{"id":"W4205262153","doi":"10.1089/cmb.2021.0445","title":"Finding Maximal Exact Matches Using the r-Index","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Set (abstract data type); Sequence (biology); Computer science; Data structure; Index (typography); Key (lock); Space (punctuation); Code (set theory); k-mer; Algorithm; Theoretical computer science; Data set; Genome; Programming language; Artificial intelligence; Biology","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":[0.0003199754,0.00007042025,0.0001125282,0.00004505033,0.0002421075,0.00000907812,0.0001980328,0.00002848704,0.00002895855],"category_scores_gemma":[0.00002507873,0.00005133367,0.00009679975,0.00005554096,0.00006574966,5.730087e-7,0.0001729519,0.0001130557,4.914511e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002051224,"about_ca_system_score_gemma":0.000117085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004526351,"about_ca_topic_score_gemma":8.566634e-7,"domain_scores_codex":[0.99936,0.0001122035,0.0002300966,0.00008912312,0.00009554899,0.0001130891],"domain_scores_gemma":[0.9995255,0.00005651665,0.000236289,0.00006338918,0.00009500037,0.00002328996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002985275,0.00008428593,0.05521445,0.000005229451,0.0004371558,0.00001101316,0.0002520388,0.5590379,0.3785272,0.001309352,0.001527848,0.003295009],"study_design_scores_gemma":[0.00645211,0.006916129,0.3707907,0.00002522583,0.0003124595,0.008692752,0.005675012,0.0295874,0.02302833,0.1328707,0.4142202,0.001428926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881896,0.001273367,0.009517708,0.0004977828,0.0003701999,0.00004210133,0.00001726812,5.641228e-7,0.00009138406],"genre_scores_gemma":[0.9970382,0.00002642138,0.002228852,0.0003599593,0.0003042732,0.000001914564,0.000009217782,0.000006738261,0.0000244507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5294505,"threshold_uncertainty_score":0.2093326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605860066026066,"score_gpt":0.2836659147171742,"score_spread":0.2576073140569136,"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."}}