{"id":"W4414453687","doi":"10.1007/978-3-032-05228-5_2","title":"KeBaB: k-mer Based Breaking for Finding Long MEMs","year":2025,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Substring; Microelectromechanical systems; Bloom filter; Filter (signal processing); Sequence (biology); Matching (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":[],"consensus_categories":[],"category_scores_codex":[0.000901477,0.0002058816,0.0002218096,0.0005510205,0.0005233032,0.0006613045,0.002483224,0.00008456397,0.000003843018],"category_scores_gemma":[0.0001773665,0.0001750981,0.00007254887,0.002252239,0.0001936942,0.0008633942,0.0009289567,0.0002138757,0.00000406073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283101,"about_ca_system_score_gemma":0.0003573012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004294393,"about_ca_topic_score_gemma":0.00002796484,"domain_scores_codex":[0.9977234,0.00003462625,0.0002834685,0.0009519545,0.0004097397,0.0005968096],"domain_scores_gemma":[0.9980396,0.0007470567,0.00009106751,0.0008976819,0.0001401976,0.00008438219],"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":[0.000006008491,0.00004661294,0.001642132,0.00003091983,0.000003348865,0.00001104762,0.0001918172,0.05855588,0.001393781,0.001650369,0.00007293418,0.9363952],"study_design_scores_gemma":[0.0004048223,0.00004589613,0.003519161,0.0001956297,0.000002494916,0.000005454999,2.478287e-7,0.9597448,0.02615171,0.00929328,0.0004289589,0.0002076098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003453069,0.000126277,0.9924392,0.001536682,0.001965544,0.0002987371,0.000003226458,0.0001415854,0.00003572655],"genre_scores_gemma":[0.5172762,9.132792e-7,0.4811785,0.001432944,0.00008732613,0.00001534684,0.000002457101,0.00000425891,0.000002055792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9361876,"threshold_uncertainty_score":0.7140294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01642489027189135,"score_gpt":0.2892989182554494,"score_spread":0.272874027983558,"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."}}