Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

April 15, 2025

Researchers have reported tracing the appearance of nonsensical phrases like "vegetative electron microscopy" in scientific papers to contamination in AI training data. Testing indicated that large language models such as GPT-3, GPT-4, and Claude 3.5 may reproduce the term. The error allegedly originated from a digitization mistake that merged unrelated words during scanning, and a later translation error between Farsi and English. And to help build a safer AI ecosystem, visit JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Scientific authors, Researchers, OpenAI, Anthropic
Alleged developer
OpenAI, Anthropic
Alleged harmed parties
Scientific record, Scientific publishers, Scientific authors, Scholars, Researchers, Readers of scientific publications, Peer reviewers, Academic integrity

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1044

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.