{
  "id": 1619441,
  "title": "Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot",
  "url": "https://urgent.news/2026/08/17/historical-backtesting-for-scientific-question-discovery-a-protocol",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-17T16:51:06.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.16795v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Systems that generate scientific research questions are evaluated today by expert scores, LLM-as-judge ratings, or curated case studies -- all subjective, none falsifiable. We formalize historical backtesting as an alternative: a system generates questions from a corpus frozen at a historical cutoff, the questions are frozen before any access to later literature, and a temporally isolated future…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}