pith:VQMPFD7E
MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
Medical vision-language models fail to refuse answers when visual evidence is broken, trailing radiologists by 14 points on a new composite score.
arxiv:2605.07919 v2 · 2026-05-08 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{VQMPFD7EHMUMO6FVYUPLBU6POS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
The independent radiologist scores MCS 83.3 at silent-failure rate 5.8%, leaving a 14.1-point composite headroom above the strongest audited model (Claude Opus 4.7 at 69.2).
That the four chosen perturbation types and the 300 clinician-authored cases sufficiently represent the range of broken visual evidence that occurs in real clinical practice.
MedVIGIL introduces a clinician-supervised benchmark showing medical VLMs frequently give fluent answers on broken visual evidence, with top models 14 points below human radiologists on the composite score.
Receipt and verification
| First computed | 2026-05-25T02:02:16.508920Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
ac18f28fe43b28c778b5c51eb0d3cf74b15b8cf4701039e8417b656176d45bf0
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/VQMPFD7EHMUMO6FVYUPLBU6POS \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: ac18f28fe43b28c778b5c51eb0d3cf74b15b8cf4701039e8417b656176d45bf0
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "133a9adea01e80b03ff81c4967815dba5865719a1437782d91a280f73ba236a3",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-08T15:55:30Z",
"title_canon_sha256": "53ac9af92f70e8a5751c4d6922585835fb90690dc00399e153d13ad726421550"
},
"schema_version": "1.0",
"source": {
"id": "2605.07919",
"kind": "arxiv",
"version": 2
}
}