{
  "id": 15267,
  "url": "https://arxiv.org/abs/2607.27281v1",
  "title": "The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models",
  "summary": "A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing. We show this no-partial-credit joint alignment is the rate-limiting step of capability formation. Two fingerprints: in a shortcut-free apparatus a five-part circuit missing three waits as long as a three-part circuit missing three (1.19-1.37), so the wait counts missing parts, not size; and on Pythia across seven capabilities and three scale",
  "authors": "Lei Dong",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T13:46:52.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/15267",
  "original_url": "https://arxiv.org/abs/2607.27281v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}