{"id":"W4416414115","doi":"10.1016/j.neucom.2025.132127","title":"Document-level event argument extraction by leveraging span boundaries and argument dependencies","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Yunnan Provincial Science and Technology Department; Key Laboratory of Software Engineering of Yunnan Province; Yunnan Provincial Department of Education","keywords":"Discriminative model; Argument (complex analysis); Span (engineering); Event (particle physics); Context (archaeology); Matching (statistics); Representation (politics); Dependency graph","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":[0.001638343,0.001803753,0.001102662,0.01087613,0.001337486,0.003282412,0.001253225,0.002296433,0.008955954],"category_scores_gemma":[0.009788635,0.000619914,0.001746304,0.006438319,0.0003887758,0.005542758,0.002268013,0.002423578,0.008495491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007408342,"about_ca_system_score_gemma":0.002200427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00232083,"about_ca_topic_score_gemma":0.00443856,"domain_scores_codex":[0.9982522,0.0002945293,0.0002673525,0.0005694213,0.000442132,0.0001743016],"domain_scores_gemma":[0.9936104,0.00355449,0.0005249425,0.0004848308,0.001557473,0.0002677789],"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":[0.001055512,0.0006053482,0.01912242,0.002542389,0.0003542301,0.001687626,0.001511443,0.006739829,0.05083055,0.01580969,0.0748983,0.8248427],"study_design_scores_gemma":[0.0002772692,0.0004837291,0.04153983,0.001144474,0.001731838,0.003290123,0.002656378,0.5839099,0.07976723,0.08882086,0.196096,0.0002824407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.11198,0.008907751,0.8030356,0.002731474,0.001281509,0.001041134,0.02858851,0.01705502,0.02537905],"genre_scores_gemma":[0.5245157,0.00337913,0.4007105,0.0003849142,0.001608559,0.0006321592,0.05633663,0.001557093,0.01087529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01087613,"threshold_uncertainty_score":0.02996063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0193853584769092,"score_gpt":0.2715695428409622,"score_spread":0.252184184364053,"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."}}