{"id":"W3010730509","doi":"10.1093/sysbio/syaa020","title":"Evaluating the Performance of Probabilistic Algorithms for Phylogenetic Analysis of Big Morphological Datasets: A Simulation Study","year":2020,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Inference; Metric (unit); Probabilistic logic; Sampling (signal processing); Bayesian probability; Tree (set theory); Computer science; Phylogenetic tree; Benchmark (surveying); Bayesian network; Artificial intelligence; Statistics; Machine learning; Data mining; Biology; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001085192,0.00008693158,0.0005591582,0.00005863215,0.00008806814,0.000003395294,0.0001981836,0.0000497916,0.00004240143],"category_scores_gemma":[0.000961942,0.00004558422,0.00007914931,0.0003985005,0.0001724958,0.00001217226,0.00001899743,0.00004573971,0.000003322667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001645587,"about_ca_system_score_gemma":0.00001848708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007871957,"about_ca_topic_score_gemma":0.0007301681,"domain_scores_codex":[0.998386,0.0006203761,0.0005746418,0.0001964065,0.0001022618,0.0001203084],"domain_scores_gemma":[0.9978183,0.001511991,0.0003622916,0.0001926606,0.00008977862,0.00002497228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005006255,0.00002859387,0.7920213,0.001927954,0.0005530055,2.062837e-7,0.0009071315,0.2041047,0.00006320597,0.00001417263,0.000001198742,0.000328548],"study_design_scores_gemma":[0.0001540626,0.001263784,0.3453332,0.00002829023,0.000712288,5.618676e-7,0.0006403522,0.6518001,0.000002398117,0.00003001632,2.799292e-7,0.00003464193],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951332,0.0006575372,0.002346163,0.00007651264,0.00006775897,0.001372701,0.0003224051,0.000008287282,0.00001544757],"genre_scores_gemma":[0.9991519,0.00000267153,0.0006130001,0.00005464119,0.00002048156,0.0000272968,0.0001283203,8.228055e-7,9.07719e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4476954,"threshold_uncertainty_score":0.1858871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.202585874019112,"score_gpt":0.3762723460564108,"score_spread":0.1736864720372988,"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."}}