cd /news/neural-networks/wangnet-1-8-mb-zero-dependency-numbe… · home topics neural-networks article
[ARTICLE · art-130674] src=github.com ↗ pub= topic=neural-networks verified=true sentiment=↑ positive

WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages

Developer GraafHenk released WangNet, a 1.8 MB JSON neural network with roughly 100 lines of pure Python standard-library inference code that adjudicates whether a number is Numberwang across 11 languages, requiring only Python 3.8 or newer. The 80,804-parameter character-level model scores 88.9% over 486 held-out adjudications (macro-F1 0.896) against a ceiling of roughly 98%, with arithmetic on unseen operands its weak spot at 44–72%. The project is MIT-licensed and also runs as a hosted demo on Hugging Face Spaces.

read3 min views3 publishedSep 15, 2026
WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages
Image: Michielbdejong (auto-discovered)

A small neural network that decides whether a number is Numberwang.

The whole model is a 1.8 MB JSON file and the inference code is about 100 lines of pure Python standard library — no PyTorch, no NumPy, nothing to install. Clone it and run it.

$ python3 numberwang.py 22
22... THAT'S NUMBERWANG!  (confidence: 99.3%)

$ python3 numberwang.py "45 - 44"
45 - 44... That's Wangernumb! Rotate the board!  (confidence: 100.0%)

$ python3 numberwang.py "hello how are you"
hello how are you... That's not even a number. It can never be Numberwang.  (confidence: 100.0%)
git clone https://github.com/GraafHenk/numberwang
cd numberwang
python3 numberwang.py 22

Run it with no arguments for an interactive session:

$ python3 numberwang.py
Welcome to Numberwang! (ctrl-c to stop playing Numberwang)
> zweiundzwanzig
zweiundzwanzig... THAT'S NUMBERWANG!  (confidence: 100.0%)
> shinty-six
shinty-six... That's not Numberwang.  (confidence: 100.0%)

Requires Python 3.8 or newer. That's the only requirement.

from numberwang import load_model, wang_probabilities

model = load_model("model.json")
probs = wang_probabilities(model, "forty-seven")

verdict = max(range(4), key=probs.__getitem__)
id verdict
0 That's not Numberwang.
1 THAT'S NUMBERWANG!
2 That's not even a number. It can never be Numberwang.
3 That's Wangernumb!
input behaviour
42 ,sixty-six ,12345 digits or words
zweiundzwanzig ,veintidós ,tweeëntwintig eleven languages, accents optional
5*2 ,96 divided by 2 ,twelve plus four arithmetic, judged on the result
45 - 44 ,double four ,eins anything worth 1 or 44 rotates the board
-7 ,4.5 ,£5 ,50% ,9:30 negatives, decimals, currency, units, times
XLIV ,twenty-third ,22nd Roman numerals and ordinals
fortnight ,vierendelen ,september words built on a number, judged as that number
achtneming ,often ,money words that merely contain one are not numbers
shinty-six ,twentington fictional numbers are numbers too
bonjour ,hello how are you no numeric content — can never be Numberwang

A number's wangness is a property of the number, not the language it is said in: four, vier, quatre and cuatro all get the same verdict.

chars → Embedding(32) → Conv1d(128, k3) → ReLU
      → Conv1d(128, k3) → ReLU → global max pool
      → Linear(128) → ReLU → Linear(4) → softmax

80,804 parameters. The network reads characters directly — there is no tokenizer, no normalizer and no rules engine at inference. Digits, operators, canon verdicts and the eleven languages are all held in the weights, and model.json contains the lot.

A hosted version runs on Hugging Face Spaces. To run the same demo locally:

pip install -r requirements.txt
python3 app.py

gradio is needed only for the demo. The model itself never needs it.

88.9% over 486 held-out adjudications (macro-F1 0.896), against a ceiling of roughly 98% — about 2% of training labels are inverted, in accordance with long-standing adjudication practice.

class precision recall F1
not Numberwang 0.820 0.885 0.851
Numberwang 0.919 0.900 0.910
not a number 0.951 0.830 0.886
Wangernumb 0.968 0.909 0.937

Arithmetic on unseen operands is the weak spot, at 44–72%. The network memorises rather than computes, so small common expressions like 5*2 are reliable while 904 * 3 is an educated guess. If arithmetic correctness matters, evaluate the expression and hand it the result.

MIT — see LICENSE.

No warranty is expressed or implied as to whether any particular number is, or is not, Numberwang.

── more in #neural-networks 4 stories · sorted by recency
── more on @wangnet 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/wangnet-1-8-mb-zero-…] indexed:0 read:3min 2026-09-15 ·