{"id":"W4386622639","doi":"10.5281/zenodo.8335901","title":"HiTaxon: A hierarchical ensemble framework for taxonomic classification of short reads","year":2023,"lang":"en","type":"article","venue":"TSpace","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Biological classification; Artificial intelligence; Natural language processing; Biology; Evolutionary biology","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":[0.004497652,0.001624047,0.001847649,0.00232333,0.001446795,0.001902079,0.002732139,0.001546355,0.003268955],"category_scores_gemma":[0.009732197,0.0006915346,0.003287872,0.002287778,0.0004481639,0.002151871,0.002787914,0.002766339,0.001377298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000956267,"about_ca_system_score_gemma":0.001907804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01849412,"about_ca_topic_score_gemma":0.03375856,"domain_scores_codex":[0.997996,0.000633312,0.0001422689,0.0004877023,0.0005336019,0.0002071975],"domain_scores_gemma":[0.9973884,0.001200018,0.0001251909,0.0004331928,0.0006923953,0.000160818],"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":[0.0007858231,0.0003632187,0.01614255,0.0005937734,0.002420612,0.0003104263,0.0006286681,0.2868114,0.01633203,0.01445582,0.03718196,0.6239737],"study_design_scores_gemma":[0.00002193991,0.00007424179,0.001922834,0.00003070592,0.00009627175,0.00003724371,0.00005023988,0.977002,0.001920114,0.01460825,0.00419411,0.00004202353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01018962,0.0003096435,0.9781379,0.0001080878,0.0001362381,0.0001587683,0.003866426,0.006677044,0.0004163014],"genre_scores_gemma":[0.1297937,0.0003173744,0.8368207,0.0002986526,0.0002348294,0.001020442,0.02714011,0.00154579,0.002828423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01849412,"threshold_uncertainty_score":0.03677297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1009105167871631,"score_gpt":0.3507975510414048,"score_spread":0.2498870342542416,"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."}}