{"id":"W4387007406","doi":"10.32942/x29025","title":"Don’t make genetic data disposable: Best practices for genetic and genomic data archiving","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Research Data Management Practices","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"U.S. Geological Survey; Biodiversa+; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Metadata; Data science; Repurposing; Genetic data; Best practice; Data management; Field (mathematics); Computer science; Genomics; World Wide Web; Biology; Ecology; Data mining; Genome; Political science; Population; Sociology","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","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.004066742,0.0005171336,0.0004956996,0.0004561747,0.0003528584,0.01427414,0.03571991,0.0001573259,0.00001863981],"category_scores_gemma":[0.005015956,0.0004935446,0.00004322748,0.0003465448,0.0001699006,0.01603397,0.1832629,0.0008263077,0.0001124886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005787034,"about_ca_system_score_gemma":0.0006217866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004560534,"about_ca_topic_score_gemma":0.004839974,"domain_scores_codex":[0.9923354,0.0004432399,0.0007541252,0.004543975,0.0009510414,0.0009722568],"domain_scores_gemma":[0.9748914,0.003007355,0.001225796,0.0204672,0.000104243,0.0003039526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001235852,0.0006873884,0.01445496,0.007829111,0.002189911,0.000632742,0.0003563925,0.002716436,0.0005519507,0.01702025,0.09671446,0.8567228],"study_design_scores_gemma":[0.0003182804,0.00008482597,0.01756225,0.0001541156,0.0002166245,0.00003016908,0.00009628398,0.6680073,0.000005318173,0.002695622,0.3101827,0.0006465132],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003391853,0.002293369,0.9763528,0.008867923,0.00107986,0.002852003,0.003357104,0.0003749601,0.001430121],"genre_scores_gemma":[0.001939216,0.02917078,0.9472365,0.0002593926,0.0006253247,0.0002693415,0.005499351,0.000114113,0.01488601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8560763,"threshold_uncertainty_score":0.9997516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4256814650014928,"score_gpt":0.4444524972125066,"score_spread":0.01877103221101373,"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."}}