{"id":"W2110015277","doi":"10.1145/1645953.1646134","title":"Suffix trees for very large genomic sequences","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Generalized suffix tree; Suffix tree; Compressed suffix array; Suffix; Computer science; String (physics); Theoretical computer science; Data structure; String searching algorithm; Suffix array; Tree (set theory); Algorithm; Mathematics; Programming language; Combinatorics","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":[0.0001265152,0.00007111196,0.00008310041,0.00003537479,0.0001162388,0.0001170343,0.0005862064,0.00002848146,0.0000243561],"category_scores_gemma":[0.000005604792,0.0000517728,0.00004166959,0.00008006349,0.000008159045,0.0004694421,0.00009733815,0.00003190391,0.00003504544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001288331,"about_ca_system_score_gemma":0.00003163555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000011552,"about_ca_topic_score_gemma":0.00001035406,"domain_scores_codex":[0.99936,0.00001014882,0.0001015815,0.0002289792,0.00009342883,0.0002058896],"domain_scores_gemma":[0.9995493,0.00003326519,0.00002815998,0.0003141428,0.00002484452,0.00005026134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001660756,0.0002283081,0.0003147954,0.00000748921,0.00001288295,0.00001381524,0.000568027,0.00008601417,0.01430558,0.6833731,0.05742585,0.2436476],"study_design_scores_gemma":[0.001425261,0.0007813713,0.02523526,0.00003046931,0.000006698827,0.00002371497,0.0001141118,0.344996,0.006339306,0.1370507,0.483353,0.0006440725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01520616,0.0001678469,0.9804881,0.00102097,0.0002121756,0.0001069431,0.00001119827,0.0001410918,0.002645573],"genre_scores_gemma":[0.5559952,0.00002723265,0.4408241,0.001727483,0.0002059599,0.000009071863,0.00001775406,0.000004233915,0.00118891],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5463223,"threshold_uncertainty_score":0.2111234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0171675373083366,"score_gpt":0.2631299366913453,"score_spread":0.2459623993830087,"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."}}