{"id":"W4404492911","doi":"10.21203/rs.3.rs-5367343/v1","title":"b-move: Faster Lossless Approximate Pattern Matching in a Run-Length Compressed Index","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Lossless compression; Index (typography); Computer science; Matching (statistics); Algorithm; Mathematics; Data compression; Statistics; World Wide Web","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":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002374346,0.0005296316,0.0006547155,0.001217555,0.0002407597,0.002363638,0.004161873,0.0005218558,0.00007525517],"category_scores_gemma":[0.00005749091,0.0004574906,0.0001955268,0.0009644422,0.000139601,0.0004708346,0.02636524,0.005114038,0.0003406431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003446664,"about_ca_system_score_gemma":0.0004907376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002085041,"about_ca_topic_score_gemma":0.0001320896,"domain_scores_codex":[0.9929366,0.000814977,0.0006865666,0.001930012,0.002309558,0.001322258],"domain_scores_gemma":[0.996164,0.0004176808,0.0001382501,0.002636263,0.0003269736,0.0003168233],"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":[0.0001592835,0.001719765,0.008485258,0.02066563,0.0002984511,0.005507054,0.01919777,0.01390459,0.0006851327,0.01714936,0.01545096,0.8967767],"study_design_scores_gemma":[0.0006547215,0.00006881598,0.008881366,0.006349986,0.000005511284,0.00002000501,0.0003508972,0.9017795,0.0002059113,0.07863951,0.002307007,0.0007367603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08334523,0.003317098,0.9020515,0.002357355,0.001888092,0.002536521,0.0004904721,0.0006998683,0.003313828],"genre_scores_gemma":[0.9937952,0.00021154,0.004455624,0.00009266921,0.0003970252,0.0003867957,0.0001683319,0.00008421745,0.000408595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.91045,"threshold_uncertainty_score":0.9997877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05159588203190445,"score_gpt":0.3708995698269282,"score_spread":0.3193036877950237,"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."}}