{"id":"W4409027996","doi":"10.1101/2025.03.26.645543","title":"Columba: Fast Approximate Pattern Matching with Optimized Search Schemes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Matching (statistics); Computer science; Mathematics; Algorithm; Pattern recognition (psychology); Artificial intelligence; Statistics","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":[0.001450461,0.001059989,0.0009962227,0.001901126,0.0008391421,0.001995525,0.003269772,0.001697612,0.01576217],"category_scores_gemma":[0.007850911,0.0006898768,0.0008084733,0.003640336,0.0006135534,0.002619913,0.002446783,0.001462171,0.006905384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001204978,"about_ca_system_score_gemma":0.002083754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004362778,"about_ca_topic_score_gemma":0.005946721,"domain_scores_codex":[0.9986304,0.0003352374,0.00009593627,0.0002300106,0.0005973307,0.0001110154],"domain_scores_gemma":[0.9984735,0.0006130458,0.0001252156,0.0004863013,0.0002378995,0.00006405604],"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":[0.001702921,0.0003330362,0.001369732,0.0006121312,0.0001834198,0.0002283931,0.0001773571,0.121051,0.03262365,0.04611204,0.07476433,0.7208419],"study_design_scores_gemma":[0.0002622216,0.0001122482,0.000409751,0.00002811801,0.00001748095,0.0001613847,0.00004362814,0.932743,0.01285189,0.03319884,0.02012759,0.00004390311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008062704,0.0003741975,0.9668951,0.0001541014,0.0001083621,0.0001403607,0.0008787301,0.02118646,0.002199973],"genre_scores_gemma":[0.08080186,0.0001621402,0.9092447,0.0001858708,0.00004180688,0.000512989,0.00311371,0.001844804,0.004092121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01576217,"threshold_uncertainty_score":0.05272973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01330848710619312,"score_gpt":0.2282395577281046,"score_spread":0.2149310706219115,"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."}}