{"id":"W2758288680","doi":"10.18653/v1/w17-5022","title":"Native Language Identification Using a Mixture of Character and Word N-grams","year":2017,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Concordia University","keywords":"Computer science; Character (mathematics); Task (project management); Natural language processing; Word (group theory); Word identification; Artificial intelligence; Identification (biology); First language; Linguistics; Transcription (linguistics); Speech recognition; Word recognition; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002697086,0.00004377263,0.00006629623,0.0000311311,0.0001624497,0.0001603283,0.000281923,0.00003581528,0.00001088531],"category_scores_gemma":[0.00007445014,0.00003612366,0.0000176266,0.00004403841,0.00004121929,0.000437354,0.0001195231,0.00005530965,0.000004593387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000739412,"about_ca_system_score_gemma":0.00001250543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004254699,"about_ca_topic_score_gemma":0.000006710476,"domain_scores_codex":[0.9995815,0.000027144,0.00009921016,0.0001331568,0.00008599202,0.00007306669],"domain_scores_gemma":[0.9994251,0.00002008669,0.0001525892,0.0003162432,0.00005760322,0.00002841603],"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":[0.00001840288,0.00007316874,0.02045598,0.0000827171,0.00004954515,0.00001401421,0.01950797,0.000003503707,0.3381122,0.3628887,0.0001068454,0.258687],"study_design_scores_gemma":[0.0005844874,0.00003362486,0.3378384,0.0001031204,0.00001840039,0.00002460874,0.0005887453,0.1256035,0.5267026,0.007259637,0.0008652514,0.0003776334],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5932242,0.00004829714,0.4054238,0.0005728164,0.0001379523,0.00006227446,0.000002052103,0.00002562893,0.0005030488],"genre_scores_gemma":[0.9884759,0.000002841476,0.01088992,0.0000567897,0.00002326734,0.0000010508,0.000001697468,0.000001785942,0.0005467592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3952517,"threshold_uncertainty_score":0.154605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04361739538232948,"score_gpt":0.334431434140087,"score_spread":0.2908140387577576,"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."}}