{"id":"W1985913097","doi":"10.1109/eict.2014.6777864","title":"Native Language Identification using probabilistic graphical models","year":2014,"lang":"en","type":"article","venue":"2013 International Conference on Electrical Information and Communication Technology (EICT)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Graphical model; Artificial intelligence; Support vector machine; Probabilistic logic; Task (project management); Feature (linguistics); Principle of maximum entropy; Point (geometry); Natural language processing; Entropy (arrow of time); Identification (biology); Naive Bayes classifier; Machine learning; Pattern recognition (psychology); Mathematics","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":[0.000621575,0.0001539287,0.000156624,0.0006654474,0.0002848399,0.0002797351,0.001216381,0.0002278556,0.00002901587],"category_scores_gemma":[0.0003690438,0.000147968,0.00004051828,0.0006743793,0.0001652596,0.001512678,0.000255818,0.0004958949,0.00006905078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049691,"about_ca_system_score_gemma":0.00006869637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002911783,"about_ca_topic_score_gemma":0.000006076975,"domain_scores_codex":[0.9985673,0.0001692863,0.00051236,0.0002211413,0.0003273195,0.0002026171],"domain_scores_gemma":[0.9982808,0.000130929,0.0003389983,0.0005984358,0.0005764142,0.00007439264],"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":[0.000009081439,0.00003442736,0.00005479811,0.00000340315,0.0000119512,8.723356e-8,0.0003403119,0.0002066995,0.0002511053,0.9628772,0.00007699602,0.03613392],"study_design_scores_gemma":[0.0002334093,0.00005537234,0.0002102713,0.0000194359,0.000004160083,0.00001158973,0.000111118,0.7858413,0.0007518546,0.2117341,0.0008925909,0.0001348238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02390383,0.00008899882,0.9513194,0.01655228,0.0001243533,0.0003011894,0.000007312995,0.0004395896,0.007263043],"genre_scores_gemma":[0.991399,0.0002229204,0.007495488,0.0006617917,0.00001200481,0.00005800904,0.00007774924,0.00000472599,0.00006828339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9674952,"threshold_uncertainty_score":0.6033959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03629424243890863,"score_gpt":0.3031466464180493,"score_spread":0.2668524039791407,"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."}}