September 22–30, 2026 · Toronto

Understand the system.
Predict what’s next.

Ten black-box simulators. A limited experiment budget. A week to turn careful research into models that can see further ahead.

An individual competition. Research with Gemma and submit your own forecasters.
A connected miniature worldAn illustrated town with a hospital, power station, reservoir, delivery warehouse, homes, and moving traffic. Decorative illustration of the competition's systems. Small interventions. Lasting effects.
THE RESEARCH

Learn by changing things.

You choose the experiments. Your models explain what follows.

01

Investigate

Read the system briefs, change the controls and measure the response. Use your 2,000 simulator steps per system to investigate the questions that matter.

02

Build a model

Use Gemma to interpret documents, compare hypotheses and develop code. Get your API key from Google AI Studio; Gemma calls do not spend simulator steps. Fit numerical models to the data you collect.

03

Forecast further

Upload one ZIP with the systems you’re ready to submit. Each forecaster predicts 4,000 steps from an initial observation and a future action schedule.

HIDDEN EVALUATION40 × 4,000

episodes × forecast steps
for every system

Same physics. Unfamiliar histories.

Discover rules that hold
beyond your experiments.

Every participant studies the same underlying parameters and mechanisms. Evaluation changes the starting observations and intervention schedules, using the same initialization rules.

Hidden episodes cover sustained operation, action order, recovery spacing and combined controls. Your uploaded model forecasts the complete trajectory without further observations or network access.

Read the scoring rules
KEY DATES

Plan your research week.

September 2026 · All times are Toronto local time.

SEP22

Development opens

Start researching and submit models for public evaluation.

SEP28

Final submissions open

At 12:00 noon. Upload your final models explicitly; public submissions do not carry over.

SEP30

All submissions close

At 12:00 noon. Final standings follow at a successful sweep once selected evaluations finish.

The public leaderboard opens September 23 at 9:00 a.m. Toronto time. Subsequent standings are swept every six hours at midnight, 6 a.m., noon, and 6 p.m. Toronto time; unfinished selected evaluations delay publication.
Three accepted uploads per system per day, shared across public and final submissions.

Start with your first question.

The kit includes the research client, system briefs and a numerical baseline.

Get started