pith:UJ5KWMCF
Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
FNO shows sharp error jumps on unseen high frequencies in wave equations while DeepONet degrades more gradually.
arxiv:2605.12997 v1 · 2026-05-13 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UJ5KWMCF4HHHZ5IUNYIHHP6VGP}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error. These differences arise from how each architecture represents and responds to variations in frequency structure.
That independently varying input frequency and coefficient smoothness produces distribution shifts representative of those encountered in practical PDE applications.
FNO exhibits strong frequency bias with sharp OOD error growth on high-frequency inputs in wave equations, while DeepONet shows milder degradation despite higher baseline error.
References
Receipt and verification
| First computed | 2026-05-18T03:09:00.477770Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a27aab3045e1ce7cf5146e1073bfd533c8e53bbe879e5d1e88d64158eb603ba1
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UJ5KWMCF4HHHZ5IUNYIHHP6VGP \
| 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: a27aab3045e1ce7cf5146e1073bfd533c8e53bbe879e5d1e88d64158eb603ba1
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "9d6b92ebfa1c8f6d742fdc4db5131c6d9d274b61dd5bf9e1ae51ffa84c8d8ba4",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-13T04:53:36Z",
"title_canon_sha256": "1cdbe8c64e8de1a2b71c01b8db89e0a2dcfa6007075abb315a18a531ecf5a9ed"
},
"schema_version": "1.0",
"source": {
"id": "2605.12997",
"kind": "arxiv",
"version": 1
}
}