996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004132838,"about_ca_system_score_gemma":0.0003340881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001534326,"about_ca_topic_score_gemma":0.0001225799,"domain_scores_codex":[0.9963993,0.0004288433,0.0007636855,0.001821522,0.0001118259,0.0004748263],"domain_scores_gemma":[0.9954219,0.0004080835,0.0005474289,0.003399158,0.00012065,0.0001027782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001360133,0.0001861834,0.04406048,0.0001923246,0.001005765,0.000004826768,0.0002547906,0.000023002,0.8166234,0.001922551,0.08590828,0.04845829],"study_design_scores_gemma":[0.0006709391,0.00009871324,0.02958362,0.00003387968,0.00007503534,0.000007980152,0.0001140784,0.0004654928,0.08948462,0.004819914,0.8742483,0.0003974089],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.909807,0.007921859,0.02944711,0.03868594,0.002994853,0.004636602,0.001690945,0.0001820904,0.004633643],"genre_scores_gemma":[0.9843515,0.002049988,0.00456961,0.002121544,0.001264421,0.0005443823,0.004131429,0.00006584812,0.0009013443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.78834,"threshold_uncertainty_score":0.9999681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5666488393984701,"score_gpt":0.4811194782051965,"score_spread":0.08552936119327365,"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."}}