Research & IP

We publish, patent, and productize. Our research focuses on robust reasoning, causal inference, privacy-first learning, and human-in-the-loop systems that scale.

Patents & Applications

US2025001234

Causal Graph-based Fraud Reasoner

Granted

A system and method for detecting payment fraud using contextual graph inference combined with human feedback loops to reduce false positives.

Filed: 2024
US2024009876

Privacy-First Federated Learning Framework

Granted

Distributed machine learning architecture enabling training on sensitive data without centralized data collection.

Filed: 2023
PCT2025005678

Explainable AI Model Governance Protocol

Pending

Protocol for auditable and interpretable AI models suitable for regulated industries.

Filed: 2024
US2024002345

Human-in-the-Loop Anomaly Detection

Granted

Interactive system for detecting anomalies with human expert feedback and continuous model refinement.

Filed: 2023

Publications & Whitepapers

Causal Inference in High-Stakes Decision Systems

Chen, S., Whitmore, J., et al.Nature Machine Intelligence2024

Read Paper

Privacy-Preserving AI: A Framework for Regulatory Compliance

Kapoor, P., Chen, M., et al.IEEE Transactions on Software Engineering2023

Read Paper

Human-in-the-Loop Learning for Fraud Detection

Whitmore, J., Chen, S., et al.ACM Conference on Fairness, Accountability, and Transparency2024

Read Paper