{"id":"W2251370914","doi":"","title":"Robust, Lexicalized Native Language Identification","year":2012,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Classifier (UML); Training set; Task (project management); Identification (biology); Set (abstract data type); Language identification; Test set; Natural language","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":[0.0005647785,0.00004990636,0.00005343889,0.00004052407,0.00007568853,0.00005858438,0.0002531325,0.00003548089,0.0001639523],"category_scores_gemma":[0.00007521956,0.00004119327,0.00002906689,0.0002291733,0.00001401086,0.000564221,0.00007121514,0.00006554546,0.000436244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002202698,"about_ca_system_score_gemma":0.00001172572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009779776,"about_ca_topic_score_gemma":9.221241e-7,"domain_scores_codex":[0.9993818,0.00007737321,0.0001153837,0.0001159432,0.0001325172,0.0001769671],"domain_scores_gemma":[0.9995786,0.00005010972,0.00004212587,0.000210366,0.00003763281,0.00008117479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001693961,0.00003607146,0.0009647023,0.000003253877,0.00000557799,5.538233e-7,0.002879409,0.00001153591,0.002862545,0.9825211,0.001147884,0.009565718],"study_design_scores_gemma":[0.001405691,0.00006277749,0.06588208,0.00002769661,0.0000252066,0.00004503394,0.002324586,0.1895361,0.6741552,0.01836945,0.04698553,0.001180645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009520771,0.0001530306,0.9786502,0.0008841382,0.0003210735,0.00006443274,8.297577e-7,0.0002164195,0.01018913],"genre_scores_gemma":[0.9673473,0.000001773087,0.02851614,0.0003404263,0.00007103536,0.000006506721,0.000005354024,0.000002465761,0.003709016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9641516,"threshold_uncertainty_score":0.5607179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0716369537548322,"score_gpt":0.3186020371403878,"score_spread":0.2469650833855556,"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."}}