Dynamic Semantic Evolution Graph — carrying the overlapping-community work toward interpretable, graph-structured semantic control.
My research has moved from structural reliability (Triad) to scalability (Highway). Building on that work, I am proposing a third direction — interpretability and control. In today's large models the internal state is a single, entangled vector: powerful, but hard to inspect and harder to steer.
DSEG asks what changes if we explicitly define every basic decision unit of the internal state — instead of leaving it as one opaque black-box function.
Give the representation a structure you can read — a graph of interpretable units and the relations between them.
Treat the internal state not as one entangled vector, but as a set of discrete, interpretable decision units — each a small, nameable carrier of one part of the computation.
Model the structure between those units, so the graph of relations — not a single opaque activation — is what carries the reasoning forward.
Because the structure is explicit, the representation becomes something you can inspect, audit, and steer by construction — rather than probe after the fact.
If representations were structured this way by construction, interpretability and control would stop being post-hoc add-ons and become properties of the model itself. I see DSEG as a graph-structured semantic control layer that complements — not replaces — existing architectures, and as the natural continuation of the structural thinking behind Triad and Highway.
This is early, exploratory work that I am developing hands-on. A preprint is in preparation; I will link concrete findings here once they are public.