paperSeptember 2026Unreviewed

ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues

Huimin Wang, Zhengyi Zhao, Yutian Zhao

Abstract

Clinical LLM assistants must reason over multi-visit patient trajectories, yet whether the compact history representations used to scale them---retrieval, structured timelines, LLM summaries, agentic memory---preserve the longitudinal signal clinical reasoning needs has not been measured. We introduce ClinTraceBench: 385 MIMIC-IV-derived verified dialogues with event-ID provenance, a nine-task taxonomy (T1--T9), and L0--L4 deterministic + L5 human-audit validation (98.92\% agreement). We evaluat

Cite

@misc{wang2026clintracebench,
  title = {{ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues}},
  author = {Huimin Wang and Zhengyi Zhao and Yutian Zhao},
  year = {2026},
  month = sep,
  eprint = {2609.01111},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01111}
}