{"id":"W4388399378","doi":"10.1101/2023.11.04.565615","title":"Movi: a fast and cache-efficient full-text pangenome index","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University; National Institutes of Health; National Science Foundation","keywords":"Cache; Computer science; Index (typography); Matching (statistics); Nanopore sequencing; Algorithm; Locality; Latency (audio); Interval (graph theory); Parallel computing; Mathematics; Statistics; Combinatorics; DNA sequencing; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006881211,0.0006432162,0.0005995707,0.0004461956,0.000322152,0.0008570401,0.001888031,0.0005116155,0.00001489687],"category_scores_gemma":[0.00009263693,0.0006316745,0.0001280336,0.000800758,0.0001342584,0.0002675531,0.005451764,0.000841527,0.000202524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001883749,"about_ca_system_score_gemma":0.0004597422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001562976,"about_ca_topic_score_gemma":0.000003955381,"domain_scores_codex":[0.996062,0.0001365139,0.0005492988,0.001819767,0.0006665658,0.0007658055],"domain_scores_gemma":[0.9962224,0.00009360582,0.0003868419,0.002520259,0.0003121071,0.0004647902],"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":[0.0001934638,0.00233161,0.0192197,0.00388568,0.00151689,0.00368459,0.0008690616,0.02513314,0.8956326,0.03409134,0.01183051,0.001611376],"study_design_scores_gemma":[0.001376372,0.0001833282,0.3002615,0.001180936,0.0001122135,3.370704e-7,0.00001393244,0.666823,0.01128536,0.0000391225,0.01551008,0.003213814],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3460018,0.002515116,0.6442184,0.0006594812,0.003366027,0.0009966105,0.0004281361,0.001802582,0.00001189755],"genre_scores_gemma":[0.9727803,0.000299344,0.02593302,0.0001748223,0.0004902288,0.0001842605,7.036098e-7,0.0001176885,0.00001961998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8843473,"threshold_uncertainty_score":0.9996135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01870896721342896,"score_gpt":0.2211760750693889,"score_spread":0.2024671078559599,"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."}}