{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001004629,0.001352344,0.001308191,0.002906377,0.000944094,0.002219263,0.003809626,0.001284265,0.007605297],"category_scores_gemma":[0.004978333,0.0008977623,0.001011641,0.004646724,0.0006578179,0.004699465,0.003307628,0.001437174,0.005265588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095594,"about_ca_system_score_gemma":0.002017471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004233935,"about_ca_topic_score_gemma":0.004804615,"domain_scores_codex":[0.998922,0.0000811578,0.0001212177,0.0002662745,0.000480151,0.0001292039],"domain_scores_gemma":[0.9984219,0.0004122978,0.0001730009,0.0004290632,0.0004069481,0.0001567331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002409132,0.0003120355,0.005571062,0.001537518,0.0002824078,0.0005263716,0.0007290512,0.01314323,0.1183271,0.01722474,0.1962526,0.6436847],"study_design_scores_gemma":[0.001003963,0.001005647,0.00718869,0.0002324631,0.0002641859,0.00121857,0.0004553551,0.4384815,0.2212953,0.03193435,0.2963873,0.000532751],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.06292057,0.006652065,0.5964432,0.001202934,0.0008954,0.0007466283,0.03500747,0.2812864,0.01484532],"genre_scores_gemma":[0.1783708,0.002041885,0.6873871,0.000937088,0.000414724,0.001098413,0.1069285,0.00983787,0.01298368],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.007605297,"threshold_uncertainty_score":0.02544218,"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."}}