{"id":"W2758909929","doi":"10.18653/v1/w17-5041","title":"Exploring Optimal Voting in Native Language Identification","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Voting; Preprocessor; Computer science; Identification (biology); Track (disk drive); Artificial intelligence; Natural language processing; Speech recognition; Political science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003482628,0.00006463509,0.00006901873,0.0001019116,0.0001762389,0.0005185957,0.001159361,0.00002294107,0.000003612327],"category_scores_gemma":[0.0002828064,0.00005729488,0.0000178369,0.0000884203,0.00002411333,0.002687745,0.0003588792,0.0001188712,0.00001284238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004030861,"about_ca_system_score_gemma":0.0000140398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002272912,"about_ca_topic_score_gemma":0.00006008503,"domain_scores_codex":[0.9993457,0.00001824999,0.0001288472,0.0002307375,0.0001344006,0.0001420694],"domain_scores_gemma":[0.9993306,0.00002733111,0.0001165259,0.000461876,0.00004139765,0.00002221564],"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":[0.00000481528,0.00005376643,0.003286178,0.00003632142,0.000007373528,0.000129491,0.01173544,0.00002516918,0.05157239,0.4032989,0.00008498033,0.5297652],"study_design_scores_gemma":[0.0002734984,0.00002390289,0.02307583,0.0001423364,0.000002093294,0.00001285478,0.0004758517,0.0831018,0.8870591,0.005412712,0.00005011399,0.0003699009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2417904,0.000203344,0.7549455,0.000691852,0.0001537099,0.00009735374,2.841341e-7,0.0004733829,0.00164416],"genre_scores_gemma":[0.7303904,0.000002017883,0.2693374,0.00002523581,0.00002274489,0.00001734457,3.784069e-7,0.000003307983,0.0002011575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8354867,"threshold_uncertainty_score":0.500083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0739580548976712,"score_gpt":0.3320063982087714,"score_spread":0.2580483433111002,"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."}}