{"id":"W4413110219","doi":"10.1186/s13015-025-00281-x","title":"b-move: faster lossless approximate pattern matching in a run-length compressed index","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institutes of Health; National Human Genome Research Institute; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Search engine indexing; Lossless compression; Index (typography); RefSeq; Memory footprint; Pattern matching; Scalability; Matching (statistics); Overhead (engineering); Theoretical computer science; Data mining; Genome; Algorithm; Data compression; Information retrieval; Mathematics; Artificial intelligence; Database","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003410973,0.0003065774,0.0004346793,0.0003348143,0.0001317546,0.0001362453,0.001382478,0.0002470367,0.000006241036],"category_scores_gemma":[0.00002521777,0.0002763464,0.0001303417,0.0004290625,0.00008400528,0.000247281,0.0009954813,0.0002764137,0.000008537359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000052616,"about_ca_system_score_gemma":0.00007818412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002742516,"about_ca_topic_score_gemma":0.0000176527,"domain_scores_codex":[0.9977434,0.0001523656,0.0004660756,0.0008649936,0.0001407543,0.0006324051],"domain_scores_gemma":[0.9986802,0.0001467182,0.0001327214,0.0008682613,0.00008966406,0.00008245144],"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":[0.0000603039,0.0004292211,0.002707984,0.0001725552,0.0001653884,0.0001295507,0.000471504,0.0007825762,0.01983031,0.06669345,0.0004152675,0.9081419],"study_design_scores_gemma":[0.003324723,0.0001633112,0.003180438,0.000183751,0.00001877577,0.00002300291,0.00006689037,0.8855392,0.0103363,0.08923618,0.007263219,0.0006642254],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01212475,0.0004305852,0.9850541,0.0006373432,0.0007179197,0.0005822739,0.00005941793,0.000123756,0.0002698963],"genre_scores_gemma":[0.8565545,0.00003164659,0.1402106,0.002471876,0.00008137805,0.0003016635,0.0001926424,0.00003489555,0.0001208013],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9074777,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01169109429062735,"score_gpt":0.2933725954004427,"score_spread":0.2816815011098153,"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."}}