{"id":"W6931585892","doi":"10.5281/zenodo.8335900","title":"HiTaxon: A hierarchical ensemble framework for taxonomic classification of short reads","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Ensemble learning; Taxonomy (biology); Biological classification; Pattern recognition (psychology); Ensemble forecasting","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":[0.004256056,0.001562063,0.001873574,0.001905551,0.001235656,0.001873328,0.002467725,0.00153761,0.002821864],"category_scores_gemma":[0.008228654,0.0006735451,0.003223521,0.001894656,0.0004172603,0.001869353,0.00245056,0.002523048,0.001341755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009109114,"about_ca_system_score_gemma":0.001839201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01582406,"about_ca_topic_score_gemma":0.0255179,"domain_scores_codex":[0.9980298,0.0006812032,0.0001334801,0.000448041,0.0004917285,0.0002157492],"domain_scores_gemma":[0.9977558,0.0009908038,0.0001159993,0.0004078348,0.0005839329,0.0001457285],"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":[0.0008235695,0.0003343147,0.01294412,0.0005617113,0.002240037,0.000263764,0.000540826,0.3795334,0.01763657,0.0185163,0.03357289,0.5330325],"study_design_scores_gemma":[0.00002175359,0.00006348632,0.00169672,0.00002801967,0.0000868931,0.00003218592,0.00003388421,0.9758045,0.00166849,0.01679451,0.003733267,0.00003634424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008938641,0.0002731965,0.981146,0.00008320438,0.0001052169,0.000118434,0.00361427,0.005394658,0.0003264472],"genre_scores_gemma":[0.1300495,0.0003234199,0.8340071,0.0002641236,0.000218391,0.00102343,0.02975437,0.001670212,0.00268945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01582406,"threshold_uncertainty_score":0.03146386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08495539708446646,"score_gpt":0.2805812845464351,"score_spread":0.1956258874619686,"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."}}