{"id":"W4401412882","doi":"10.4230/lipics.sea.2024.10","title":"Taxonomic Classification with Maximal Exact Matches in KATKA Kernels and Minimizer Digests","year":2024,"lang":"en","type":"article","venue":"PubMed","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Human Genome Research Institute; 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; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002668123,0.0007068911,0.0007714454,0.002150842,0.0006235506,0.002074721,0.001399136,0.001240852,0.003929907],"category_scores_gemma":[0.01752184,0.000468325,0.001161678,0.002015195,0.0005997919,0.003543096,0.001706206,0.001369294,0.002921807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000753486,"about_ca_system_score_gemma":0.001119538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002186876,"about_ca_topic_score_gemma":0.00272569,"domain_scores_codex":[0.9985456,0.0003563275,0.0002041531,0.0004073061,0.0003315992,0.0001549257],"domain_scores_gemma":[0.9953349,0.001855497,0.0003907488,0.001473317,0.0007916045,0.000153947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003092855,0.0005401234,0.02134189,0.001196851,0.0003417175,0.0003935146,0.001235334,0.131119,0.05382955,0.03374332,0.02024759,0.7329182],"study_design_scores_gemma":[0.00006223024,0.0002394041,0.005924128,0.00008966386,0.00006985985,0.0004747667,0.0004451636,0.9187243,0.02278253,0.04363461,0.00747858,0.00007473171],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2501264,0.0007188531,0.7323964,0.0004390363,0.0001199549,0.0001926421,0.002805342,0.009818113,0.003383222],"genre_scores_gemma":[0.5027436,0.0002170969,0.4864811,0.00009248456,0.0000334106,0.000218142,0.006494349,0.0007279505,0.002991885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003929907,"threshold_uncertainty_score":0.01411057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02307681910436923,"score_gpt":0.2293612411250336,"score_spread":0.2062844220206644,"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."}}