{"id":"W4213288981","doi":"10.1093/gigascience/giac003","title":"Future-proofing and maximizing the utility of metadata: The PHA4GE SARS-CoV-2 contextual data specification package","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Dalhousie University; McMaster University; BC Centre for Disease Control; Simon Fraser University","funders":"Biotechnology and Biological Sciences Research Council; National Institutes of Health; U.S. National Library of Medicine; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Interoperability; Computer science; Metadata; Harmonization; Standardization; Consistency (knowledge bases); Data science; Open science; Data sharing; Openness to experience; Best practice; Data integration; World Wide Web; Data mining; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.00142754,0.00007258877,0.00008819794,0.00001253602,0.0004191339,0.00004248682,0.001129122,0.00002963283,0.000007698054],"category_scores_gemma":[0.0002604192,0.00004130245,0.00002425591,0.0001610374,0.0007598143,0.00001156419,0.001104411,0.0001279838,4.969393e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003760277,"about_ca_system_score_gemma":0.00005480023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003467952,"about_ca_topic_score_gemma":0.00003398762,"domain_scores_codex":[0.9989747,0.0001437831,0.0001517297,0.0003506569,0.0002242382,0.0001548309],"domain_scores_gemma":[0.9988957,0.0000566026,0.00009927894,0.0009063538,0.00002460448,0.0000174613],"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":[0.00004388316,0.00004317783,0.0008281393,0.000009805319,0.00002367922,0.000001643678,0.0004531064,7.177833e-7,0.8544675,0.0006959457,0.0138394,0.1295931],"study_design_scores_gemma":[0.00038029,0.0002168646,0.0207563,0.000006271174,0.00003765093,0.00006933384,0.007382172,0.001522939,0.2917612,0.0003917336,0.677278,0.0001972853],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778286,0.006418903,0.009854907,0.00438903,0.0004409376,0.0002256104,0.0002338732,0.00001486604,0.0005932454],"genre_scores_gemma":[0.9984371,0.0001304992,0.0007480198,0.0004493224,0.0001051429,0.00001100815,0.00005689081,0.000003528752,0.00005846698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6634386,"threshold_uncertainty_score":0.3223681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.102220590335467,"score_gpt":0.3214307627217884,"score_spread":0.2192101723863215,"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."}}