AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

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

AI Incident Database · article · Feb 10, 2025 · UTC

Researchers reportedly traced the appearance of the nonsensical phrase "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.

Read original source ↗ Open in workspace

recordType
incident-report
evidenceStatus
reported
region
Global

Reported occurrence date: 2025-04-15T00:00:00.000Z

Evidence & attribution

AI Incident Database, Responsible AI Collaborative; McGregor (2021), Preventing Repeated Real World AI Failures by Cataloging Incidents. Incident-specific contributor credits are available at each citation link. Metadata adapted; article text excluded.

License: CC BY-SA 4.0

First collected: 2026-09-19T22:50:59.123Z. This is not the publication date.

Observed changes

AIIC observation times, not verified publisher revision times. Up to eight recent revisions.

2026-09-20T23:22:28.549Z

  • publishedAt: Not provided2025-02-10T00:00:00.000Z