Metraipolis › archive › dc_26bf9345b862

Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit — arXiv:2608.29800

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29800
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:07.062Z
SHA-256 of the archived text
d22a560fe4fd1304c83aacecd997d446aa0467a4c5e580fe29f5416831017567
Stable URL of this page
https://metraipolis.com/documento/dc_26bf9345b862

How to cite

Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit — arXiv:2608.29800 — arXiv (en), https://arxiv.org/abs/2608.29800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26bf9345b862 (Metraipolis archive dc_26bf9345b862, sha256 d22a560fe4fd1304c83aacecd997d446aa0467a4c5e580fe29f5416831017567)
BibTeX
@misc{dc26bf9345b862,
  title = {Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit — arXiv:2608.29800},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29800},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26bf9345b862; sha256 d22a560fe4fd1304c83aacecd997d446aa0467a4c5e580fe29f5416831017567},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-using agents are being proposed for medical imaging, and their behaviour when a tool returns a false finding is largely unmeasured. We audit whether a ReAct-style tool-calling agent abandons an answer it has already given correctly once a falsified finding arrives, and whether that depends on how the finding is presented. On 20 VQA-RAD closed questions across four vendor-designated model tiers, the agent commits to an answer from the image alone; a negated finding is then delivered either as JSON from an analyze_image tool the agent invokes itself, or as quoted prose attributed to a radiologist. Our outcome is the commission-error rate over cases answered correctly without any tool. Deference is much higher under the prose-attributed claim: at the strongest tier the agent revised its correct answer in 10 of 13 cases against 1 of 13 under the tool (exact McNemar p=0.0039, Holm-adjusted 0.012). We do not claim this isolates the source label. Attribution travels with the delivery channel in our design, and exposure differs because the tool claim reaches the agent only when it calls the tool. The finding is a joint source-and-delivery asymmetry from a small-scale pilot whose pre-specified stopping rule was not met.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29800 — 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 2026-10-17T09:28:48.066Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).