{
  "id": 7550,
  "url": "https://arxiv.org/abs/2603.07388v2",
  "title": "Sparsity and Out-of-Distribution Generalization",
  "summary": "Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's \"grue\" puzzle in 1946. Today it's a central problem in machine learning, including AI alignment. Here we propose a principled account of OOD generalization with three main ingredients. First, the world is always presented to experience not as an amorphous mass, but via distinguished features (for example, visual and auditory channels). Second, Occam's Razor favors hypotheses that are \"sparse,",
  "authors": "Scott Aaronson, Lin Lin Lee, Jiawei Li",
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-08T00:16:25.000Z",
  "fetched_at": "2026-07-14T16:33:16.670Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7550",
  "original_url": "https://arxiv.org/abs/2603.07388v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}