{"id":"W4417091474","doi":"10.1093/bioinformatics/btaf652","title":"Columba: fast approximate pattern matching with optimized search schemes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Source code; Scripting language; Code (set theory); Pattern matching; Matching (statistics); Software; Pattern recognition (psychology)","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":[0.0002451621,0.0001555748,0.0002063835,0.0001492152,0.0001684031,0.0003568269,0.000730394,0.0000567757,0.000005079428],"category_scores_gemma":[0.00001817532,0.0001241037,0.00004430586,0.0005547326,0.00006315912,0.001181103,0.0004293901,0.0001882547,0.00002413656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004844762,"about_ca_system_score_gemma":0.0001038573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009093069,"about_ca_topic_score_gemma":0.000001115781,"domain_scores_codex":[0.9989116,0.00001922885,0.0003106269,0.0001615399,0.0002760227,0.0003210334],"domain_scores_gemma":[0.9991215,0.00005926448,0.00009124709,0.000539357,0.0001268684,0.00006177585],"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":[0.00003188338,0.00007829222,0.0003652256,0.0004897957,0.00006893896,0.00001719386,0.001743936,0.0002975222,0.0002258465,0.01459013,0.001732034,0.9803592],"study_design_scores_gemma":[0.00198761,0.0002786921,0.0002886483,0.00074739,0.00002519249,0.00003688046,0.0009633854,0.8968996,0.08311851,0.004460559,0.01044665,0.0007468654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009671089,0.00006972032,0.9885221,0.0002518921,0.00005729764,0.0003128563,0.00000388663,0.0004875425,0.00932764],"genre_scores_gemma":[0.02485247,0.0000893968,0.9733523,0.001077421,0.00001315232,0.00002327768,0.000006039847,0.000008915259,0.0005770755],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9796124,"threshold_uncertainty_score":0.5060801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01377287271257562,"score_gpt":0.2763447204906703,"score_spread":0.2625718477780947,"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."}}