{
  "id": 5662,
  "url": "https://arxiv.org/abs/2604.17429v1",
  "title": "Jupiter-N Technical Report",
  "summary": "We present Jupiter-N, a hybrid reasoning model post-trained from Nemotron 3 Super, a fully open-source 120 billion parameter LLM. We target three objectives: (1) agentic capability via uncertainty-curated trajectories; (2) UK cultural alignment via synthetic data grounded in cultural norms; and (3) Welsh language support via parallel corpora and LLM-translated Welsh conversations. Our data curation strategy carefully preserves the base model's capabilities: using our Forget-Me-Not framework, we ",
  "authors": "George Drayson",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": "uk",
  "published_at": "2026-04-19T13:18:51.000Z",
  "fetched_at": "2026-07-14T16:31:53.169Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5662",
  "original_url": "https://arxiv.org/abs/2604.17429v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}