SubmissionNumber#=%=#24
FinalPaperTitle#=%=#CASPAR: A Context-Aware Span Refinement Approach for Decision Support
ShortPaperTitle#=%=#
NumberOfPages#=%=#
CopyrightSigned#=%=#
JobTitle#==#
Organization#==#
Abstract#==#This paper presents CASPAR, a two-stage approach for the MedExACT shared task on medical decision span extraction and classification from ICU discharge summaries. Stage 1 performs document-level sequence labeling using a sliding-window RoBERTa encoder with BiGRU and CRF to generate candidate spans. Stage 2 applies a lightweight refinement module that revisits each candidate within its surrounding context to revise category assignments and correct span boundaries. The system achieves a final score of 0.5668 on the official leaderboard, substantially outperforming the organizer baseline on span-level F1. In addition to system description, we provides ablation results, repeated-run validation statistics, and subgroup- and error-level analyses that highlight the challenges of exact boundary recovery and confusion in race categories subgroups in clinical decision extraction.
Author{1}{Firstname}#=%=#Jing
Author{1}{Lastname}#=%=#Tao
Author{1}{Username}#=%=#jing.tao
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#jing.tao@queensu.ca
Author{1}{Affiliation}#=%=#Queen's University
Author{2}{Firstname}#=%=#Farhana
Author{2}{Lastname}#=%=#Zulkernine
Author{2}{Orcid}#=%=#
Author{2}{Email}#=%=#farhana.zulkernine@queensu.ca
Author{2}{Affiliation}#=%=#Queen's University
Author{3}{Firstname}#=%=#Amir
Author{3}{Lastname}#=%=#Eskandari
Author{3}{Orcid}#=%=#
Author{3}{Email}#=%=#Amir.Eskandari@queensu.ca
Author{3}{Affiliation}#=%=#Queen‘s University

==========
èéáğö