{"id":"W2798712760","doi":"10.1109/infoteh.2018.8345541","title":"Slavic language identification using cascade classifier approach","year":2018,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Slavic languages; Language identification; Preprocessor; Classifier (UML); Natural language processing; Artificial intelligence; Identification (biology); Cascade; Focus (optics); Natural language; Linguistics","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":[0.0004310863,0.00007101211,0.00006664603,0.00006940513,0.0001760064,0.00014852,0.0003883727,0.00006462097,0.00006097803],"category_scores_gemma":[0.00002838302,0.00006140028,0.00003245593,0.0003760491,0.00004724685,0.0003596614,0.0001002945,0.00008397121,0.0002724545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003754717,"about_ca_system_score_gemma":0.00003544334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003758183,"about_ca_topic_score_gemma":0.000003739647,"domain_scores_codex":[0.9991642,0.00006803771,0.0001563305,0.0002662615,0.0001611431,0.0001840736],"domain_scores_gemma":[0.9994105,0.00001713589,0.0000594398,0.000382216,0.00007012003,0.00006060555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000100144,0.0001406365,0.001853314,0.00004037202,0.00003754162,0.00001038569,0.01377717,0.00005972529,0.259288,0.6672646,0.003119114,0.05439914],"study_design_scores_gemma":[0.000165304,0.00001966524,0.003320322,0.000006394785,0.000006980625,0.00003848285,0.0004379767,0.8384664,0.154046,0.001358391,0.001910174,0.0002238522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06760686,0.00003607337,0.9215247,0.0002196313,0.0002987601,0.00007758869,7.242098e-7,0.0001888412,0.01004679],"genre_scores_gemma":[0.9116818,5.603386e-7,0.08567463,0.0002683315,0.0001569602,0.000002814025,0.000004487555,0.00000453078,0.002205853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.844075,"threshold_uncertainty_score":0.3501943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06249432480819379,"score_gpt":0.3338656570210166,"score_spread":0.2713713322128228,"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."}}