{"id":"W4322762246","doi":"10.20944/preprints202303.0037.v1","title":"PHA4GE Quality Control Contextual Data Tags: Standardized Annotations for Sharing Public Health Sequence Datasets with Known Quality Issues to Facilitate Testing and Training","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Western University; Dalhousie University; Simon Fraser University","funders":"European and Developing Countries Clinical Trials Partnership; Foreign, Commonwealth and Development Office; Bill and Melinda Gates Foundation; European Commission; Medical Research Council; Genome Canada","keywords":"Computer science; Standardization; Quality (philosophy); Data quality; Data science; Data sharing; Software portability; Data mining; Interoperability; Documentation; World Wide Web; Metric (unit); Medicine; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07213318,0.002728852,0.002359277,0.01269887,0.003488122,0.007889905,0.004187076,0.003580636,0.009890833],"category_scores_gemma":[0.1403522,0.002073989,0.00265723,0.01156802,0.003586335,0.01022782,0.01295329,0.006973794,0.01232406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005020593,"about_ca_system_score_gemma":0.01684098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00820915,"about_ca_topic_score_gemma":0.008103459,"domain_scores_codex":[0.9603624,0.01247461,0.01091011,0.005206678,0.008784175,0.002262059],"domain_scores_gemma":[0.8303338,0.05414717,0.02060675,0.06146881,0.02901703,0.004426415],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.008124484,0.001253421,0.04717826,0.01094329,0.0006287042,0.001869581,0.01146404,0.00863335,0.08310503,0.1199814,0.4216437,0.2851748],"study_design_scores_gemma":[0.0002894147,0.0002846611,0.0122611,0.003903842,0.0002317973,0.0005559858,0.001764881,0.006281253,0.06717686,0.03579608,0.8708864,0.0005676563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02295399,0.001659709,0.6527867,0.004993413,0.002848324,0.005439474,0.203617,0.08254807,0.0231533],"genre_scores_gemma":[0.04471252,0.001385151,0.6049277,0.003444286,0.0004821372,0.008241441,0.3126825,0.0164969,0.0076273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9278668,"threshold_uncertainty_score":0.3814813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6657609092479185,"score_gpt":0.482584756827902,"score_spread":0.1831761524200166,"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."}}