Metraipolis › archive › dc_e47612155e2e

Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication — arXiv:2609.13062

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13062
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:00.116Z
SHA-256 of the archived text
46c62fe53d0a6ec12e5f9bfd766d7378f21b85f6a271a0993fce05b36a2d36c1
Stable URL of this page
https://metraipolis.com/documento/dc_e47612155e2e

How to cite

Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication — arXiv:2609.13062 — arXiv (en), https://arxiv.org/abs/2609.13062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e47612155e2e (Metraipolis archive dc_e47612155e2e, sha256 46c62fe53d0a6ec12e5f9bfd766d7378f21b85f6a271a0993fce05b36a2d36c1)
BibTeX
@misc{dce47612155e2e,
  title = {Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication — arXiv:2609.13062},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13062},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e47612155e2e; sha256 46c62fe53d0a6ec12e5f9bfd766d7378f21b85f6a271a0993fce05b36a2d36c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Clinical timelines support treatment-window analysis and leakage-free modeling, but discharge summaries often obscure chronology and structured EHR tables describe only part of the patient course. We present a UID-preserving framework that links each narrative event occurrence to its source span and retains that identity through text-only estimation, structured-evidence retrieval, timestamped source-row grounding, and joint revision. We also present GAVEL, an LLM judge that compares two UID-aligned timelines against the narrative and structured record, to augment prior matching and temporal assessments. Across six open-weight models and 40 mixed-critical-care summaries, the GLM 5.2 multimodal revision, as compared to its text-only variant, improved temporal agreement without reducing event recovery and performed competitively with clinician annotations, while other model revisions showed smaller gains and lower overall performance. Ablations showed that UIDs primarily preserve event retention, whereas source-row linkage supports temporal placement. Blinded human review upheld most GAVEL findings, and controlled adjudication favored multimodal over text-only GLM 5.2 but did not for DeepSeek V3.2. In developing the UID and judge pipeline, we are able to demonstrate 43\% increased event recovery, a framework competitive with clinician annotations, and a system with occurrence-level provenance for both reconstruction and evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13062 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.832Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).