{"id":"W4401034109","doi":"10.1007/978-3-031-66159-4_10","title":"How to Find Long Maximal Exact Matches and Ignore Short Ones","year":2024,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Human Genome Research Institute; Università degli Studi di Milano-Bicocca","keywords":"Computer science; Algorithm; Theoretical computer science","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005087477,0.000228056,0.000199878,0.0003995356,0.0002125069,0.002700519,0.001555986,0.00007197723,0.000003461078],"category_scores_gemma":[0.00006003302,0.0001749767,0.00003648282,0.001662525,0.0002034346,0.001630599,0.001673303,0.0002596018,0.00001132866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006385014,"about_ca_system_score_gemma":0.0001364201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003632265,"about_ca_topic_score_gemma":0.00003464328,"domain_scores_codex":[0.9976283,0.00003280062,0.0001720472,0.00112281,0.0005365245,0.0005075718],"domain_scores_gemma":[0.9987753,0.0002614124,0.00001977099,0.0006833866,0.000059261,0.0002008769],"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":[0.000002185401,0.0000171234,0.001410478,0.00002690767,0.00000283799,0.0001319209,0.0009239117,0.002580279,0.001786472,0.0004458117,0.00006263482,0.9926094],"study_design_scores_gemma":[0.00007006909,0.0001417293,0.02698298,0.0002359415,0.000002612689,0.0001659639,0.00000160971,0.9565374,0.008040637,0.006819048,0.0006559615,0.0003459918],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07488401,0.0007000982,0.9190601,0.003916339,0.001084854,0.0001680814,0.000003758609,0.0001733325,0.00000949832],"genre_scores_gemma":[0.6540174,0.00001068188,0.3453573,0.0004119967,0.0001839492,0.000006145577,0.000001150908,0.000006677411,0.000004691771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9922634,"threshold_uncertainty_score":0.9983348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01619052697209217,"score_gpt":0.2570697544311087,"score_spread":0.2408792274590165,"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."}}