{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001931201,0.00173639,0.001772436,0.005200995,0.001926621,0.00209371,0.001714089,0.001862248,0.004880704],"category_scores_gemma":[0.004010095,0.000432373,0.001201516,0.00196465,0.0004653494,0.002956297,0.001284892,0.001795461,0.005592913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007493115,"about_ca_system_score_gemma":0.001299548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005777112,"about_ca_topic_score_gemma":0.009332822,"domain_scores_codex":[0.9973948,0.000400929,0.0001882839,0.0007936449,0.0007928816,0.000429369],"domain_scores_gemma":[0.9973729,0.0006391686,0.0001784571,0.000302767,0.001295779,0.000210986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001674915,0.001031359,0.02147776,0.0004377971,0.0003512001,0.002269671,0.0007384681,0.02859355,0.07575082,0.005692389,0.03773255,0.8242495],"study_design_scores_gemma":[0.00005554935,0.0004445879,0.00820276,0.00006528806,0.0002073588,0.001084177,0.0004077487,0.9270743,0.04220591,0.009147312,0.01098766,0.0001173689],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2627198,0.003732711,0.6944423,0.0008878971,0.001113154,0.001234993,0.003016434,0.01229469,0.02055804],"genre_scores_gemma":[0.7809716,0.0007492861,0.1937623,0.0003159393,0.0004703024,0.0003872645,0.005296368,0.0003255043,0.01772137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005777112,"threshold_uncertainty_score":0.01632756,"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."}}