SOPHIA XT
Research · visualiser

Give every word a place,
then let it spread.

LOTU puts tokens on a lattice. Each word is hashed to a cell and becomes a source of probability. The field then diffuses, decays and is topped up by the sources every step, and the picture shows where the mass collects. It is a way to see the lattice mechanics. It is not a model and it does not score real text.

Figure 1 A probability lattice, simulated live Illustrative
step 17 / 40 mass 49.4 mean source confidence 0.70 12 tokens placed
Orange is high mass, navy is none. White squares are the tokens, numbered in order. The diffusion is the equation below, run once per step on the lattice you choose. Each token's confidence comes from a hash of the word and the temperature slider, so the same text always gives the same picture.
How it works

One equation,
three moves.

The lattice holds a probability density P. Each step it changes by a diffusion term that spreads mass to neighbouring cells, a decay term that removes a fraction, and source terms where tokens sit:

∂P/∂t = D∇²P − λP + ΣSᵢ(z, t)

D is the diffusion coefficient (0.2 here), λ the decay rate (0.035) and Sᵢ the source for token i, scaled by its confidence.

Token anchoring

A word is hashed to a coordinate, and that cell becomes a source. Two words that hash close together reinforce each other, and a lone word leaves a single hot spot with a halo that widens as the steps run.

What the readouts mean

Mass is the sum of P over the lattice, so it rises while sources feed it and levels off when decay balances them. Mean source confidence is the average of the per-token values the hash and temperature produce. Higher temperature lowers every source, which lowers the plateau.

Address, not meaningIn our own ablation of LTMi-XT, the lattice coordinate behaved as an address and carried no semantic geometry. LOTU shows the address space, and nothing here claims more than that.
What this page isA visualiser written to make the lattice idea easy to see. The coordinates come from hashing, the confidences from a formula, and the diffusion is the real equation above. The picture shows how the mechanism behaves. It reports nothing about any trained model.