{"id":"W4317600672","doi":"10.1101/2023.01.18.524557","title":"Recursive Prefix-Free Parsing for Building Big BWTs","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Israel Institute for Biological Research; National Institutes of Health; National Science Foundation","keywords":"Prefix; Parsing; Computer science; Arithmetic; Artificial intelligence; Mathematics; Linguistics; Philosophy","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":[0.001051312,0.0006904806,0.0006991593,0.0004719892,0.0004793234,0.0009579602,0.004062057,0.0006011067,0.000003078],"category_scores_gemma":[0.0007171226,0.0007260699,0.0002718077,0.000809429,0.00008861066,0.0005358729,0.005262776,0.0007794751,0.00005012831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003170204,"about_ca_system_score_gemma":0.000685697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006970803,"about_ca_topic_score_gemma":0.00000228665,"domain_scores_codex":[0.995517,0.0001337558,0.0006847673,0.002030393,0.0006478118,0.0009862516],"domain_scores_gemma":[0.9939013,0.0003151858,0.0006215178,0.004139598,0.0006464035,0.0003760099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002374679,0.001385062,0.002456998,0.00489696,0.001458476,0.0007127331,0.0002891154,0.003034167,0.7318776,0.1557986,0.09650612,0.001346678],"study_design_scores_gemma":[0.006351926,0.0006264455,0.03871962,0.01014814,0.0005018973,2.126583e-7,0.00001334396,0.1950956,0.5812026,0.004996134,0.1539142,0.008429893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03135777,0.00103107,0.9541947,0.0009595753,0.008594226,0.00137226,0.0006881754,0.001796514,0.00000575248],"genre_scores_gemma":[0.2496202,0.0003393387,0.7462295,0.0003397899,0.002381792,0.0007781941,0.000001894888,0.0002861011,0.0000232321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2182624,"threshold_uncertainty_score":0.9995191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03721075118758353,"score_gpt":0.2527261444949686,"score_spread":0.215515393307385,"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."}}