{"id":"W2136711891","doi":"10.1109/cibcb.2010.5510426","title":"Nearest neighbor training of side effect machines for sequence classification","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Rand index; Support vector machine; Feature (linguistics); k-nearest neighbors algorithm; Machine learning; Pattern recognition (psychology); Algorithm; Cluster analysis","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":[0.0002882308,0.00009715856,0.0001082216,0.00002553987,0.00004744988,0.00001439733,0.0001565021,0.0001165828,0.00002214238],"category_scores_gemma":[0.0006237308,0.00007787296,0.00006565699,0.00004152356,0.0000675843,0.000003672977,0.00003135971,0.0001039886,0.000003736172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002365982,"about_ca_system_score_gemma":0.00004110994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000158423,"about_ca_topic_score_gemma":0.00005444098,"domain_scores_codex":[0.999451,0.00002153875,0.0001933821,0.0001320749,0.00007014017,0.0001317935],"domain_scores_gemma":[0.9994591,0.0000589613,0.0001148007,0.000260603,0.00006673051,0.0000397746],"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":[0.00003724398,0.000008425355,0.005819222,0.00005948805,0.00001282386,5.483695e-8,0.00005991527,0.00004008074,0.9696713,0.001972411,0.0002070677,0.02211193],"study_design_scores_gemma":[0.001242691,0.001091341,0.02515564,0.00002091594,0.00004036712,0.00003152364,0.00008723692,0.1184126,0.8179713,0.0003306831,0.0352308,0.0003849209],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9695211,0.00001228474,0.01754471,0.0001761585,0.0001827429,0.0002801632,0.00002035905,0.00002158253,0.01224091],"genre_scores_gemma":[0.9719619,0.000002720798,0.02719352,0.0001039798,0.0001310456,0.00002699437,0.0001633462,0.00001353696,0.0004030054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1517,"threshold_uncertainty_score":0.3175567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02344163874877428,"score_gpt":0.3139397900067358,"score_spread":0.2904981512579615,"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."}}