Research Map

Representation, validation, residual learning.

The model should not carry the whole system. Keep artifacts, state, relations, validators, and review loops outside the learned part.

Cursed regions

Low-abstraction artifacts, scarce data, and unstable objectives need measurement before model selection.

Applied epistemics · DXF/CAD proof

Cognitive security

Adversarial information systems need evidence paths, confidence, context, and operator agency.

Cognitive security · T-UEBA proof

Graph boundaries

A graph is the relation layer. It works after object identity has been stabilized and validators keep the artifact honest.

Graph modeling · RAM Labs

Agent environments

Post-training depends on state, tools, traces, verifier failures, and feedback close to the action that caused the failure.

Agent environments · AIxCC / DL-Patcher

Physical AI

CAD and AEC workflows need exact artifacts, stable object state, typed relations, hard validators, learned residuals, and review.

Mechanical roots · Manufacturing proof