{"id":"W4409589740","doi":"10.1007/978-3-031-85870-3_4","title":"Predicting Soil Bacterial and Fungal Communities at Different Taxonomic Levels Using Machine Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000233134,0.0003263603,0.0005341807,0.000241313,0.0005167341,0.00005966385,0.0002288863,0.0002103626,0.00001840628],"category_scores_gemma":[0.0001809476,0.0003214867,0.00003937963,0.0001467558,0.0002953025,0.000004707072,0.001756108,0.0001568786,8.579417e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009096772,"about_ca_system_score_gemma":0.00006805389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001034207,"about_ca_topic_score_gemma":0.01471975,"domain_scores_codex":[0.9986395,0.00009821904,0.0004695075,0.0005667298,0.00007235857,0.0001536565],"domain_scores_gemma":[0.9986885,0.00008031388,0.0003001208,0.0005930126,0.0003011655,0.00003687096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004331304,0.00004892673,0.9666598,0.0003745504,0.005413806,6.749918e-7,0.001734069,0.00005233976,0.02228753,0.001313364,0.0005131906,0.001558389],"study_design_scores_gemma":[0.004848155,0.0004875556,0.6573423,0.001295556,0.02341218,0.00004518144,0.008730507,0.06305741,0.007347409,0.0009403677,0.2276801,0.00481333],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379636,0.05279674,0.001361892,0.00007656273,0.0005426882,0.0004341457,0.001957823,0.00001884289,0.004847706],"genre_scores_gemma":[0.9299156,0.05073847,0.0001848795,0.00001184009,0.0002987235,0.000006336755,0.00693633,0.00003802526,0.0118698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3093176,"threshold_uncertainty_score":0.9999237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09552162689760141,"score_gpt":0.3075578810994994,"score_spread":0.212036254201898,"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."}}