{"id":"W3026218946","doi":"10.1109/tit.2020.2996543","title":"Levenshtein Distance, Sequence Comparison and Biological Database Search","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Levenshtein distance; Edit distance; Nearest neighbor search; Heuristics; Computer science; Metric (unit); Similarity (geometry); Data mining; Smith–Waterman algorithm; Database; Theoretical computer science; Artificial intelligence; Sequence alignment; Biology","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":[0.0001342046,0.00009417493,0.00009086418,0.0000239066,0.0001345345,0.0000227201,0.00008430226,0.0000580942,0.00002228648],"category_scores_gemma":[0.00001070892,0.00008253601,0.00003418824,0.0000606361,0.0001111834,0.00000547633,0.000004582408,0.00009510548,0.00002971027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006081653,"about_ca_system_score_gemma":0.00002091923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002935303,"about_ca_topic_score_gemma":0.00000209458,"domain_scores_codex":[0.9994652,0.00005294595,0.0001734664,0.0001229909,0.00006993812,0.0001154819],"domain_scores_gemma":[0.9997007,0.00002440135,0.00003606262,0.0001229473,0.00004046987,0.00007547611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002092723,0.0001793066,0.001271824,0.0001730716,0.0003014513,0.000002329549,0.005465987,0.0194989,0.7712341,0.01016408,0.001536771,0.1880795],"study_design_scores_gemma":[0.00256633,0.002159754,0.002744848,0.00004055921,0.00006758585,0.00002706525,0.005347265,0.01266733,0.8740139,0.0009072214,0.09845048,0.001007646],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4254569,0.000131027,0.5732668,0.0001933938,0.00006961595,0.0001229881,0.0002416627,0.000008396717,0.0005092022],"genre_scores_gemma":[0.9979577,0.0003008432,0.0007530695,0.0008666877,0.00003025657,0.00001590546,0.00004359604,0.000004369047,0.00002754096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5725138,"threshold_uncertainty_score":0.3365721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04782399564894595,"score_gpt":0.2778887731993038,"score_spread":0.2300647775503578,"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."}}