The best public record of court filings with AI-invented citations is Damien Charlotin's AI Hallucination Cases Database (CC BY 4.0). It is excellent at what it covers: courts, federal contract-appeal boards, many foreign tribunals and the agency cases that make the news.
We wanted to know what it cannot see. So we went to the tribunals' own archives and read them, using pre-registered censuses where possible: the predictions and code were published before any decision text was read, every flagged decision was then read by hand, and each result was compared with the database.
What the archives hold
- California Workers' Compensation Appeals Board: of 3,121 readable panel decisions from 2024 to November 2026, 10 decisions in 7 cases say a filing cited authority or quotations that do not exist. The database has no WCAB row at all.
- California Office of Tax Appeals: of 1,849 opinions read, 3 (May and June 2026) say a party cited opinions or other authority that do not exist. One is now precedential. One, filed by a self-represented taxpayer, sits in a footnote that the OTA's own issue summary leaves out. The database lists none of the three.
- Merit Systems Protection Board: of 3,567 Board decisions from January 2024 to November 2026, one says a filing relied on cases that do not exist. It is not in the database.
- Board of Immigration Appeals: of 288 precedent decisions from 2020 to 2026, one deals with fabricated citations (Matter of Sethi, a reciprocal suspension). The database has the Ninth Circuit order behind it, not the Board's decision.
- USPTO practitioner discipline: of 160 decisions since 2023, 133 have a text layer, and one (a 2025 reprimand) deals with cases that do not exist. It is not in the database. 27 of the 160 are image-only PDFs that no text search can see.
- California PERB: its own monthly summaries show four decisions on fabricated or nonexistent authority from December 2025 to October 2026; the database lists one. NLRB: three 2026 decisions on citations to cases that do not exist; by 13 November 2026 the database listed one.
- Where the database already matches: the FLRA (one AI decision in 310, listed), the U.S. Tax Court (4 documents, 3 listed) and New York's tax tribunals (917 documents, none at all).
Four things we did not expect
- Searching for "AI" misses most of them. In the WCAB, AI is named in only 2 of the 7 cases, and both times by the filer: once a legal publisher's own research chatbot, once office staff. The Board's position is that a false citation in a verified petition is the problem however it was made.
- The filers are often professionals, not self-represented people. In 5 of the 7 WCAB cases the bad citations came from lawyers for employers or insurers. At the OTA, two of the three came from related restaurant companies represented by CPAs.
- Timing differs by tribunal. Every WCAB case began between June and December 2025; 2026 brought only follow-up sanctions. The OTA's three all came in May and June 2026.
- Some decisions are invisible to text search. Footnotes, issue summaries that skip the sanction, and scanned PDFs without a text layer (44 of 9,980 decision PDFs across seven archives) all hide cases.
If you build legal research or AI-risk tools
Agency and state tribunals are where a lot of this is now being decided, and they publish in ways that courts don't: month pages, year folders, PDFs named by case number. A tracker or alert that only watches court dockets and news will undercount, and a keyword filter on "AI" will undercount again.
Everything is open: the per-decision data (with PDF hashes, and without injured workers' names), the pre-registrations, the code and a hand-checked list of the cases at munimtechnologies/bar-ai-guidance (code Apache-2.0, text CC BY 4.0). We plan to send the list of untracked decisions to the database's maintainer. The next census, pre-registered, covers the U.S. Employees' Compensation Appeals Board.
This post and the studies behind it were made with AI agents working in MV2's name; every flagged decision was read in full before it was counted. It is information about public decisions, not legal advice, and it judges no lawyer, party or official.
MV2, Munim, Inc., mv2@munimtech.com
Top comments (0)