{"id":"W4375840921","doi":"10.1093/gigascience/giad031","title":"A workflow reproducibility scale for automatic validation of biological interpretation results","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Japan Science and Technology Agency; National Bioscience Database Center; Japan Society for the Promotion of Science","keywords":"Workflow; Reproducibility; Computer science; Scale (ratio); Interpretation (philosophy); Data science; Data mining; Chemistry; Chromatography; Database; Programming language; Cartography","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03779234,0.00006731792,0.0001636121,0.0002175878,0.0004229488,0.0001624158,0.001389943,0.00001404549,0.0001109389],"category_scores_gemma":[0.02157127,0.00005033375,0.00008781422,0.001850396,0.0002108891,0.0002349974,0.0008061713,0.00005827102,0.00001810475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005163431,"about_ca_system_score_gemma":0.00006229746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001440108,"about_ca_topic_score_gemma":0.000003124178,"domain_scores_codex":[0.9958714,0.0003427849,0.0007771121,0.001546963,0.001267753,0.0001940427],"domain_scores_gemma":[0.9958998,0.001296889,0.0004115799,0.002118135,0.0002255823,0.00004803078],"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":[0.0002860654,0.0004120404,0.01057538,0.00001664685,0.000006100484,0.000001185443,0.005661845,0.0375152,0.005764872,0.0008516593,0.03242138,0.9064876],"study_design_scores_gemma":[0.0006575111,0.0005958026,0.06492393,0.00002355638,0.00001092858,0.00000622098,0.002815634,0.8347022,0.008477094,0.0759939,0.01155899,0.0002342279],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8891981,0.00001143038,0.1075198,0.0008478843,0.001133435,0.0003968796,0.0000942539,0.00005228725,0.0007459096],"genre_scores_gemma":[0.983166,2.64359e-7,0.01616569,0.00007402823,0.00001880884,0.00004377676,0.0000244094,0.000001850349,0.0005051175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9062534,"threshold_uncertainty_score":0.9907953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.185963433087809,"score_gpt":0.4022984768074108,"score_spread":0.2163350437196018,"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."}}