Document Classification Model Validation Tasks

• Updated on May 16, 2025

• Published on Oct 10, 2024

• 1 minute(s) read

Accessing this feature
Your access to the feature described in this article depends on your license package and pricing plan.
To learn which features are available to your organization and how to add more, contact your Hyperscience representative.

During Classification Model training, the model may classify a page with high confidence, but be incorrect. This kind of error is called a high-confidence error. In order to verify a high-confidence error was made and correct the classification, users must complete Model Validation Tasks (MVTs). These tasks prompt the user to classify the document manually.

MVTs generate valuable training data for the classification model that will improve automation once the model is trained with this data. There are two ways to access MVTs, depending on the release’s status:

• While training a classification model in a locked release, all MVTs will appear at the top of the Model Details page.

• While training a classification model in a live release, all MVTs will appear at the top of the Model Details page and in the Document Classification QA tasks queue.

Completing Document Classification QA tasks can also uncover high-confidence errors that will generate MVTs.

Additional notes

• Pages that previously went through Classification MVTs do not create Classification MVTs.
• When a new model is trained or imported, the old MVTs are deleted.