Sanction teardown · CA Indiana, USA · 2025-09-19
Cingel v. Ferreri
What happened
In CA Indiana, USA, 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:
-
Fabricated (Case Law)Appellant cited 'In re Marriage of Dunston, 989 N.E.2d 830, 835 (Ind. Ct. App. 2013)' to support abuse-of-discretion review; court found no such case and reporter citation pointed to unrelated decisions.
-
Fabricated (Case Law)Appellant cited 'McCain v. State, 924 N.E.2d 56, 60 (Ind. 2009)' for a custody proposition; court determined that citation does not exist as given.
-
Fabricated (Legal Norm)Appellant relied on 'Indiana Code § 31-17-2.5-1' as the custody statute; court found no such statutory section (correct statute is 31-17-2-8).
-
Fabricated (Legal Norm)Appellant cited and purported to quote 'Indiana Code § 31-17-2.2-23(a)'; court noted no such statutory provision exists.
-
Fabricated (Legal Norm)Appellant cited 'Trial Rule 60.1' and 'Trial Rule 60.1(A)' to support procedural requirements for custody modifications; court found no such trial rule.
-
Misrepresented (Legal Norm)Appellant cited 'Trial Rule 59(G)' as requiring written orders or hearings on motions to correct error; court explained Rule 59(G) concerns cross errors and was misapplied.
-
Misrepresented (Case Law)Appellant cited 'Bowman v. Bowman, 682 N.E.2d 23, 28 (Ind. Ct. App. 1997)' for multiple propositions; court observed the correct Bowman citation is different (686 N.E.2d 921) and the cited reporter/pincite pointed to unrelated authority, and the asserted propositions were inaccurate.
-
Misrepresented (Legal Norm)Appellant relied on subsections 'Indiana Code § 31-17-2.2-1(a)' and '(b)' for notice timing and burden of proof on relocation; court found those subsections were mischaracterized (they address filing location and exceptions) and pointed to the correct provisions (31-17-2.2-3 and 31-17-2.2-5).
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
Warning
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/820/Cingel_v_Ferreri.pdf, via Damien Charlotin's public AI Hallucination Cases Database (CC0).