Sanction teardown · T. Siracusa, Italy · 2026-02-20

R.G. n. 1244/2025

What happened

In T. Siracusa, Italy, a filing relied on an unnamed/unconfirmed AI tool to help draft legal argument. The court identified the following problems with the citations in that filing:

• False Quotes (Case Law)
  Counsel attributed a quoted maxim to Cass. civ., sez. III, 11 aprile 2006, n. 8379 which the Tribunal determined is not present in the authentic ruling; opposing party produced the true text.
• False Quotes (Case Law)
  Counsel quoted a purported textual passage attributed to Cass. civ., sez. III, 4 febbraio 2000, n. 1216 that the court found does not appear in that decision; opposing party produced the authentic text disproving the quote.
• False Quotes (Case Law)
  Counsel cited a purported passage on litisconsorzio as from Cass. civ., sez. I, 3 ottobre 2003, n. 14795; the court found the quoted passage does not correspond to that decision.
• False Quotes (Case Law)
  Counsel quoted a passage on creditor's free choice attributed to Cass. civ., sez. III, 5 marzo 2004, n. 4553 which the Tribunal verified is not contained in that ruling.

Which AI tool

an unnamed/unconfirmed AI tool. Note: Charlotin's public database records tool attribution only where a court order, brief, or reporting on the matter states it explicitly; "unidentified" or "implied" means the record indicates AI use but does not name a specific product — we do not guess.

Outcome

Monetary sanction (monetary penalty: 2000 EUR.)

How Citation Safe would have caught this

Citation Safe runs three deterministic layers before a brief is filed: (1) does the citation exist against CourtListener's database of published opinions, (2) if quoted, does that exact language appear in the source, (3) does the cited case actually support the proposition it is cited for. Fabricated case citations fail Layer 1. Fabricated or misattributed quotations fail Layer 2 even when the underlying case is real. Misrepresented holdings — a real case cited for a proposition it does not support — are the target of Layer 3. None of these checks involve asking another language model whether the citation looks right; they are lookups and text-matches against the actual source, which is why a hallucinated citation has to survive a direct lookup against the authoritative source — not another model's opinion — to earn a VERIFIED stamp; our measured false-verify rate is published live at /quality.

Check a brief before you file it → · See our live false-verify rate

Source: https://www.damiencharlotin.com/documents/1598/Siracusa.pdf, via Damien Charlotin's public AI Hallucination Cases Database (CC0).