{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001449623,0.001679807,0.001421009,0.001717328,0.001035396,0.002338187,0.004143228,0.002196332,0.02432562],"category_scores_gemma":[0.009484234,0.0009832423,0.001239354,0.003309038,0.0007378377,0.003229508,0.002595984,0.001822848,0.01248905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001278658,"about_ca_system_score_gemma":0.00269708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005464992,"about_ca_topic_score_gemma":0.007940398,"domain_scores_codex":[0.9983797,0.0003578711,0.0001024706,0.0003073798,0.0007050952,0.0001475444],"domain_scores_gemma":[0.9984029,0.0007258902,0.0001167175,0.0004101062,0.0002692452,0.00007510666],"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":[0.002049392,0.0003807997,0.002335333,0.001559153,0.0003079471,0.0003579886,0.0002247091,0.1742519,0.02776851,0.04098973,0.1689974,0.5807771],"study_design_scores_gemma":[0.0003800506,0.0001309549,0.0004611226,0.0000509677,0.00003299458,0.0002041802,0.00005237079,0.9162865,0.009420016,0.03975676,0.03316351,0.00006060489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01078643,0.001012332,0.9079888,0.0003232127,0.0002359203,0.0002782634,0.003268611,0.07045916,0.005647215],"genre_scores_gemma":[0.07584622,0.0003182024,0.901891,0.0003528383,0.00006330966,0.0007846644,0.009621361,0.005758751,0.005363635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02432562,"threshold_uncertainty_score":0.08137727,"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."}}