{"id":"W4402467995","doi":"10.1016/j.isci.2024.110933","title":"Building a pangenome alignment index via recursive prefix-free parsing","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; Directorate for Biological Sciences; National Science Foundation; National Institutes of Health; Seattle Children’s Hospital; Seattle Children's Research Institute","keywords":"Prefix; Index (typography); Parsing; Computer science; Natural language processing; Linguistics; Programming language; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001179632,0.0009505035,0.001181938,0.004120539,0.00103659,0.00216188,0.001959065,0.001005444,0.004842274],"category_scores_gemma":[0.00622343,0.0007774846,0.001027956,0.006481747,0.0006471314,0.003940688,0.003001592,0.001653944,0.004350504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007773442,"about_ca_system_score_gemma":0.00230538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002269843,"about_ca_topic_score_gemma":0.003981665,"domain_scores_codex":[0.9988474,0.0001330536,0.000198145,0.0003481277,0.0003589869,0.0001142701],"domain_scores_gemma":[0.9978784,0.0005654395,0.0001359637,0.0006708027,0.0006616861,0.00008771979],"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":[0.000442783,0.0001758471,0.003733697,0.0004330892,0.0001172735,0.0003825467,0.000529997,0.02637286,0.06030399,0.03712685,0.03316154,0.8372195],"study_design_scores_gemma":[0.0001476598,0.0002852599,0.003710539,0.0001258097,0.0001575897,0.0008989645,0.0003673915,0.6544997,0.1222469,0.1051986,0.1121686,0.0001931166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01555334,0.0003983572,0.9583086,0.0001940873,0.0001134018,0.0001537349,0.002770058,0.01972238,0.002785993],"genre_scores_gemma":[0.04199411,0.000278149,0.9418151,0.0001344584,0.00006176326,0.0002789446,0.01191275,0.00159371,0.001931073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004842274,"threshold_uncertainty_score":0.01619905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01755946177133917,"score_gpt":0.2691087212566652,"score_spread":0.2515492594853261,"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."}}