{"id":"W4391800639","doi":"10.48550/arxiv.2402.06935","title":"Taxonomic classification with maximal exact matches in KATKA kernels and minimizer digests","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Gruppo Nazionale per il Calcolo Scientifico; Agencia Nacional de Investigación y Desarrollo; Ministero della Salute; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; National Institutes of Health; National Science Foundation","keywords":"Mathematics; Statistics; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004503952,0.0009871032,0.001129959,0.001971643,0.00069251,0.001947152,0.001553013,0.001777741,0.001470846],"category_scores_gemma":[0.02160107,0.0005531363,0.001429034,0.001405246,0.0008646709,0.00434745,0.00202967,0.002335568,0.001232823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332739,"about_ca_system_score_gemma":0.001476956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004872057,"about_ca_topic_score_gemma":0.004185264,"domain_scores_codex":[0.9976394,0.0007223747,0.0003191855,0.0005737913,0.0004761003,0.0002691975],"domain_scores_gemma":[0.9929976,0.003581131,0.000784077,0.001496988,0.0009233541,0.0002168246],"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":[0.003079261,0.000866938,0.03871556,0.0005799297,0.0004227859,0.0003495151,0.001368976,0.3802819,0.02829137,0.01965681,0.007798949,0.518588],"study_design_scores_gemma":[0.00002928141,0.0001101199,0.002173584,0.00002204652,0.00002528082,0.00009173872,0.000182286,0.9825606,0.004316649,0.009630388,0.0008259801,0.00003201164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4386636,0.0006356699,0.5510507,0.0004470963,0.00008157065,0.0001866697,0.0009140853,0.006559871,0.001460841],"genre_scores_gemma":[0.674373,0.0001312912,0.3203855,0.0001413291,0.00003200161,0.000208046,0.002642233,0.0003481883,0.001738372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004872057,"threshold_uncertainty_score":0.02381945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07483692217326347,"score_gpt":0.1863372144139413,"score_spread":0.1115002922406778,"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."}}