{"id":"W3164362182","doi":"10.1101/2021.05.22.445262","title":"Theory of local k-mer selection with applications to long-read alignment","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Division of Mathematical Sciences; University of Toronto","keywords":"Selection (genetic algorithm); Computer science; Task (project management); Computation; Variety (cybernetics); Metric (unit); Sliding window protocol; Upper and lower bounds; String (physics); Window (computing); Theoretical computer science; Mathematics; Algorithm; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.00675134,0.0009043257,0.001640802,0.003057716,0.001548435,0.002453334,0.002878835,0.001806839,0.009180482],"category_scores_gemma":[0.03727464,0.0008592739,0.001605528,0.002668888,0.003228367,0.005412943,0.003037242,0.003419217,0.001821304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002952631,"about_ca_system_score_gemma":0.00175502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001736266,"about_ca_topic_score_gemma":0.001642386,"domain_scores_codex":[0.995398,0.002029695,0.0002354445,0.0006465134,0.001443986,0.0002464005],"domain_scores_gemma":[0.9625338,0.03017241,0.001699751,0.001800105,0.003125505,0.0006683767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005426311,0.0000587574,0.001206561,0.0003909318,0.00003961109,0.00016665,0.0002649774,0.1488833,0.001525444,0.8112058,0.004241934,0.03196177],"study_design_scores_gemma":[0.00001043849,0.00002747287,0.0002267415,0.00006033726,0.000009432117,0.00007296827,0.00003446245,0.6128464,0.0007202459,0.3831439,0.002826632,0.00002087612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008425785,0.0009278471,0.9839053,0.000567151,0.00007630676,0.00005255963,0.00008055435,0.0003441907,0.005620303],"genre_scores_gemma":[0.3902824,0.002482937,0.5885293,0.001259692,0.0009503716,0.001054222,0.0006394376,0.001475861,0.01332582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009180482,"threshold_uncertainty_score":0.03570497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009237429156380655,"score_gpt":0.2143180730044064,"score_spread":0.2050806438480257,"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."}}