{"id":"W2250174871","doi":"","title":"Classifying English Documents by National Dialect","year":2013,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"British National Corpus; Linguistics; Variety (cybernetics); Variation (astronomy); Computer science; Natural language processing; Intuition; Artificial intelligence; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002444758,0.00006443385,0.00005549936,0.00003901409,0.0001102983,0.0002569431,0.0003517751,0.00004236296,0.0006524492],"category_scores_gemma":[0.0001277445,0.00005582872,0.00002795958,0.0001955826,0.00001333118,0.0008339738,0.0001046633,0.0000900025,0.0006638333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004696336,"about_ca_system_score_gemma":0.00004252946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002710032,"about_ca_topic_score_gemma":8.550903e-7,"domain_scores_codex":[0.9991755,0.00004691334,0.000122797,0.0001862708,0.0002878393,0.0001807146],"domain_scores_gemma":[0.9994938,0.0000775975,0.00003390923,0.0001178814,0.0001965837,0.00008027923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001215081,0.00005884449,0.005659017,0.000007626721,0.0000216611,8.470569e-7,0.0008861108,0.00001431188,0.003871561,0.4910548,0.4689103,0.02951371],"study_design_scores_gemma":[0.001674227,0.0001323745,0.0114124,0.00003501853,0.000006452818,0.000009737974,0.0001927053,0.1847794,0.06328899,0.1274454,0.6097474,0.001275874],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007998296,0.0000650834,0.8574371,0.002313665,0.0007927798,0.000172955,0.000002185905,0.0004242751,0.1307937],"genre_scores_gemma":[0.9783517,0.000003331272,0.01424098,0.00140422,0.00008776251,0.00002361749,0.000008458018,0.000003336275,0.005876655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9703534,"threshold_uncertainty_score":0.8532455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02166335923556349,"score_gpt":0.2665022127154754,"score_spread":0.2448388534799119,"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."}}