{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002998787,0.0002633124,0.0002581444,0.0001980014,0.000160997,0.0003177271,0.001196043,0.0002407309,0.00003027151],"category_scores_gemma":[0.00002860847,0.0002188283,0.0001403865,0.0004549777,0.00007733663,0.0005114854,0.000421973,0.0002039774,0.00006972239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003627774,"about_ca_system_score_gemma":0.00009874009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008096312,"about_ca_topic_score_gemma":0.000004188752,"domain_scores_codex":[0.9979634,0.0001040902,0.0002941134,0.0009536455,0.0001444934,0.0005403075],"domain_scores_gemma":[0.9987318,0.00008426166,0.0000518121,0.0008329992,0.0001216507,0.0001774636],"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":[0.00001375033,0.00009527356,0.00002825383,0.00002783705,0.00009939959,0.0001585695,0.0001171763,0.00006926236,0.05079982,0.110462,0.001380804,0.8367479],"study_design_scores_gemma":[0.0004175065,0.000551815,0.00007233661,0.00001981662,0.00001653129,0.00008594305,0.0000106398,0.8494522,0.01959071,0.05195629,0.07741966,0.0004065693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00401137,0.001380998,0.9911991,0.0006012869,0.001621322,0.0003349026,0.00008475711,0.0005311192,0.0002350847],"genre_scores_gemma":[0.573393,0.00006755796,0.4230097,0.001529299,0.0006609395,0.0001206377,0.0008620291,0.00008601262,0.0002707244],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493829,"threshold_uncertainty_score":0.8923558,"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."}}