{"id":"W3037038044","doi":"10.1101/2020.06.27.175091","title":"<i>pixy</i> : Unbiased estimation of nucleotide diversity and divergence in the presence of missing data","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Missing data; Population; Statistics; Computer science; Data mining; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.008309473,0.001156926,0.001356512,0.001735468,0.000899896,0.001748697,0.002913957,0.001135525,0.01152832],"category_scores_gemma":[0.03321194,0.001093962,0.0009022471,0.001885603,0.001256373,0.001995277,0.002434237,0.002273506,0.004707691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005803527,"about_ca_system_score_gemma":0.001765507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002761056,"about_ca_topic_score_gemma":0.003269363,"domain_scores_codex":[0.9974044,0.001057469,0.0001226115,0.0005225197,0.0008009815,0.000092009],"domain_scores_gemma":[0.9893519,0.006857665,0.0007843097,0.001683617,0.00108642,0.0002360852],"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":[0.0006521348,0.0001164372,0.0290838,0.001045389,0.001160859,0.001073336,0.000719475,0.1671792,0.0169705,0.05483504,0.226076,0.5010878],"study_design_scores_gemma":[0.0001018351,0.00004965199,0.003615494,0.0001150205,0.00006772579,0.0004268698,0.00004649357,0.9274083,0.01606554,0.03006628,0.02194154,0.00009533331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005525162,0.0002264594,0.9700921,0.0003784118,0.0001411096,0.00005734792,0.001662147,0.02077158,0.001145784],"genre_scores_gemma":[0.06999901,0.0002244586,0.9164499,0.0005055812,0.000157446,0.0004355686,0.003545015,0.006880256,0.001802651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01152832,"threshold_uncertainty_score":0.04394519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03261909373470249,"score_gpt":0.238633612616915,"score_spread":0.2060145188822126,"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."}}