ResearchTechnical note 3
Learned at 32 bits. Exact at 4,096.
Neural networks tend to fail on inputs longer than the ones they were trained on. METRON learned its laws on 32-bit numbers and then answered exactly on numbers 128 times wider, with nothing relearned.
- Measured
- 13 November 2026
- Learned at
- 32 bits
- Tested up to
- 4,096 bits
- Record
- 116
At a glance
exact answers across addition, subtraction, comparison and multiplication.
wider than anything seen during learning, with no relearning.
laws changed between 32 and 4,096 bits. They are frozen and fingerprinted.
In plain words
A child who learns to add two-digit numbers can add twenty-digit numbers the same way: the rule does not change, only the length. Most neural networks cannot do this. METRON can, because what it learns is the rule itself.
For engineers
Bit-level laws for addition, subtraction, comparison and the stages of multiplication were learned at w = 32 and frozen. They were then applied at w = 64, 128, 256, 1,024 and 4,096 through a structure declared in advance, on uniform, hard and publicly drawn operands.
Why it matters
Learn once, deploy at any size. The cost of learning does not grow with the size of the problem, which is the opposite of how model training scales today.
MTRMETRON is AIDON’s exact co-processor. It learns laws from data, proves them and runs them, alongside a neural model or on its own.
The bottleneck
Trained on short inputs, wrong on long ones.
Length generalisation is one of the best-documented weaknesses of neural networks. A model that is accurate on the lengths it was trained on degrades, often to zero, as the input grows beyond them.
The usual remedy is more data and a larger model for every new length. That is a recurring cost, and it never reaches certainty.
Result
One lesson at 32 bits. Exact up to 4,096.
Operand width in bits, logarithmic scale
Fig. 1 Share of exact answers at each operand width, the four operations together. The laws were learned at 32 bits and frozen; every width to the right was answered without relearning anything.
| Operand width | Addition | Subtraction | Comparison | Multiplication | Width vs learning |
|---|---|---|---|---|---|
| 32 bits | 2,088 | 2,088 | 2,088 | 2,088 | 1× |
| 64 bits | 2,088 | 2,088 | 2,088 | 2,088 | 2× |
| 128 bits | 2,088 | 2,088 | 2,088 | 2,088 | 4× |
| 256 bits | 2,088 | 2,088 | 2,088 | 2,088 | 8× |
| 1,024 bits | 2,088 | 2,088 | 2,088 | 2,088 | 32× |
| 4,096 bits | 2,088 | 2,088 | 2,088 | 2,088 | 128× |
Across both public draws of the test, the sealed total is 56,256 exact answers out of 56,256.
Method
How the laws are reused
- Learnthe laws, from 32-bit examples
- Freezethe laws are fingerprinted and never touched again
- Applythe same laws serve every wider number
The laws are learned once, from examples of 32-bit operations.
They are frozen. From this point on, no parameter of the system changes.
They are applied at every width, through a structure declared before the test. Nothing is tuned to the new sizes.
Controls
What was checked
Public randomness
Part of the operands came from a public randomness beacon round published only after the test had been registered. Nobody, including us, could have chosen them.
Hard cases
40 hard operand pairs per cell, chosen to stress the operation, all answered exactly.
Altered laws
With the laws deliberately altered, errors appear in every operation. The test can fail, and it detects when it should.
Reproduction first
Before the test, 35 earlier results were reproduced and matched one by one.
Open questions
What this opens
- Widths beyond 4,096 bits and operations beyond the four measured here.
- The same learn-once behaviour for structures that are not arithmetic.
Fields of application
Where it fits
- Wide-integer arithmetic for cryptography, where 2,048 and 4,096 bits are everyday sizes.
- Processors and accelerators whose word size changes from one product to the next.
- Any system that must keep working when the input outgrows the training data.
Record
How this result is kept
- Record
- 116
- Run
- 13 November 2026, 39 min 13 s
- Sample
- 6 widths; 4 operations; 2,088 operand pairs per cell, plus a second public draw
- Measurement file
- SHA-256 6fcdfe2054326d832ef222fcdaeb11fc324de08d297666c7d4520a026188c4fa
Every figure on this page was read by a program from the raw measurement file, not typed. The fingerprint identifies that file: when it is disclosed, anyone can check that it is the same one.
Contact
Talk to the founders
Get in touch. We would be glad to share our ideas and walk you through the results, the proof and the measurements.