{"id":"W4366598888","doi":"10.1101/2023.04.19.537466","title":"Exploring the impact of read clustering thresholds on RADseq-based systematics: an empirical example from European amphibians","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Universität Potsdam; Deutsche Forschungsgemeinschaft","keywords":"Coalescent theory; Cluster analysis; Biology; Evolutionary biology; Phylogenomics; Systematics; Genomics; Genome; Population; Computational biology; Phylogenetic tree; Clade; Ecology; Genetics; Computer science; Machine learning; Gene; Taxonomy (biology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008960128,0.000620931,0.0005308246,0.001875967,0.001185362,0.00111495,0.0009127424,0.0007125075,0.001449443],"category_scores_gemma":[0.02514433,0.0002451345,0.0008581624,0.001724815,0.001632772,0.001230662,0.001239752,0.0009350672,0.0003497439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000568983,"about_ca_system_score_gemma":0.000378975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003945926,"about_ca_topic_score_gemma":0.005081792,"domain_scores_codex":[0.9948974,0.002733302,0.0002900767,0.001393367,0.0004401921,0.0002455898],"domain_scores_gemma":[0.9768275,0.01543781,0.002421814,0.002527958,0.002261398,0.000523403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006925514,0.0001580505,0.8929126,0.0003882922,0.0009800147,0.001174265,0.002944523,0.0298553,0.03614173,0.001626752,0.001296289,0.03182974],"study_design_scores_gemma":[0.00004160378,0.0004975564,0.9296,0.0001056497,0.00053179,0.00103534,0.002564974,0.05078864,0.008281937,0.002331634,0.004137596,0.00008332537],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958573,0.0002821147,0.003086748,0.00004211363,0.000003902248,0.000008775112,0.0002625702,0.00006191891,0.0003944811],"genre_scores_gemma":[0.99675,0.00005083807,0.002477118,0.0000285989,0.000004179192,0.000007839237,0.000556278,0.00005849116,0.00006671096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008960128,"threshold_uncertainty_score":0.04738623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1108499609664617,"score_gpt":0.284468763266463,"score_spread":0.1736188023000013,"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."}}