{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001780889,0.001844539,0.001255846,0.001862144,0.001392989,0.003155981,0.003584224,0.001738057,0.01728177],"category_scores_gemma":[0.01436522,0.001027233,0.00216477,0.004011465,0.001853881,0.007152023,0.003688745,0.003067267,0.009984573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001745207,"about_ca_system_score_gemma":0.002890249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003220786,"about_ca_topic_score_gemma":0.005038599,"domain_scores_codex":[0.9970151,0.0005399756,0.0003185401,0.0006978108,0.001064054,0.0003644766],"domain_scores_gemma":[0.9928617,0.003483667,0.0003384911,0.002098202,0.001023226,0.0001946912],"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":[0.0008295198,0.0003069293,0.00280438,0.001519866,0.0001537142,0.001036365,0.001150413,0.06050245,0.04909511,0.1420643,0.06646577,0.6740711],"study_design_scores_gemma":[0.0001947209,0.0002182991,0.0006904469,0.0002529784,0.0001368133,0.0006891423,0.0003663241,0.481085,0.09915515,0.3408683,0.07620616,0.0001366853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01255685,0.0004347214,0.9356717,0.0003063768,0.0001622463,0.0001696793,0.00166874,0.04351996,0.005509638],"genre_scores_gemma":[0.09915007,0.0002509412,0.8811806,0.0002782175,0.00007967547,0.0002947856,0.006384541,0.007871495,0.004509639],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01728177,"threshold_uncertainty_score":0.05781329,"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."}}