{
  "id": 19173,
  "url": "https://arxiv.org/abs/2608.13262v1",
  "title": "Into the ORBIT for Time Series: Training Regimes for Foundation Models",
  "summary": "Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Boo",
  "authors": "Hongjie Xia, Yiding Liu, Yifan Hu, Peiyuan Liu, Zewei Dong",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T14:00:39.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19173",
  "original_url": "https://arxiv.org/abs/2608.13262v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}