{"id":"W2997348301","doi":"10.7717/peerj-cs.243","title":"HACSim: an R package to estimate intraspecific sample sizes for genetic diversity assessment using haplotype accumulation curves","year":2020,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Sampling (signal processing); Barcode; Haplotype; Sample size determination; DNA barcoding; Sample (material); Biology; Statistics; Genetic diversity; Computer science; Estimator; Evolutionary biology; Mathematics; Genetics; Population; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001543222,0.0001113061,0.0001069728,0.00003768874,0.000463359,0.0001095046,0.0004537899,0.0000420127,0.00001712022],"category_scores_gemma":[0.00006343683,0.0001160117,0.00003907997,0.0002211336,0.00008641962,0.00002365309,0.0006040843,0.00003859971,0.000002714477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001910717,"about_ca_system_score_gemma":0.00009062557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003095313,"about_ca_topic_score_gemma":0.00001475039,"domain_scores_codex":[0.998903,0.00002659698,0.0001178611,0.0004791726,0.0002612758,0.0002121056],"domain_scores_gemma":[0.999281,0.00001415631,0.0000571158,0.0002336617,0.0002021819,0.0002118758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001373566,0.00009990377,0.1841599,0.0001806009,0.00004801498,0.000004556859,0.00203281,0.2936253,0.4725527,0.0004037725,0.003960447,0.04279461],"study_design_scores_gemma":[0.000467779,0.000656714,0.6716238,0.00002100931,0.0000357476,0.000004820589,0.00003633621,0.3100605,0.01379025,0.0002802791,0.002649406,0.0003733509],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5074296,0.00001782448,0.4918804,0.0003084647,0.0001519636,0.0001606982,0.00003116958,0.00001437177,0.000005557652],"genre_scores_gemma":[0.6889127,0.00000380898,0.3099526,0.0009181942,0.0001503095,0.000001178805,0.00005313958,0.000004564631,0.000003479088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4874639,"threshold_uncertainty_score":0.4730819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08286917328849763,"score_gpt":0.3542387032832539,"score_spread":0.2713695299947563,"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."}}