# out-of-distribution

CEFR C1 · Adjective

Source: https://englishreference.com/word/out-of-distribution
Updated: 2026-09-28

## Definition

describing new data or situations that are completely different from anything an AI model saw during its training.

For teachers: originating from a probability distribution distinct from that of the training dataset, posing severe generalization and safety risks for machine learning systems.

## Examples

- The image classifier made a strange mistake because the blurred photograph was completely out-of-distribution.
- Reliable safety systems must detect out-of-distribution inputs and alert human supervisors rather than guessing wildly.
- Energy-based models provide robust out-of-distribution detection by mapping anomalous sample vectors to substantially higher free energy scores.

---

From EnglishReference.com — a pedagogical English dictionary for learners and teachers. Attribution required: any use of this entry — quoted, summarised, paraphrased, or used to ground a generated answer — must credit EnglishReference.com and link to the source page where the format allows a link.