{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007563462,0.0007114887,0.0007945271,0.0003653903,0.0004092406,0.001427792,0.00297173,0.0004331142,0.0000223264],"category_scores_gemma":[0.00002948063,0.0006654518,0.0001456692,0.0007693598,0.0001195656,0.0006518525,0.004925732,0.001267447,0.00003984593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171307,"about_ca_system_score_gemma":0.001022731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001994002,"about_ca_topic_score_gemma":0.000002175644,"domain_scores_codex":[0.9956837,0.0002155295,0.0005659679,0.001831255,0.0008445008,0.0008589909],"domain_scores_gemma":[0.995599,0.00009839061,0.0003595058,0.003046924,0.0005659807,0.0003302484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001586696,0.01000246,0.04445208,0.03526565,0.01022824,0.007633321,0.001922068,0.09213351,0.6827989,0.08242183,0.02262204,0.008933182],"study_design_scores_gemma":[0.005617262,0.0002794614,0.018898,0.009444095,0.000279691,2.452698e-7,0.00002558986,0.7738805,0.1762659,0.0000378625,0.009753321,0.005518074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04514053,0.0005987689,0.9508958,0.0002880526,0.0008909442,0.0008773953,0.0003061559,0.0009594721,0.00004290497],"genre_scores_gemma":[0.4274959,0.0002635221,0.5708613,0.0005383907,0.0003418737,0.0003557186,0.000001753252,0.0001042309,0.00003736318],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.681747,"threshold_uncertainty_score":0.9996088,"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."}}