{"id":"W4394688386","doi":"10.1186/s13015-024-00260-8","title":"Pfp-fm: an accelerated FM-index","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; Japan Society for the Promotion of Science; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Computer science; Parsing; Suffix; Word (group theory); Sorting; Search engine indexing; Prefix; Character (mathematics); Suffix array; Index (typography); Algorithm; Artificial intelligence; Natural language processing; Data structure; Programming language; Mathematics","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":[0.0007467364,0.001884546,0.00111224,0.002542709,0.00110842,0.001911006,0.004775871,0.00132585,0.01801186],"category_scores_gemma":[0.004214151,0.000700842,0.001037828,0.003708819,0.0006339944,0.00365726,0.002469211,0.001331249,0.009234801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508729,"about_ca_system_score_gemma":0.002125485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009960888,"about_ca_topic_score_gemma":0.006124523,"domain_scores_codex":[0.9986899,0.0001147635,0.0001061981,0.0003306895,0.0005958313,0.0001625052],"domain_scores_gemma":[0.9984372,0.0004080711,0.0001025306,0.000507244,0.0004195519,0.0001254504],"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":[0.001409681,0.0003240217,0.002600748,0.0006118346,0.00009986639,0.0002889796,0.000200546,0.01837159,0.03265528,0.01045105,0.1692707,0.7637158],"study_design_scores_gemma":[0.0005596659,0.0004323654,0.002400146,0.00009914806,0.00007761067,0.0007405545,0.0001321323,0.7682129,0.07048935,0.01888274,0.1377982,0.0001750969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03900819,0.002215725,0.73498,0.0007430591,0.0008491033,0.0005293011,0.006515872,0.2014747,0.01368396],"genre_scores_gemma":[0.1197426,0.0003836676,0.8451272,0.0004049069,0.0002692019,0.0005004718,0.01499586,0.005804365,0.01277166],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01801186,"threshold_uncertainty_score":0.06025571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03292274683587503,"score_gpt":0.3461846779970787,"score_spread":0.3132619311612037,"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."}}