{"id":"W3204620962","doi":"10.3389/fdata.2021.725095","title":"NPARS—A Novel Approach to Address Accuracy and Reproducibility in Genomic Data Science","year":2021,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Hamilton Health Sciences Foundation; Arkansas Research Alliance; U.S. Department of Health and Human Services","keywords":"Python (programming language); Computer science; Software; Data science; Pipeline (software); Reproducibility; Data mining; Software engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.04478234,0.000157184,0.000352755,0.0007657878,0.0002023749,0.001267851,0.01208586,0.00004112767,0.00001137159],"category_scores_gemma":[0.06026752,0.0001381519,0.00001391839,0.004864193,0.0004195172,0.00191254,0.03209112,0.0002047918,0.00002729439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009953808,"about_ca_system_score_gemma":0.000438725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002610445,"about_ca_topic_score_gemma":0.0003010925,"domain_scores_codex":[0.9895364,0.000193153,0.0008180081,0.00749456,0.001440504,0.0005173999],"domain_scores_gemma":[0.9655409,0.0004049695,0.0001699297,0.03350383,0.0001641236,0.000216255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00003446749,0.0004086979,0.1013025,0.00001740971,0.00000775629,0.00001925794,0.0006288267,0.0004726045,0.0007406684,0.0001670179,0.451033,0.4451678],"study_design_scores_gemma":[0.0007574043,0.00001122458,0.3969315,0.00004906924,0.00001094979,0.00001533024,0.003456333,0.2053893,0.0001517046,0.001731718,0.3910938,0.0004016432],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5943699,0.002060326,0.3614554,0.00357796,0.02087079,0.001510569,0.006267113,0.00008762969,0.009800261],"genre_scores_gemma":[0.6853238,0.00007883417,0.3105597,0.000672066,0.0002766146,0.00001224018,0.001803393,0.00001715726,0.001256207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4447662,"threshold_uncertainty_score":0.9997689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4783767704711935,"score_gpt":0.4240416025368894,"score_spread":0.0543351679343041,"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."}}