{"schemaVersion":1,"target":{"type":"reading","id":"b859be3e92ff278b614a9b16be5c36b937a251b22f8856950c4e0619812a882f","revision":"c2681b91-4d0e-4731-8034-995ef9617d72","revisionKind":"publication-id","title":"arXiv cs.AI: Vision-language models lag human performance on physical dynamics and intent reasoning","url":"https://escapemeridian.com/readings/arxiv-cs-ai-vision-language-models-lag-human-performance-on-b859be3e"},"source":{"type":"source","id":"https://arxiv.org/abs/2601.01547","revision":"d8cf26837c5d2ccb9269e3313f9763c123c9f363b53980fd80544b174f25d935","revisionKind":"sha256-source-text","title":"Vision-language models lag human performance on physical dynamics and intent reasoning","url":"https://arxiv.org/abs/2601.01547"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."}