Models Page

Models Page

• Updated on Jun 22, 2026

• Published on May 6, 2026

• 4 minute(s) read

The Models page provides a centralized location for managing models trained on your instance. In this article, you'll learn how to navigate the page and understand the information displayed for each model.

Accessing the features mentioned in this article
Your access to some of the features mentioned 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.

Accessing Models

Navigation changes in v42.0.2 and later Starting with v42.0.2, Models became a standalone category in the main navigation menu. In earlier versions, model-related pages are available under Library > Models.

To access the Models page, go to Models and select the model type you want to manage:

• Classification models
• Vision Language Models (VLM) Field Extraction
• Identification models
  • Field Identification models
  • Table Identification models
• Text Classification models
• Transcription Models.

Each model type provides different functionality and displays information specific to its purpose. The following sections describe the available model pages and the information shown for each model type.

Classification Models tab

By default, the Models page opens on the Classification Models tab.

• You can filter the Classification models table by release with the Filter by release drop-down list, which is located on the right-hand side of the page.
• Access the model management page for a particular model by clicking on its name in the table.
• See the number of Classification models available in your instance.

The Classification models table contains the following columns:

| Column | Description | | Model | Classification model’s name. | | Compatible Releases | Indicates the number of releases that the Classification model can generate predictions for. Learn more in Semi-structured Document Classification. | | Status | Model’s current state (e.g., Needs Training or Live). | | Date Deployed | The date the model was deployed. |

Learn how to train classification models in TDM for Classification Models.

VLM Field Extraction tab

Available in v42.3 and later

The VLM Field Extraction tab provides an overview of all Model Definitions, associated with specialized VLM models. Learn more in ORCA (Optical Reasoning and Cognition Agent) VLMs.

The Model Definitions table contains the following columns:

| Column | Description | | Scope | The data or objects the model operates on (for example, a layout or set of fields). | | Task | The type of problem the model is trained to solve. | | Type | The model family used for this task and scope. | | Compatibility | Shows compatibility between the current product version and the latest deployed model for this definition. | | State | Shows whether the model is Live or Inactive. | | Training Status | The status of the current model training. | | Date Deployed | The timestamp of the last deployment for this model definition. |

Learn more about VLM Field Extraction in TDM for ORCA VLMs.

Identification Models tab

The Identification tab provides an overview of all Field ID and Table ID models associated with semi-structured layouts in your instance. Learn more in Identification Models Overview.

The Identification models table displays the following columns:

| Column | Description | | Model | Shows the name of the model’s layout. This column is sortable. | | Type | The type of locator models available for the layout:
- Field Identification model

- Table Identification model | | Model Status | The current status of the model:
- Needs Training

- Live | | Training Status | - Needs Training

- Pending

- In Progress

- Failed

- Canceled

- Finished

- Last trained on [date] |

Learn more in TDM for Identification Models.

Text Classification tab

Text Classification models allow you to classify freeform text in documents, emails, and more. Go to the Text Classification tab to access this table.

• You can import or create a Dataset by clicking on the buttons located above the table. The number of Text Classification datasets appears at the top.

| Column | Description | | Dataset Name | The name of the training data you’ll use for the model. | | Date Created | The date the model was created. | | Source UUID | UUID code of the model. |

To learn more, see Text Classification.

Transcription Models tab

The Transcription tab provides information about the transcription models available in your instance. Learn more in Transcription Models Overview.

| Column | Description | | Transcription Model | The name of the transcription model. | | Flows | The number of flows using this transcription model. Clicking this number reveals a list of the flows. | | Model Types | The types of specialized models that have at least one QA record available to them (e.g., Latin Semi-Structured, Checkbox, Signature). |

To manage training datasets, review model performance, and retrain models, see our Training Data Management (TDM) section.

Overview of Machine Learning Models

• A machine learning model that automatically identifies a document’s type—Structured, Semi-structured, or Additional—and matches it to the correct layout. This classification helps Hyperscience process different document types accurately without manual intervention. Learn more in Classification models.

• Models that understand both the text and images in a document. They combine what’s written with where it appears on the page to help the system read and extract information more accurately. Learn more in Visual Language Models.

• A machine learning model in Hyperscience that learns where fields are located in semi-structured documents. It uses examples from training to predict the position of each field on a page so the system can extract the right data. To learn more, see Identification models.

• A machine learning model in Hyperscience that learns where cells and rows are located in semi-structured documents. It uses examples from training to predict the position of each cell and row on a page so the system can extract the correct data. Learn more in Identification models.

• A machine learning model that reads unstructured text—like comments, emails, or notes, and assigns them to predefined categories. This categorization helps automate decisions and organize freeform text based on business rules.

• A machine learning model that automatically extracts text from scanned document images. It supports both printed and handwritten text. When the model’s confidence in the extracted text is low, the system generates a Transcription task for human review to ensure accuracy. Learn more in Transcription models.

• A configuration object used to manage Vision Language Models (VLMs). Model definitions define a model's scope, task, compatibility, deployment status, and associated model versions. Learn more in Model Definitions.

• A group of documents used to help the system learn or improve. Datasets are used for training, testing, or evaluating how well the system reads and extracts information.