---
title: "Labs, AI research at StrucTime"
description: "Labs trains compact language models and a world model from scratch, on its own machine, and publishes how it measures them."
canonical: https://structime.com/en/research/
language: en
last_modified: 2026-10-21
publisher: "AEON Systems (SIREN 993102821)"
source_format: html
---

# Labs trains its own models.

> Labs trains compact language models and a world model from scratch, on its own machine, and publishes how it measures them.

Source : https://structime.com/en/research/
Publisher: AEON Systems (SIREN 993102821) · StrucTime

Labs

- Trained from scratch
- No customer data
- Dedicated machine

Work

## Two lines.

Language and the dynamics of systems are not handled the same way.

### Language

**What it reads**

Text.

**What it predicts**

What comes next.

Compact models, organised as experts by domain, designed to run on the device.

Language models

### World

**What it reads**

The state of a system.

**What it predicts**

The next state.

The world model of Furnace, which speeds up the exploration of a site’s futures.

World models

Status

## What exists today.

| Object | Nature | Status |
| --- | --- | --- |
| Language models | Compact, experts by domain | In preparation |
| World model | Dynamics of physical systems | Ongoing, plugged into Furnace |
| Dataset classification | Public levels and audit tool | In preparation |
| Publications | Papers, weights, code | Nothing published yet |

Data

## A dataset gets a rating, like a power supply.

Data quality weighs on a training run more than any other setting. We are preparing a public classification: each level bounds the error rate measured on a hand-audited sample.

The audit tool will be open and the sample published. A label falls as soon as a third party finds more errors than its bound.

1. Bronze
2. Silver
3. Gold
4. Platinum
5. Titanium

Open questions

## What we do not know how to do.

### Recovering the hidden state of a system whose equations are unknown.

Nobody manages it today, us included: published work stalls at the same point.

### Making a world model state what it has found.

A language model bolted on top would rephrase without understanding the system.

### Keeping a simulation stable in high dimension.

Over a long horizon, a trajectory ends up diverging. We have not measured it properly yet.

Method

## How we measure.

### The yardstick comes from outside.

Each model must beat a classical method: gradient boosting, a heuristic or an exact algorithm. Otherwise it has learned nothing.

### Accuracy has a cost.

We measure accuracy per parameter and energy per inference, as well as the score.

### The threshold is set beforehand.

A threshold set afterwards turns the measurement into a negotiation with the number obtained.

### Failures stay on record.

Each one is logged with its measurement and date. We have abandoned several leads.

### Brioche, our training tool

Every run restarts identically and resumes at the exact step after an interruption.

## Research ends up in a product.

Furnace explores thousands of futures of a site. Our world model lets it explore more of them, faster.