A quarter of the citations in filed briefs are Westlaw or Lexis ids. We list them, we do not guess.Coverage ›
PROOFREAD.LAW
Proofread

What is checked,
and how often it is wrong

A checker that hides its blind spot is the thing it is supposed to catch. Every number below was measured on filed briefs and on machine-drafted paragraphs, with the same instrument the checker runs.

89%

of invented cases caught (court-adjudicated set, 528 citations)

14 / 15

invented quotations caught

1.2%

false flags on the court's own writing

0%

hallucination rate. The default check uses no language model.

The register

sourcewhat it holdsas of
CourtListener bulk data10.1 million cases, 18.1 million citations, one opinion text per casedump 2026-06-30, refreshed daily from the search API
Caselaw Access Projectopinion text where CourtListener has none (to 2019)static
govinfofederal appellate opinions, all 13 circuits, 2018 onward2026-09
Supreme Court DatabaseU.S. Reports citations for recent terms the bulk data lacks2025 release

Blind spots, stated

  • Westlaw and Lexis identifiers (2023 WL 1234567) cannot be resolved by any open register. A quarter of the citations in filed briefs. Listed, never flagged.
  • Federal appellate opinions from 2019 to 2023 are 10 to 15% incomplete in the bulk data. Recent reporter citations attach late. A miss in those years is shown as "cannot verify", never as a finding.
  • Statutes, regulations, rules, treatises and law reviews are not checked.
  • Whether a case is still good law is not checked. This is not a citator.

How the numbers were measured

528 citations from court decisions that found fabricated or misused authorities; 7,067 citations in 141 briefs filed in 29 federal district courts in 2024 and later; 300 paragraphs drafted by three language models against the court's own 100 paragraphs as the floor. Real filed briefs carried zero fabricated cases; the LLM drafts carried 7 to 21%.

The deep check (opt-in) confirms 69% of good citations and certifies a wrong passage 10.5% of the time, 5% at the confidence it shows. That is why it is a review queue with the passage, never a verdict.