How Grok scores a story

Each story is scored 1–10 on four equally weighted tests: fidelity to primary sources; accurate handling of contested or soft numbers; explicit uncertainty where it is warranted; no omission that would reverse the central claim. Grok is told to under-score when evidence is incomplete. Grok is made by xAI, which has no connection to Badiyaa, and it can make mistakes too, so every story has buttons to run the same check yourself.

Fact-check this article against primary sources: [story link]. Extract every verifiable claim, find the earliest or most authoritative public source for each, and score the article 1–10 on: primary-source fidelity; handling of contested or soft numbers; explicit uncertainty framing; absence of material omission. Return a table of claims with sources and a one-line verdict.

Each result is one observation of a live story on a given date. It is not a certification. How we verify · The History audit · Corrections