{
  "id": 12316,
  "url": "https://arxiv.org/abs/2607.16401",
  "title": "Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence",
  "summary": "Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausibility only at the output level, without verifying whether the model arrives there through a faithful, law-grounded reasoning process. We introduce Apple-PI, the first benchmark that anchors video-model evaluation explicitly in physical laws. Apple-PI comprises three components. 1) Orchard: a dataset of 400 videos cove",
  "authors": "Runmao Yao, Kairui Hu, Yukang Cao, Ruisi Wang, Shulin Tian, Ziang Cao",
  "category": "research",
  "topics": "regulation",
  "orgs": "apple",
  "regions": null,
  "published_at": "2026-07-16T20:00:00.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/12316",
  "original_url": "https://arxiv.org/abs/2607.16401",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}