{"id":"W2160877678","doi":"10.1109/cibcb.2008.4675755","title":"Classifying synthetic and biological DNA sequences with side effect machines","year":2008,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Computer science; Finite-state machine; Feature (linguistics); Artificial intelligence; Population; Algorithm; Set (abstract data type); State (computer science); Machine learning; Sequence (biology); Biological data; String (physics); Mathematics; Bioinformatics; Biology","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":[0.0009926698,0.0003226422,0.0004868423,0.0007164672,0.0002686739,0.0004961847,0.0004848803,0.0006408115,0.0007382101],"category_scores_gemma":[0.005016416,0.000162063,0.0003392262,0.0005878996,0.0004923654,0.0007300169,0.0002835885,0.0005822154,0.0002626732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004272824,"about_ca_system_score_gemma":0.0003131384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005472297,"about_ca_topic_score_gemma":0.0005948679,"domain_scores_codex":[0.9994888,0.0001490178,0.00005464454,0.000127323,0.0001434208,0.00003670645],"domain_scores_gemma":[0.9964228,0.002445228,0.0002623297,0.0003679512,0.0004347748,0.00006694465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009262371,0.0003410803,0.01265703,0.0002008057,0.00006972138,0.0003435003,0.0003165069,0.4692982,0.09460068,0.007258626,0.001363632,0.412624],"study_design_scores_gemma":[0.00000600782,0.0001157912,0.001323379,0.00000583915,0.000005001716,0.00007423179,0.00002190702,0.9716552,0.02330801,0.003105753,0.0003699553,0.000008877407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6412971,0.0002165002,0.3547416,0.0002238141,0.00007235824,0.0001394002,0.0002726232,0.00136968,0.00166697],"genre_scores_gemma":[0.8139074,0.00009079116,0.1843509,0.00005449359,0.00002285917,0.0001345879,0.0004958403,0.00003413219,0.0009089556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0009926698,"threshold_uncertainty_score":0.005249798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02567140859502908,"score_gpt":0.240573625183412,"score_spread":0.2149022165883829,"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."}}