{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02508624,0.001630428,0.00139488,0.003144233,0.001740372,0.007514951,0.00541968,0.001816914,0.004932852],"category_scores_gemma":[0.05853925,0.001299314,0.002971466,0.003207651,0.00306453,0.008891091,0.01406341,0.004690113,0.00442187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001663117,"about_ca_system_score_gemma":0.006098943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003590241,"about_ca_topic_score_gemma":0.003282169,"domain_scores_codex":[0.9701012,0.008706203,0.002771681,0.006610094,0.01097861,0.0008321889],"domain_scores_gemma":[0.9518177,0.0146303,0.003735858,0.01968472,0.009020415,0.001111122],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001146993,0.0004677199,0.01839702,0.001203972,0.0008856929,0.001468201,0.003368115,0.05007554,0.02716647,0.1785729,0.04439897,0.6728485],"study_design_scores_gemma":[0.0001955631,0.0004955592,0.005334404,0.0002984949,0.0004482319,0.001607597,0.0007426707,0.5598758,0.05189493,0.2121888,0.1665915,0.0003264158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00352987,0.0001371333,0.9761174,0.0005908295,0.0001734749,0.0002086974,0.0004631682,0.01656206,0.002217543],"genre_scores_gemma":[0.06673317,0.0002923936,0.9221254,0.0006576285,0.0002401857,0.0004794841,0.002510031,0.003481799,0.003479864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9749138,"threshold_uncertainty_score":0.1326703,"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."}}