{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003123989,0.0003216965,0.0004246238,0.004557529,0.001903158,0.002014908,0.000393506,0.0003779212,0.003111653],"category_scores_gemma":[0.008653863,0.0001753168,0.0002065796,0.0062607,0.002020053,0.001308641,0.002565114,0.0007602355,0.0003288378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113831,"about_ca_system_score_gemma":0.0008871331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008758514,"about_ca_topic_score_gemma":0.02049452,"domain_scores_codex":[0.9976233,0.001259524,0.0002288845,0.0003887571,0.0003613443,0.0001382224],"domain_scores_gemma":[0.9873413,0.009472457,0.0006144422,0.0007379742,0.001583857,0.0002498849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0009559507,0.0006529576,0.05761469,0.004119343,0.0001619512,0.003340912,0.6097466,0.001088956,0.0458727,0.02684293,0.01390979,0.2356933],"study_design_scores_gemma":[0.0001479079,0.0002300473,0.3593022,0.0008474822,0.0001724645,0.001711594,0.3457671,0.002649847,0.01582786,0.004116383,0.2690924,0.0001348382],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9666621,0.001298996,0.006564151,0.0004626101,0.0000679307,0.0003290004,0.006064187,0.0000694613,0.01848149],"genre_scores_gemma":[0.9801438,0.0005832671,0.008039972,0.0001137438,0.00004771953,0.0004619731,0.007414353,0.0001826799,0.003012397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008758514,"threshold_uncertainty_score":0.01741505,"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."}}