Skip to main content

Reveal Review Publication

COSMIC (Cognitive Machine Coding)

COSMIC (Cognitive Machine Coding) is the next generation of technology assisted review from Reveal AI. The Reveal AI COSMIC feature is an optional feature. In order to utilize COSMIC, there should be at least one COSMIC Group created in the storybook.

Users can add a new COSMIC Group two ways after creating or opening a storybook.

  1. Use the COSMIC SETTINGS tab.

  2. Use the Models dropdown in the thread viewer under the TRAINING tab.

Reviewers can train the COSMIC model by reviewing documents using different queues. COSMIC queues are designed to provide documents to reviewers for tagging.

You can use the COSMIC panel to review and tag documents.

  1. Primary COSMIC Group Selector - Click the dropdown to select the primary COSMIC group when you have more than one COSMIC group in the current storybook.

  2. Primary COSMIC Group Tags - Sets of tags used for the primary COSMIC Group, based on the labels set for the COSMIC group.

  3. Secondary COSMIC Groups - In the next row(s) appear tagging buttons for the other available COSMIC groups. These allow you to set tags to the current document without switching the focus of the primary COSMIC group.

  4. Include / Exclude Selector - By default, all documents are included in a user’s model. However, if the user believes a document or a set of documents are irrelevant in building a model, they may choose to exclude documents from the model.

  5. Segment Level COSMIC Tags - Reviewers can also assign a tag at the segment level for the primary COSMIC Group. The segment level COSMIC tag is located on the top right corner of each segment.

  6. COSMIC Cycle Information - By clicking the COSMIC SETTINGS tab you can review the current status of the COSMIC projects.

  7. COSMIC Notifications - When a reviewer finishes the last document in the current queue, the system will display a notification based on the readiness of the model.

High Precision Classification (HPC) is a highly-focused method of model training built on user coding of document snippets rather than full documents to assess relevance. Results are continuously measured against standard model retrieval to automatically determine the optimal model type for the current review.

HPC applies the COSMIC tagging method of supervised learning in a more granular way. Instead of addressing all content at the document level, HPC looks at selections (chunks of text) within the document that a user highlights. This gives the HPC model a more focused picture of what within a particular document makes it relevant so that it may then score the remaining documents in more accurately.

The default Autodetect mode automatically selects the better of the COSMIC document and highlight-weighted High Precision scores in presenting model results.

User can access COSMIC Settings in the Navigation Bar and click Report or Settings to open COSMIC Mission Control.

  1. COSMIC Report - The COSMIC report tab shows the status of COSMIC, including the Cycle Info, Statistics table and the control set.

  2. Settings - The SETTINGS tab provides various settings used to configure COSMIC.

  3. Stability History, Agreement and Review Actions - The STABILITY HISTORY tab shows the results each time the system recalculates stability. The results can be Still LearningApproaching StabilityStabilized and Still Learning (Data Load). For the system to reach stability, it has to encounter Approaching Stability 3 times in a row. The system automatically sets stability to Still Learning (Data Load) each time new data has been added to the storybook.

  4. Assigned To Report - The ASSIGNED TO REPORT tab shows documents currently assigned to any reviewers.

  5. Correlation Matrix - Correlation Matrix provides a cross examination of COSMIC scores from all COSMIC groups.

Admin rights are required to publish a model to the COSMIC model library. See Admin Guide Section 1. Storybook Settings > F. COSMIC Groups. All other COSMIC model access is available to the end-user.

  1. Accessing the COSMIC Model Library - You access the COSMIC Model Library through the User dropdown menu by choosing Model library.

  2. Reveal AI Pre-trained Starter Models - Reveal AI comes with a growing number of pre-trained starter reference models. These models are ready out of the box to apply to your data. The list of models is augmented as new versions of Reveal AI are released.

  3. Import COSMIC Model - Import a model to the existing model library if you want to use the model in a different Reveal AI environment.