{"id":"W2775087763","doi":"10.1038/s41598-017-17168-6","title":"A Random Categorization Model for Hierarchical Taxonomies","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Particle Physics","funders":"National Institute of General Medical Sciences; National Science Foundation; National Institutes of Health; National Cancer Institute; Aspen Center for Physics; East China Normal University","keywords":"Categorization; Computer science; Taxonomic rank; Directory; Taxonomy (biology); Sample (material); Relative abundance distribution; Data science; Parametric statistics; Abundance (ecology); Ecology; Information retrieval; Relative species abundance; Artificial intelligence; Biology; Statistics; Taxon; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008882183,0.001128867,0.001792752,0.003731963,0.001724941,0.00312283,0.005817701,0.003713913,0.01558452],"category_scores_gemma":[0.02795126,0.0008032221,0.002808935,0.003195542,0.002720272,0.008103402,0.00221045,0.004140982,0.00414985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004053223,"about_ca_system_score_gemma":0.001605633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01124278,"about_ca_topic_score_gemma":0.01028682,"domain_scores_codex":[0.9962649,0.001420778,0.0001696142,0.001212001,0.0005018817,0.0004309176],"domain_scores_gemma":[0.9850825,0.01029637,0.001347948,0.001502783,0.001156581,0.0006137565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005547659,0.0003763303,0.01388361,0.0004127007,0.0002019281,0.0004919939,0.002005588,0.233399,0.002873147,0.6251429,0.02007059,0.1005873],"study_design_scores_gemma":[0.00006409499,0.00005504963,0.001345354,0.00005611189,0.00002872739,0.0001620031,0.0001182502,0.7807443,0.000187982,0.2134332,0.003768128,0.0000367896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0676708,0.0008027799,0.9164727,0.002919744,0.0002134043,0.0006348096,0.003052673,0.001556058,0.006676929],"genre_scores_gemma":[0.6629089,0.001168736,0.2872432,0.001684555,0.0005206926,0.003033021,0.00693033,0.0005920156,0.0359186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01558452,"threshold_uncertainty_score":0.05213547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850897945260198,"score_gpt":0.2928553617912049,"score_spread":0.2643463823386029,"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."}}