{"id":"W6913037803","doi":"10.5524/100977","title":"Supporting data for \"Future-proofing and maximizing the utility of metadata: The PHA4GE SARS-CoV-2 contextual data specification package\"","year":2022,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Fundação para a Ciência e a Tecnologia; Genome Canada","keywords":"Interoperability; Consistency (knowledge bases); Contextual design; Standardization; Data integration; Data aggregator; Data quality; Data consistency; Alliance","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006022183,0.001647393,0.001159939,0.003470628,0.001333915,0.002779218,0.003314404,0.002249418,0.09679301],"category_scores_gemma":[0.02366958,0.0009592098,0.002102681,0.006284906,0.0006207358,0.002483844,0.00471279,0.002525479,0.06473546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002266159,"about_ca_system_score_gemma":0.006714951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04033272,"about_ca_topic_score_gemma":0.05771762,"domain_scores_codex":[0.9968359,0.0007953935,0.0005856073,0.0005266616,0.0008639866,0.000392481],"domain_scores_gemma":[0.9900438,0.003497469,0.0008934938,0.002278234,0.002388377,0.000898588],"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":[0.0001389446,0.00001988877,0.001535138,0.0008436819,0.00004266427,0.000039943,0.000074865,0.0004244638,0.000270571,0.002419842,0.989446,0.004743971],"study_design_scores_gemma":[0.0002821804,0.00001636568,0.003288523,0.0006791239,0.00003591131,0.00005563497,0.0001764294,0.0006939659,0.0007292439,0.00421017,0.9897833,0.00004915756],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000120422,0.00002608184,0.0006419728,0.0002223647,0.00005133256,0.00004281031,0.9971426,0.0008101312,0.0009422185],"genre_scores_gemma":[0.0005279747,0.00004646724,0.00271832,0.0001243085,0.000008058172,0.0002307145,0.9956996,0.0002576883,0.000386919],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09679301,"threshold_uncertainty_score":0.3238049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2391469643514842,"score_gpt":0.4007605994116636,"score_spread":0.1616136350601794,"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."}}