Coverage narrative

Coverage of US Department of Defense (Pentagon)

How the 46 sources on this entity in the platform's archive frame it. Tones are auto-classified by an LLM reading the title + raw-content excerpt. Critical doesn't mean wrong; favourable doesn't mean innocent. The distribution is itself the signal.

46
Sources on record
27
Classified
19
Pending
Neutral · 15 · 55.6%
Critical · 1 · 3.7%
Primary record · 11 · 40.7%

Representative sources by tone

Critical 1 source
Neutral 15 sources
  • Research: U.S. Department of Defense — Parliamentary records (no results) Search Scope Note 2026 📜 Receipt
  • Research: U.S. Department of Defense — Court records (no results) Search Scope Note 2026 📜 Receipt
  • Research: U.S. Department of Defense — USASpending contracts (no results) Search Scope Note 2026 📜 Receipt
  • SEARCH_ERROR: U.S. Department of Defense not found in opencorporates Pipeline — search validation (opencorporates) 2026-05-10 📜 Receipt
  • Center for Arms Control and Non-Proliferation; House records Directed Inquiry — Web Search 2024-12-12 📜 Receipt
Primary record 11 sources

How tones are assigned

For each source, the title + the first ~1500 characters of raw content go to an LLM (cheap call) with a prompt asking it to pick exactly one tone from the canonical five:

  • Favourable — positive framing, advocacy, sympathetic, PR-like
  • Neutral — descriptive reporting without editorial lean
  • Critical — adversarial framing, accountability journalism, investigative
  • Mixed — substantial both-sides framing in a single piece
  • Primary record — government filing, court docket, SEC submission, raw transcript — framing doesn't apply

The classifier runs on a boot-time backfill (small batches, high-priority entities first). New ingested sources also pass through it. The model name (and run date) is stored per source — a future upgrade can re-classify with a stronger model.

A high critical % means the coverage in this archive is adversarial. It does NOT mean the subject is guilty of anything. A high favourable % means the coverage leans positive — it does NOT mean the subject is benign. The distribution shows the editorial frame; verify against the linked primary sources before citing.

Machine-readable: JSON