{"id":"W4243450674","doi":"10.1093/bioinformatics/btab790","title":"Theory of local k-mer selection with applications to long-read alignment","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; Algorithm; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00006898148,0.00007730026,0.00008572179,0.00001795179,0.00005396911,0.00000746932,0.00006327622,0.00004277161,0.00001183832],"category_scores_gemma":[0.000006343145,0.0000645932,0.00003051095,0.00008263542,0.00004712179,5.970225e-7,0.00006607728,0.00002139428,0.00001045228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009120446,"about_ca_system_score_gemma":0.00006766788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002000958,"about_ca_topic_score_gemma":0.00001901472,"domain_scores_codex":[0.9995534,0.0000107556,0.0001617329,0.00008895498,0.00007785579,0.0001072847],"domain_scores_gemma":[0.9995849,0.000006895857,0.00005488045,0.0001832826,0.000125538,0.00004456177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004563838,0.000667767,0.02167123,0.0005736872,0.00144444,0.000003513492,0.002037648,0.0155182,0.6579995,0.02678574,0.005454761,0.2673872],"study_design_scores_gemma":[0.0006269164,0.0006582594,0.01414254,0.00002708715,0.00009149517,0.00005099549,0.001610524,0.0003449223,0.9048313,0.0004042637,0.07685609,0.0003555982],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2834543,0.0003484391,0.7125371,0.00008350288,0.00003584876,0.0002385781,0.00002970255,0.000003415045,0.003269158],"genre_scores_gemma":[0.9692147,0.00008286848,0.02965179,0.0002975857,0.00005527832,0.00005000627,0.00004657578,0.00000908301,0.0005921365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6857604,"threshold_uncertainty_score":0.2634034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009314820077001981,"score_gpt":0.228510763946307,"score_spread":0.219195943869305,"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."}}