Pith Number

pith:BIN2ZJL2

pith:2026:BIN2ZJL2JUG2PAKDCXWYE5LJ3E

not attested not anchored not stored refs pending

(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models

Ana Lucic, Jan-Willem van de Meent, Maksim Zhdanov, Max Welling

Mosaic achieves near-perfect spectral alignment in 1.5° weather forecasts by using block-sparse attention and learned ensemble perturbations, matching finer-resolution models.

arxiv:2604.16429 v3 · 2026-04-06 · cs.LG · cs.AI · cs.CV · physics.ao-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{BIN2ZJL2JUG2PAKDCXWYE5LJ3E}

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

Mosaic produces well-calibrated ensembles whose individual members exhibit near-perfect spectral alignment across all resolved frequencies at 1.5° resolution while matching or outperforming models trained on 6× finer grids.

C2weakest assumption

That the mesh-aligned block-sparse attention fully captures necessary long-range dependencies without introducing new artifacts or losing critical interactions that standard attention would preserve.

C3one line summary

Mosaic achieves state-of-the-art spectral alignment in 1.5° weather forecasts via learned functional perturbations and hardware-aligned sparse attention, matching finer-resolution models with fast inference.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Uncertainty-aware Machine Learning Interatomic Potentials via Learned Functional Perturbations

Receipt and verification

First computed	2026-05-20T00:04:31.915899Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0a1baca57a4d0da7814315ed827569d9080db00689188a8bf5b10614aed96b69

Aliases

arxiv: 2604.16429 · arxiv_version: 2604.16429v3 · doi: 10.48550/arxiv.2604.16429 · pith_short_12: BIN2ZJL2JUG2 · pith_short_16: BIN2ZJL2JUG2PAKD · pith_short_8: BIN2ZJL2

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/BIN2ZJL2JUG2PAKDCXWYE5LJ3E \
  | 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: 0a1baca57a4d0da7814315ed827569d9080db00689188a8bf5b10614aed96b69

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "59a59c77216e980dc0f0406b6986c4e202c6a6f9fccd0ea129574f1a308c15c3",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV",
      "physics.ao-ph"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-06T08:50:42Z",
    "title_canon_sha256": "c8538bfff0f2835dfb25b2f4bbf501ea5ac8b38070aa6e7e41a6768c4998c663"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.16429",
    "kind": "arxiv",
    "version": 3
  }
}