{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005554016,0.0007139103,0.00154311,0.001966338,0.0008990964,0.001372347,0.003033869,0.001818921,0.003740431],"category_scores_gemma":[0.02000797,0.0008820523,0.001530994,0.001402842,0.001604183,0.002291022,0.001984663,0.002065813,0.001134866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001480966,"about_ca_system_score_gemma":0.00159945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008186314,"about_ca_topic_score_gemma":0.007073086,"domain_scores_codex":[0.998346,0.0007394106,0.00009486066,0.0003589925,0.0003198862,0.0001408573],"domain_scores_gemma":[0.9915399,0.005954461,0.0007060308,0.0008133739,0.0007588408,0.0002273936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001801737,0.0001290425,0.0118532,0.0002526477,0.0001917641,0.0003457363,0.0003763595,0.7451707,0.005011386,0.134198,0.003126452,0.09916466],"study_design_scores_gemma":[0.000009017671,0.0000134182,0.0006290743,0.00001021253,0.000007352383,0.00004040419,0.00001030502,0.9770345,0.0006224862,0.0211806,0.0004288397,0.0000138205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009831585,0.0001137586,0.9891173,0.0000813759,0.00001599321,0.00005168681,0.00009146704,0.0003315145,0.0003652081],"genre_scores_gemma":[0.2069678,0.0002755578,0.7884768,0.00016534,0.0000922227,0.000452664,0.000940451,0.00027495,0.002354234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008186314,"threshold_uncertainty_score":0.02937281,"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."}}