HISPI Project Cerebellum HISPI PROJECT CEREBELLUM

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

April 15, 2025

Researchers uncovered an anomaly, dubbed 'vegetative electron microscopy', in several scientific papers they traced back to questionable AI training data. Preliminary tests suggest that large language models such as GPT-3, GPT-4, and Claude 3.5 may reproduce the term, raising concerns about AI governance and trustworthiness. The error seems to stem from a digitization mistake during scanning process, compounded by a Farsi-to-English translation error. This incident underscores the need for safe and secure AI practices.

Join Us in HISPI Project Cerebellum TAIM to help prevent such incidences and establish guardrails for AI development and deployment. JOIN US

Matched TAIM controls

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

Alleged deployer
openai, anthropic, researchers, scientific-authors
Alleged developer
openai, anthropic
Alleged harmed parties
researchers, scientific-authors, scientific-publishers, peer-reviewers, scholars, readers-of-scientific-publications, scientific-record, academic-integrity

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.