{"id":"W2950287694","doi":"10.1016/j.amc.2019.02.018","title":"Improving MinHash via the containment index with applications to metagenomic analysis","year":2019,"lang":"en","type":"article","venue":"Applied Mathematics and Computation","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"National Sleep Foundation; National Science Foundation","keywords":"Jaccard index; Computer science; Probabilistic logic; Bloom filter; Intersection (aeronautics); Similarity (geometry); Data mining; Containment (computer programming); Index (typography); Set (abstract data type); Algorithm; Artificial intelligence; Pattern recognition (psychology)","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":[0.004242469,0.00100969,0.002405685,0.003848097,0.001358821,0.002611176,0.002602056,0.001195463,0.003793012],"category_scores_gemma":[0.02254447,0.0006385,0.001196034,0.004300094,0.001458661,0.004140333,0.003325518,0.002310767,0.001161069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105303,"about_ca_system_score_gemma":0.002404873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002843647,"about_ca_topic_score_gemma":0.004456196,"domain_scores_codex":[0.9972951,0.001067048,0.0001585931,0.000485318,0.0008123844,0.0001815825],"domain_scores_gemma":[0.9879332,0.007957324,0.0004636621,0.001941471,0.001344674,0.0003596443],"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":[0.001002782,0.000338184,0.005621837,0.000428082,0.0002517815,0.0001705773,0.0003795645,0.1413814,0.01155522,0.1028876,0.01222076,0.7237622],"study_design_scores_gemma":[0.00005646921,0.0001033351,0.0007368574,0.00002558618,0.00003400004,0.0000812349,0.00005721729,0.8416642,0.004135868,0.1494927,0.003585039,0.0000273689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02035338,0.0008421889,0.9748024,0.0005028208,0.0001170017,0.0000519607,0.0003541371,0.001616192,0.001359815],"genre_scores_gemma":[0.208028,0.0004665243,0.7868528,0.0003643278,0.00040345,0.0001713273,0.001220706,0.0008432746,0.001649578],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004242469,"threshold_uncertainty_score":0.02243656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007035659586375496,"score_gpt":0.2366137185515617,"score_spread":0.2295780589651862,"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."}}