
Sentinel-EVC
Final-action validation and verifiable execution
Between policy and controller: final-action validation, single-use authorization, and independently verifiable evidence.
Explore researchRESEARCH
From computation in hidden states to reliability in the real world—and the research process itself.
All 9 research projects

Final-action validation and verifiable execution
Between policy and controller: final-action validation, single-use authorization, and independently verifiable evidence.
Explore research
Compositional computation in latent representations
Explores compositional computation in latent representations, focusing on reasoning depth, state stability and learning.
Explore research
Causal credit and capability consolidation
Using active causal experiments from the same state to identify the contribution of intermediate operations, then studying how repairs can become model capabilities.
Explore research
Model collapse and feature detection
Investigating the limits of recursive training, rare information, and feature detection, including information that remains hidden within models.
Explore research
Automated research and recursive improvement
Connecting questions, literature, search, refutation, and frozen experiments so that sustained exploration accumulates evidence future work can build on.
Explore researchPricing exploitable structure before black-box search
Before black-box search, ask what structure an instance offers, what finding it costs, and when the evidence calls for an uncertain answer.
Explore research
Normalization: representation and feedback
Studies when batch normalization works through variational selection and feedback tracking.
Explore research
Initialization and Signal Propagation
Study what individual units and backward signals experience beyond average activation scale, and how depth changes input distinguishability.
Explore research
Reading Tasks from Behaviour
When a task label is observed only through a trajectory, what information comes from geometric differences and what comes from time direction?
Explore researchResearch manuscripts currently in development. These are presented as working papers.
Studying how information available at policy interfaces constrains runtime failure detection.
Related researchExploring feature-detection conditions and error bounds in superposition and sparse autoencoders.
Related research