Research

Our research spans two fundamental areas that are critical to a future where AI proliferates and permeates every aspect of our lives.

Model Informatics

The study of models as complex information systems. We investigate how AI models encode, process, and transform information, developing frameworks to understand their internal representations, behaviors, and capabilities. This includes analyzing model architectures, training dynamics, and emergent properties to create comprehensive profiles of AI systems.

Verifiable Computation

The development of techniques to programmatically verify execution of complex systems. We create cryptographic and algorithmic methods that enable automated verification of AI model behaviors, capabilities, and integrity without requiring access to internal parameters or training data.

Read Our Latest Publications

Behavioral Fingerprints for LLM Endpoint Stability and Identity

We introduce Stability Monitor, a black-box stability monitoring system that periodically fingerprints an endpoint by sampling outputs from a fixed prompt set and comparing the resulting output distributions over time. In controlled validation, Stability Monitor detects changes to model family, version, inference stack, quantization, and behavioral parameters. Submitted to CAIS 2026 System Demonstrations.

arXiv | PDF

Identifying and Banning AI Developed by Foreign Adversaries

Exploring methods and frameworks for identifying AI systems developed by foreign adversaries and implementing appropriate policy responses.

White Paper

ZKTorch: Open-Sourcing the First Universal ZKML Compiler for Real-World AI

Introducing ZKTorch, the first universal zero-knowledge machine learning compiler designed for real-world AI applications.

White Paper | code

Security Assurances for AI in High-Stakes Environments using Verifiable Computation

A comprehensive white paper exploring the critical importance of AI model verification, behavioral fingerprinting, and establishing trust in AI systems for enterprise deployment.

White Paper

Introducing Stability Arena and The Seven Metrics of Model Hosting

The evolving landscape of LLM agents requires a fundamental shift in how model hosting infrastructure is measured. Introducing Stability Arena, a public monitor designed to track Identity, Stability, and Fidelity — three new, essential metrics for the agent era.

Substack

Reliability ≠ Stability

Just because an AI is generating tokens reliably doesn't mean those tokens are the right ones. Exploring why standard reliability metrics fall short and why stability — behavioral consistency over time — is what actually matters for AI-native applications.

Substack

Building a Vocabulary for AI Assurance — Part II: Verifiability and Accuracy

Establishing ground truth via verifiability and accuracy. Exploring how to prove the authenticity of model outputs and ensure correctness — two prerequisites for meaningful AI assurance.

Substack

Building a Vocabulary for AI Assurance — Part I: Explainability and Interpretability

Establishing clarity around the terms used to discuss AI assurances. Part I tackles explainability and interpretability — what they mean, how they differ, and why the distinction matters.

Substack

What is Model Informatics? What Does It Mean to "Verify" AI?

Inspired by bioinformatics, Model Informatics is the systematic study of AI models as complex information systems. Exploring the tools and frameworks needed to understand, recognize, and verify properties of AI models.

Substack

Agents, Task Time Compute, & Task Time Marketplaces

Agents coordinating to complete complex, multi-step tasks for users and using a marketplace to bid out individual tasks to specialty agents.

Substack

The Security Evolution of Core Technologies: What It Means for AI (Part I)

There is a consistent pattern of increasing the robustness of security features for core computing technologies. AI shouldn't be any different. Walking through how previous core technologies increased security as they gained adoption.

Substack

Product Development in the Age of AI

Developing on top of probabilistic compute changes how we build software, software products, and eventually anything. Exploring the challenges product leaders face around model uncertainty and planning.

Substack

Transparency vs Interpretability

While we may not know how a model generates its result, we should still know what was asked of the model to get the result. Examining the critical differences between transparency and interpretability.

Substack

Which Model Am I Getting?

Just reviewing outputs from a model won't tell you which model you're using. Even if your API provider says which model you're using, you have no way to verify it independently.

Substack

VAIL Use Case: Verifiable Evals

How can you prove a model passed an eval with the reported score? Exploring why benchmark results need cryptographic verification and how VAIL makes that possible.

Substack

AI is like Sugar

The number of AI models is growing fast and that's good. Drawing parallels between AI proliferation and sugar adoption to understand societal impacts and dependencies.

Substack

Part 4: Stochastic Computation Needs Verifiable Computing

Since AI models are stochastic machines, we can't predict their exact outputs. Exploring why verifiable computing is essential to ensure trust in probabilistic AI systems.

Substack

Subscribe for More Insights

Stay updated with the latest research, insights, and thought leadership on AI and model informatics.

Visit our Substack →