{"id":"W2951332226","doi":"10.1089/cmb.2019.0309","title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","year":2020,"lang":"en","type":"preprint","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"String (physics); Search engine indexing; Computer science; Rank (graph theory); Sample (material); Suffix array; Compressed suffix array; Index (typography); Data structure; Suffix; Database index; Space (punctuation); Data mining; String searching algorithm; Information retrieval; Mathematics; Combinatorics; World Wide Web; Programming language","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":[0.0004099432,0.0001898237,0.0005894258,0.0002185389,0.00006415186,0.00004416715,0.000893979,0.000182299,0.000006039854],"category_scores_gemma":[0.00007263859,0.0001609277,0.0002540969,0.0001052823,0.00012363,0.00004459942,0.000815367,0.0003308313,0.000001959521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109841,"about_ca_system_score_gemma":0.0005782596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008897316,"about_ca_topic_score_gemma":2.857675e-7,"domain_scores_codex":[0.998095,0.0001300332,0.001011478,0.0003162281,0.0002862056,0.0001610841],"domain_scores_gemma":[0.9966672,0.0004430857,0.001864653,0.0002252248,0.0007037093,0.00009609471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002491028,0.0001957695,0.0002396968,0.0001585344,0.0003492632,0.0000105362,0.0003955043,0.8359571,0.002740053,0.09897394,0.001141668,0.05958888],"study_design_scores_gemma":[0.000872482,0.0004621941,0.001354984,0.0001096667,0.00003080803,0.0001334781,0.00002229191,0.7542195,0.0002262514,0.237359,0.005036272,0.0001730265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02286416,0.000278342,0.9728288,0.001629929,0.001796942,0.0002567695,0.0003022651,0.00001366319,0.00002913875],"genre_scores_gemma":[0.4147854,0.00002610483,0.5845633,0.0001729304,0.0003181582,0.000005413329,0.0001195476,0.000007717017,0.000001431823],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3919213,"threshold_uncertainty_score":0.6562443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03835700790850998,"score_gpt":0.2969671167264644,"score_spread":0.2586101088179544,"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."}}