Risk signals for models you control.

Capsa adds model-level and output-level risk estimates to supported models you run, giving your application more information about each prediction.

Capsa provides a proprietary risk-estimation capability within Themis’s broader decision-layer approach. For supported models, these signals inform policies governing what proceeds, what needs more evidence and what should reach an expert.

Evaluate Capsa Read the documentation

  • Automate the clear cases

    Let more routine work proceed under policies you define.

  • Spend review where it counts

    Focus experts and additional checks on the decisions that need them.

  • Put evidence where it matters

    Choose when another document, simulation or experiment is worth its cost.

Add risk estimation to a supported model.

Load a supported model, wrap it with Capsa, and use the returned risk estimate alongside each prediction.

  1. 1. Load your model

    Start with a supported model in your existing framework.

  2. 2. Add risk estimation

    Capsa wrappers apply the model modifications needed for the selected uncertainty method.

  3. 3. Use the additional signal

    Use the resulting risk estimates alongside predictions to inform your application’s next step.

See where the model is unsure.

Prioritize review

Identify ambiguous inputs and potentially mislabeled examples for closer inspection.

Report uncertainty during inference

Report uncertainty with every output at runtime and automate quality assurance by filtering low certainty output or requesting human intervention.

Detect Failures

Capsa automatically detects prediction risk. In this example, Capsa correctly highlights the passing bus, which sits outside the training set.

Note: Bright colors represent areas of high uncertainty flagged by Capsa that were missed by the initial model.

Quantify multiple types of uncertainty.

  • Aleatoric Uncertainty

    What the model can’t understand from data due to ambiguity and irreducible noise like errors.

  • Epistemic Uncertainty

    What the model doesn’t know due to limited knowledge or data.

  • Vacuitic Uncertainty

    What the model can’t understand due to latent feature imbalance.

Solutions for every stage of the ML workflow.

  • Data cleaning

    Optimize data labeling costs by finding incorrect or noisy labels.

  • Data curation

    Identify missing data to intelligently curate datasets.

  • Model conversion

    Add a risk score to a model you already run.

  • Risk-aware training

    Optimize models to overcome their deficiencies.

  • Quality control

    Targeted validation on high-risk scenarios.

  • Anomaly detection

    Quickly detect out-of-distribution events.

From risk signals to operating decisions.

Compare your current workflow with a policy that determines what can proceed, what needs another check, and where to focus expert review. A policy can deny an action that is not permitted, or abstain when the evidence is insufficient.

Working with frontier APIs? Themis brings decision-policy, model and production-engineering expertise to your workflow.

Discuss your workflow