{"id":"W2759906493","doi":"10.18653/v1/w17-5023","title":"Ensemble Methods for Native Language Identification","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":"University of Victoria","funders":"","keywords":"Computer science; Identification (biology); Natural language processing; Artificial intelligence; Language identification; 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":[0.001126314,0.00004373936,0.00005872613,0.0000271585,0.0004167368,0.0003065695,0.0006336091,0.00003212514,0.0000134177],"category_scores_gemma":[0.0005265056,0.00003761772,0.000037621,0.00003453691,0.00001876679,0.00042249,0.0001061626,0.00003851469,0.0000368122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001388896,"about_ca_system_score_gemma":0.00001985111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001472421,"about_ca_topic_score_gemma":0.000004417659,"domain_scores_codex":[0.9995105,0.000059577,0.00009603942,0.0001722579,0.00005423453,0.0001074484],"domain_scores_gemma":[0.999123,0.0001355599,0.0001061298,0.0005156198,0.00008560537,0.00003402778],"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":[0.000001762062,0.000007168776,0.00004180003,0.000005041819,0.000005041968,2.848118e-7,0.0009419468,9.204731e-7,0.02083978,0.6589284,0.000362135,0.3188657],"study_design_scores_gemma":[0.000223877,0.00002152511,0.002745243,0.000004630091,0.000004116522,0.000001981418,0.0001368105,0.11154,0.8137978,0.0612151,0.01017511,0.0001338529],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007861424,0.00003676606,0.9894244,0.001912643,0.000379693,0.0001514168,0.000001337089,0.00009123155,0.007216354],"genre_scores_gemma":[0.457684,9.84896e-7,0.5362524,0.000117463,0.00003151205,0.0000225996,0.000002475038,0.000002192107,0.00588638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.792958,"threshold_uncertainty_score":0.3205245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0906035831245341,"score_gpt":0.4595583548269149,"score_spread":0.3689547717023808,"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."}}