{"id":"W4412887991","doi":"10.18653/v1/2025.findings-acl.818","title":"A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Scheme (mathematics); Annotation; Pipeline (software); Tree (set theory); Natural language processing; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003574009,0.00169034,0.0008568395,0.002412406,0.001799642,0.002451358,0.00220162,0.001581539,0.01664797],"category_scores_gemma":[0.01648422,0.001160715,0.001733231,0.001690816,0.0008837171,0.004365651,0.003817654,0.003084868,0.01319228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00163181,"about_ca_system_score_gemma":0.004280557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006552664,"about_ca_topic_score_gemma":0.01201867,"domain_scores_codex":[0.9975068,0.0009725905,0.0001788362,0.0006021966,0.0006059951,0.0001336358],"domain_scores_gemma":[0.9920802,0.004157308,0.0002919887,0.001804727,0.001378228,0.0002875429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004594978,0.0002635014,0.002803884,0.001141617,0.0001139017,0.0004178643,0.00459628,0.01697401,0.048498,0.05812158,0.1538659,0.7127439],"study_design_scores_gemma":[0.0000932795,0.00008933465,0.001480473,0.0002548213,0.00007622107,0.0003207416,0.00127411,0.6276165,0.04622414,0.1282324,0.1941793,0.0001587566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004218245,0.0001010857,0.9349831,0.0003775186,0.0001025428,0.0002561104,0.00361586,0.05309852,0.003246981],"genre_scores_gemma":[0.04618467,0.0000980967,0.9363794,0.0001606639,0.00003766487,0.0004877477,0.009190802,0.004592903,0.002868189],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01664797,"threshold_uncertainty_score":0.05569297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.013420934460765,"score_gpt":0.3018274128048487,"score_spread":0.2884064783440837,"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."}}