{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004318116,0.0001359602,0.0001107018,0.000139473,0.0002493865,0.0006400447,0.00196687,0.00004244601,0.00001439692],"category_scores_gemma":[0.0000367055,0.0001094714,0.0000471781,0.0007884683,0.00009672128,0.001401749,0.001339481,0.0001332208,0.00006403722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001098021,"about_ca_system_score_gemma":0.0001000557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005910589,"about_ca_topic_score_gemma":0.000002830427,"domain_scores_codex":[0.9981422,0.00003698847,0.0001780281,0.000687864,0.0005550766,0.0003997711],"domain_scores_gemma":[0.9988407,0.00008210599,0.0000440741,0.0008604861,0.00003631767,0.0001363217],"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":[0.000003427188,0.00005589975,0.0001200501,0.00003687206,0.00001218998,0.0001711582,0.00218055,0.0005163013,0.02898553,0.09869143,0.005596186,0.8636304],"study_design_scores_gemma":[0.0002216274,0.0001615574,0.001976471,0.0004737081,0.000009445538,0.0001534342,0.00005363984,0.7312619,0.009570803,0.1384773,0.1170944,0.000545698],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006754923,0.002610154,0.9868971,0.001088227,0.00132655,0.000127946,0.000007953437,0.0002427566,0.000944401],"genre_scores_gemma":[0.7577823,0.00004750265,0.2413968,0.0003229237,0.0001936756,0.00002133912,0.000001449471,0.00001117679,0.0002227698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8630847,"threshold_uncertainty_score":0.6171966,"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."}}