{"id":"W4414739115","doi":"10.22250/24107190-2025-11-3-87","title":"Corpus-based discourse analysis of connected speech phenomena in typologically diverse languages","year":2025,"lang":"en","type":"article","venue":"Theoretical and Applied Linguistics","topic":"Discourse Analysis and Cultural Communication","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scripting language; Annotation; Python (programming language); Computational linguistics; Speech corpus; Corpus linguistics; Natural language; Text corpus","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":[0.0004476845,0.00007880908,0.0002825418,0.0001318709,0.0001266813,0.00002856584,0.0001956795,0.00007021425,0.0002694266],"category_scores_gemma":[0.0007783371,0.00005920258,0.00006310787,0.0008744552,0.001222919,0.000005109668,0.00005698427,0.0001004928,0.000002016161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001928479,"about_ca_system_score_gemma":0.00004035574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00021921,"about_ca_topic_score_gemma":0.0007088418,"domain_scores_codex":[0.9992391,0.0001074569,0.0002089929,0.0001456609,0.0001491658,0.0001495763],"domain_scores_gemma":[0.9992735,0.0003435199,0.00006705887,0.0001685151,0.00009768129,0.00004976582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004158996,0.0001082799,0.002299698,0.000005389617,0.0001021351,0.000001255157,0.0006684901,0.00009534181,0.00007818697,0.9908807,0.00001469306,0.005704233],"study_design_scores_gemma":[0.002547944,0.0001673435,0.04915309,0.0001653938,0.00695228,7.896898e-8,0.1137019,0.01449527,0.001640731,0.7920298,0.01809634,0.001049834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4021178,0.0001479162,0.000362834,0.0006340742,0.00003333099,0.0001401948,0.00002578648,0.00003091799,0.5965071],"genre_scores_gemma":[0.9990621,0.00008463842,0.000425332,0.000169231,0.00005207093,0.000004595579,0.0000563734,0.000002178828,0.0001434445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5969443,"threshold_uncertainty_score":0.4505895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01298485957063372,"score_gpt":0.339433345069315,"score_spread":0.3264484854986813,"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."}}