Metraipolis › archive › dc_16c48cb20ca3
Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records — arXiv:2608.29965
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29965
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:44:26.127Z
- SHA-256 of the archived text
10303c9b52f9a26fc2d7491cd642ef10a12b3a0d0eb37fb951646a4a8b69742b- Stable URL of this page
https://metraipolis.com/documento/dc_16c48cb20ca3
How to cite
Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records — arXiv:2608.29965 — arXiv (en), https://arxiv.org/abs/2608.29965 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16c48cb20ca3 (Metraipolis archive dc_16c48cb20ca3, sha256 10303c9b52f9a26fc2d7491cd642ef10a12b3a0d0eb37fb951646a4a8b69742b)
BibTeX
@misc{dc16c48cb20ca3,
title = {Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records — arXiv:2608.29965},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29965},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16c48cb20ca3; sha256 10303c9b52f9a26fc2d7491cd642ef10a12b3a0d0eb37fb951646a4a8b69742b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29965. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can convert medical documents into structured data, but plausible output may still be unsupported by the source. Persisting such output in a longitudinal health record, a record that accumulates patient information over time, therefore creates an integrity risk: unverified data may influence later summaries, trends, or preventive-care computations. We introduce an evidence-gated trust-promotion model that keeps generated data provisional until a deterministic monitor verifies it against the source document. The monitor admits a candidate for a specified downstream use only when the source contains a unique supporting quotation, the relevant fields occur within the same laboratory row, and the required provenance is preserved. The generator cannot approve its own output, missing or ambiguous evidence causes refusal, and refused candidates remain available for human review rather than being silently discarded. We implement the model in Medical DataCloud, a personal health-record application, and evaluate it through automated tests and a replay of saved extraction outputs. All 22 conformance and mutation tests pass. The replay covers nine historical laboratory PDF reports containing 102 manually labelled rows. The reports produce 97 numeric candidates: schema validation accepts all 97, an earlier packet-level evidence check accepts 94, and the hardened quotation- and row-level policy admits 72 while retaining 25 for review. The study evaluates system integrity rather than clinical correctness or clinical safety. The results demonstrate the technical feasibility of an enforceable boundary that prevents generated claims from authorizing their own reuse in a longitudinal health record. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29965 — 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 2026-10-17T07:28:26.570Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).