{"id":"W3146187752","doi":"10.1186/s12859-021-04018-6","title":"Reliable genomic strategies for species classification of plant genetic resources","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Newfoundland and Labrador; Ministerie van Landbouw, Natuur en Voedselkwaliteit","keywords":"Naive Bayes classifier; Classifier (UML); Documentation; Computer science; Data mining; Random forest; Variety (cybernetics); Bayes' theorem; Machine learning; Artificial intelligence; Support vector machine; Bayesian probability","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":[],"consensus_categories":[],"category_scores_codex":[0.00009449117,0.0001191605,0.000160341,0.00002973023,0.0000784377,0.0000378101,0.0001400745,0.00009116189,0.000006562777],"category_scores_gemma":[0.00004157242,0.0001121456,0.00009300545,0.00005654521,0.00007738623,0.000001685822,0.00008873671,0.00002904808,0.000003555648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008694222,"about_ca_system_score_gemma":0.0001921694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004202175,"about_ca_topic_score_gemma":0.00005920244,"domain_scores_codex":[0.9992241,0.00001179499,0.0003701892,0.0001370584,0.00008270702,0.0001741419],"domain_scores_gemma":[0.9993021,0.00002400249,0.0001716845,0.0003149977,0.0001524351,0.00003476311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001058854,0.00006866784,0.009749845,0.0005705974,0.0001391847,4.657503e-7,0.001049725,0.003813549,0.9736207,0.00321626,0.006842086,0.0008230933],"study_design_scores_gemma":[0.001903201,0.0007497044,0.2160952,0.00006774512,0.0001654781,0.00005065696,0.02016731,0.03431569,0.179907,0.00217893,0.5436016,0.0007975038],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578812,0.002216042,0.03436489,0.00003975954,0.0001747775,0.0002712696,0.0003459505,0.000005063032,0.004701069],"genre_scores_gemma":[0.7421289,0.001290329,0.254423,0.0001232358,0.0002656855,0.00005266553,0.0003885232,0.00002813466,0.001299548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7937137,"threshold_uncertainty_score":0.4573167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02844512426101886,"score_gpt":0.2325085918689675,"score_spread":0.2040634676079486,"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."}}