{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001156141,0.0001059965,0.00012865,0.0000329415,0.0002042854,0.00006282144,0.0002932771,0.00003592672,0.00001076381],"category_scores_gemma":[0.00002071972,0.00005081212,0.00001626644,0.0001087093,0.0001278722,0.0002947665,0.0002231574,0.00007019413,0.0000116206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005672733,"about_ca_system_score_gemma":0.00001529422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006017913,"about_ca_topic_score_gemma":0.000004433445,"domain_scores_codex":[0.9992673,0.00006461037,0.00008204848,0.0003063444,0.0001254043,0.0001542742],"domain_scores_gemma":[0.9994621,0.0001940507,0.00002860947,0.0002334119,0.0000135251,0.00006835347],"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":[0.0001090611,0.0001830775,0.2290313,0.00008095392,0.00007165689,0.00131279,0.0008783975,0.0001306116,0.02629377,0.03519294,0.001528392,0.705187],"study_design_scores_gemma":[0.002168837,0.003969638,0.2996354,0.0003302473,0.00002257532,0.006223019,0.00005748351,0.6446103,0.02875397,0.005231421,0.007398987,0.001598087],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7244434,0.0002266548,0.2723566,0.0002815977,0.00006561861,0.00009018809,0.00000112089,0.0001830656,0.002351813],"genre_scores_gemma":[0.9440312,0.00005682474,0.05567717,0.000118564,0.00002576672,0.000006187349,0.000001253838,0.000002688442,0.0000803046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.703589,"threshold_uncertainty_score":0.2072058,"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."}}