{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008238903,0.0009127537,0.001334885,0.002033839,0.0007602844,0.001885456,0.002324507,0.001281215,0.01009049],"category_scores_gemma":[0.004762298,0.0004553218,0.0005470302,0.003748407,0.0008031566,0.003809872,0.002838697,0.00132125,0.003816392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002544,"about_ca_system_score_gemma":0.001754843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004325115,"about_ca_topic_score_gemma":0.006026074,"domain_scores_codex":[0.9983155,0.000190809,0.0001054578,0.0002429266,0.001003768,0.0001417098],"domain_scores_gemma":[0.9981266,0.0005683344,0.0001372322,0.0008047795,0.0002666172,0.00009647804],"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":[0.002401195,0.000405582,0.001215546,0.000344658,0.0001146744,0.0002615958,0.0002456092,0.02094474,0.04916499,0.0213691,0.0370169,0.8665154],"study_design_scores_gemma":[0.0006434669,0.0007815898,0.001213308,0.00009418134,0.0001030101,0.0008240368,0.0002398427,0.8258129,0.0992273,0.04125671,0.02972167,0.00008197551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07022029,0.00212493,0.8965843,0.0008293451,0.0005850582,0.0003669252,0.001447288,0.01928804,0.008553819],"genre_scores_gemma":[0.259731,0.0005429863,0.7211235,0.0005575548,0.0002584526,0.0004053798,0.002608318,0.001166127,0.01360661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01009049,"threshold_uncertainty_score":0.03375608,"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."}}