{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001118697,0.000086047,0.0001035614,0.00005118407,0.00007318924,0.00004089722,0.00008260559,0.00003455619,0.00000687346],"category_scores_gemma":[0.000001257114,0.00005889831,0.00002769361,0.0001880302,0.00001686612,0.000001767118,0.00004642923,0.00003127165,0.00001239095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001049686,"about_ca_system_score_gemma":0.00001748449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000051661,"about_ca_topic_score_gemma":0.000009958971,"domain_scores_codex":[0.999455,0.00000630041,0.0001344925,0.0002183912,0.0001014118,0.00008435905],"domain_scores_gemma":[0.9995798,0.00001293935,0.0001026332,0.0002269337,0.00003722969,0.00004050642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005131138,0.00008875454,0.000490977,0.00005919655,0.000313266,7.726025e-8,0.0004814084,0.01363041,0.9169688,0.006936736,0.0001211911,0.06085794],"study_design_scores_gemma":[0.006518027,0.001440906,0.04023591,0.00006423525,0.003153939,0.00003522896,0.01416991,0.5037359,0.3619811,0.01481679,0.05112761,0.002720432],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2828057,0.00003441157,0.7159691,0.00008208383,0.000007690385,0.0004926117,0.000001369525,0.000006134069,0.0006008188],"genre_scores_gemma":[0.9829518,0.000005816862,0.01638719,0.000221632,0.00002357827,0.0002456541,0.00004277815,0.000009955254,0.0001116629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.700146,"threshold_uncertainty_score":0.2401804,"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."}}