{"id":"W3094595856","doi":"10.1101/2020.10.24.353599","title":"Microbial diversity estimation and hill number calculation using the hierarchical Pitman-Yor process","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; HEC Montréal; York University","funders":"Medical Research Council","keywords":"Population; Abundance (ecology); Statistics; Context (archaeology); Diversity (politics); Relative species abundance; Biology; Mathematics; Ecology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008550512,0.0003797465,0.0003766654,0.00008365771,0.0005751603,0.0004750862,0.0009593989,0.0003698413,0.00000426562],"category_scores_gemma":[0.0001668033,0.0003298822,0.0001053242,0.0004226849,0.0001414227,0.0003804474,0.00224276,0.0008267777,0.000008249258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301821,"about_ca_system_score_gemma":0.0003384607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005239682,"about_ca_topic_score_gemma":8.745776e-7,"domain_scores_codex":[0.9975312,0.0003902642,0.0003517967,0.001001668,0.0003745692,0.0003505206],"domain_scores_gemma":[0.9982739,0.00009027871,0.0003186557,0.0008209599,0.000266518,0.0002296706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002147101,0.0006396357,0.02546623,0.0038612,0.0008973884,0.000366214,0.003002209,0.006507237,0.7743781,0.181949,0.001412172,0.001305891],"study_design_scores_gemma":[0.0005093567,0.00002565077,0.0308603,0.0002805448,0.0001674901,2.682654e-7,0.000001266112,0.9380908,0.02770625,0.001217768,0.0002050112,0.0009353188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2432652,0.00007241634,0.7544954,0.001037097,0.0004608637,0.000446979,0.00002477976,0.0001930018,0.000004246518],"genre_scores_gemma":[0.6896763,0.0000124238,0.3097263,0.0003393033,0.0002059609,0.00001388264,1.369397e-7,0.00002492669,7.54714e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9315835,"threshold_uncertainty_score":0.9999153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02614307284607648,"score_gpt":0.2628381144831295,"score_spread":0.236695041637053,"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."}}