pith:PUMJ7S2N
Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects
A minimal filling architecture for polynomial neural networks need not have unimodal hidden-layer widths.
arxiv:2605.09609 v2 · 2026-05-10 · cs.LG · math.AG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{PUMJ7S2NWIEN6IQV7EJWZTXVWD}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We provide a counterexample to the minimal unimodal conjecture for polynomial neural networks (PNNs) with power activation functions.
The architecture found by frontier search is indeed a minimal filling architecture that is not unimodal, as certified by the recursive dimension bounds and symbolic computation.
A counterexample disproves the conjecture that minimal filling architectures of polynomial neural networks always have unimodal hidden layer widths.
Cited by
Receipt and verification
| First computed | 2026-06-19T16:12:20.628374Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
7d189fcb4db208df2215f9136ccef5b0f5873237b0cf77be6237ea8d323e9e7a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/PUMJ7S2NWIEN6IQV7EJWZTXVWD \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 7d189fcb4db208df2215f9136ccef5b0f5873237b0cf77be6237ea8d323e9e7a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "4210a9b371799aca9cfbcff92ad0602a047ad4aac8135ed6c4a5992120b377dd",
"cross_cats_sorted": [
"math.AG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-10T15:46:00Z",
"title_canon_sha256": "1195c39bcb1a48711b3ab359a6c89febaa9c28ad5dad46ae5fa0a4bb78f42bf4"
},
"schema_version": "1.0",
"source": {
"id": "2605.09609",
"kind": "arxiv",
"version": 2
}
}