Course / Lecture 01 / Lab Lab 01

Sudoku: rules repair perception.

A four-clue 4×4 puzzle. The neural part reads the clues with noise; the symbolic part enforces the rules. Switch modes, turn up the noise, and watch what each part contributes.

4×4 puzzle 4 clues · minimal 288 candidate solutions No install · runs in the browser

The Sudoku lab

Press Solve to run the current mode.

Board legend. Shaded cells with an orange dot are clues. The thin bar under a clue is the neural module’s confidence in its own read; red means the read disagrees with the true clue. Teal digits are filled by the symbolic solver.

Mode

55%

What the neural part reads

CellReadp(read)Status

What happened

Press Solve to see the perception, the candidate count, and the result.

Why this is NeSy

The neural part supplies digit probabilities; the symbolic part supplies the row, column, and box constraints. The rules are not a post-hoc filter: they change which solution is selected. At low noise, the perception is reliable and the rules are almost redundant. At high noise, the rules can correct a misread — or choose a different valid solution, because four clues are not enough to identify which read is wrong.

The puzzle has four clues, the minimum for this solution. There are 288 valid 4×4 grids; the solver ranks them by how well they explain the perceived clues, then picks the best. That ranking is the interface.

WHAT TO NOTICE

Three regimes, one lesson.

REGIME 01 · LOW NOISE

Perception is enough

The neural read is correct; the solver fills the grid. The symbolic part is doing real work, but the interface is quiet.

REGIME 02 · MEDIUM NOISE

The rules repair a read

A clue is misread, but the other clues and the rules make the true digit the best explanation. This is the NeSy sweet spot.

REGIME 03 · HIGH NOISE

The rules choose a different world

With four clues, a misread can make another valid grid the best explanation. The output is still a valid Sudoku — just not the one you started with. That is not a bug; it is the limit of the information.

What the lab is not

It is a 4×4 toy with a simulated perception module, not a benchmark. The point is to make the interface visible: probabilities in, constraints over them, a solution out. The papers in §6 use the same idea at a much larger scale.

Back to the seven worked examples · Read the formulation again