Pith Number

pith:WRQIFOZU

pith:2026:WRQIFOZUYANB2IGIGCPDXSDY3D

not attested not anchored not stored refs resolved

Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel

Bangyu Wu, Deyu Meng, Ruihua Chen, Xile Zhao, Yisi Luo

The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence.

arxiv:2605.14370 v1 · 2026-05-14 · physics.geo-ph · cs.AI · physics.comp-ph

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WRQIFOZUYANB2IGIGCPDXSDY3D}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The neural tangent kernel induced by neural representation adaptively modulates the original sensitivity and wave tangent kernels. This modulation leads to the spectral filtering effect, the gradient wavenumber modulation, and the wave frequency bias, connecting the convergence behavior of NeurFWI with the eigen-structures of NSK and WTK.

C2weakest assumption

That the modulation effects of the neural tangent kernel on NSK and WTK can be directly connected to convergence behavior through eigen-structure analysis without unstated approximations or domain-specific assumptions in the derivation.

C3one line summary

Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.

References

174 extracted · 174 resolved · 1 Pith anchors

[1] An overview of full-waveform inversion in exploration geophysics , author=. Geophysics , volume=. 2009 , publisher= 2009

[2] International Conference on Computational Learning Theory , pages= 2006

[3] Geophysical Prospecting , volume= 2023

[4] Reparameterized full-waveform inversion using deep neural networks , author=. Geophysics , volume=. 2021 , publisher= 2021

[5] Topology and its Applications , volume= 2007

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:07.840490Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb

Aliases

arxiv: 2605.14370 · arxiv_version: 2605.14370v1 · doi: 10.48550/arxiv.2605.14370 · pith_short_12: WRQIFOZUYANB · pith_short_16: WRQIFOZUYANB2IGI · pith_short_8: WRQIFOZU

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D \
  | 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: b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e1f639d485d90c0da452fa391b57323bb100ab8df71f89abcbcfb5f4104b78a5",
    "cross_cats_sorted": [
      "cs.AI",
      "physics.comp-ph"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "physics.geo-ph",
    "submitted_at": "2026-05-14T04:49:23Z",
    "title_canon_sha256": "7da4d44bd103febe0b814eff503998003474d7876c449c1089553aa58065d37c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14370",
    "kind": "arxiv",
    "version": 1
  }
}