{"id":"W2895034650","doi":"10.1101/434795","title":"Improving on hash-based probabilistic sequence classification using multiple spaced seeds and multi-index Bloom filters","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Bloom filter; Computer science; Hash function; Search engine indexing; Probabilistic logic; Hash table; Sensitivity (control systems); Data mining; Data structure; Algorithm; Artificial intelligence","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":[0.002899197,0.0007839006,0.001279814,0.002335645,0.001156742,0.002267215,0.002965879,0.001501438,0.002629515],"category_scores_gemma":[0.009309806,0.0005841352,0.0007675063,0.002334966,0.0007667512,0.004021168,0.001670618,0.001169684,0.002338712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00257539,"about_ca_system_score_gemma":0.003787195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009457314,"about_ca_topic_score_gemma":0.009904416,"domain_scores_codex":[0.9978642,0.0003325852,0.0001806547,0.0004865594,0.0009188464,0.0002171349],"domain_scores_gemma":[0.993176,0.002785157,0.0006065719,0.001497401,0.001700824,0.0002340377],"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":[0.001469145,0.0004728288,0.01787234,0.0001811804,0.0001244727,0.0001142082,0.0003314302,0.08524271,0.07666703,0.01366981,0.008768456,0.7950864],"study_design_scores_gemma":[0.00005919885,0.0001012558,0.001192701,0.00001391811,0.00002015736,0.0001000484,0.00005010523,0.9495347,0.04005155,0.005912117,0.002929655,0.00003464795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07685034,0.0002691494,0.909075,0.000329654,0.00008566249,0.0001434891,0.0003614311,0.01164005,0.001245158],"genre_scores_gemma":[0.2129647,0.00009061531,0.7828683,0.0002155502,0.00004794795,0.0001511713,0.0008738586,0.0003081664,0.002479542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009457314,"threshold_uncertainty_score":0.01880455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03748126852700348,"score_gpt":0.2464035094900839,"score_spread":0.2089222409630804,"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."}}