{"id":"W2053743126","doi":"10.1006/jcss.2002.1823","title":"Finding Similar Regions in Many Sequences","year":2002,"lang":"en","type":"article","venue":"Journal of Computer and System Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Combinatorics; Polynomial-time approximation scheme; Mathematics; Hamming distance; Core (optical fiber); Sequence (biology); Time complexity; Approximation algorithm; Discrete mathematics; Entropy (arrow of time); Computer science; Biology; Physics; Genetics","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":[0.00100544,0.00009388738,0.0002293818,0.0003071947,0.0002220575,0.0003910535,0.0009454823,0.00003336961,0.000003468197],"category_scores_gemma":[0.000007749937,0.00006176317,0.00004955903,0.0004754137,0.00009724248,0.001297873,0.0001929477,0.0001204542,0.000003674039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002720152,"about_ca_system_score_gemma":0.00003044511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001206312,"about_ca_topic_score_gemma":0.000001870663,"domain_scores_codex":[0.9986388,0.0001060128,0.000424402,0.0002042578,0.0004291128,0.0001974216],"domain_scores_gemma":[0.9992965,0.0001297799,0.0002678615,0.0001488941,0.00005914202,0.00009775546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001646541,0.000426395,0.03478491,0.0003759205,0.00007929279,0.002553932,0.01795238,0.01424464,0.0007225266,0.4983366,0.03474648,0.3957605],"study_design_scores_gemma":[0.0003020554,0.000286341,0.003311555,0.0005415668,0.000003225205,0.001450887,0.0003683663,0.9904628,0.00004199517,0.001114239,0.001974275,0.0001426919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0752771,0.002346128,0.9178856,0.001423304,0.0012951,0.00007380483,9.20997e-7,0.00002848768,0.001669582],"genre_scores_gemma":[0.923916,0.0001111568,0.07567155,0.00008653112,0.0001875221,5.440299e-7,4.051169e-8,0.000001711252,0.0000249929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9762182,"threshold_uncertainty_score":0.3770938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05043055801681404,"score_gpt":0.2647240296950133,"score_spread":0.2142934716781993,"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."}}