{"id":"W4389053094","doi":"10.1007/s41701-023-00159-6","title":"Eh Across Englishes: A Corpus-Pragmatic Analysis of the Corpus of Global Web-Based English","year":2023,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Christian-Albrechts-Universität zu Kiel","keywords":"Punctuation; Linguistics; Variety (cybernetics); Variation (astronomy); Interrogative; Sentence; Contrast (vision); Computer science; Corpus linguistics; Discourse marker; Narrative; Natural language processing; Artificial intelligence; Philosophy; Astrophysics; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000956221,0.0003833911,0.001188792,0.0002557118,0.0004279953,0.0001766094,0.000973577,0.0001038285,0.0005470742],"category_scores_gemma":[0.00200724,0.0002750374,0.0009033296,0.002193308,0.001376581,0.0001934247,0.000394055,0.0002136953,0.00003450592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001134,"about_ca_system_score_gemma":0.0001867833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002683264,"about_ca_topic_score_gemma":0.008980558,"domain_scores_codex":[0.9966125,0.0002660601,0.001211188,0.0003689789,0.0009863132,0.0005549002],"domain_scores_gemma":[0.9955851,0.0008170351,0.001177725,0.001285454,0.001048112,0.00008651836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001673884,0.001635246,0.1513058,0.002638961,0.02176776,0.00007339628,0.3867843,0.02574876,0.0002832055,0.368375,0.02826454,0.01295566],"study_design_scores_gemma":[0.008835612,0.001027906,0.07934637,0.002416311,0.05056658,0.000006662298,0.4275432,0.2326049,0.002197535,0.01369697,0.1778501,0.003907884],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9617202,0.0008995741,0.0001310163,0.0002007127,0.00185793,0.0005276672,0.002024774,0.0003038611,0.03233431],"genre_scores_gemma":[0.997698,0.00007275677,0.0001550919,0.0001697494,0.000254493,0.00005475696,0.0001079705,0.00003797685,0.00144919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.354678,"threshold_uncertainty_score":0.9999702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918366678165337,"score_gpt":0.2799128157519163,"score_spread":0.2607291489702629,"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."}}