Pith Number

pith:EWKWJLMR

pith:2026:EWKWJLMRXVAW5YBV3VNOLV5V4K

not attested not anchored not stored refs resolved

ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing

Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Jeffrey A Fessler, Lianghe Shi, Qing Qu, Saiprasad Ravishankar, Siyi Chen, Xiao Li, Yida Pan, Yixuan Jia, Yue Cynthia Wu

A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation.

arxiv:2605.14285 v1 · 2026-05-14 · eess.IV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EWKWJLMRXVAW5YBV3VNOLV5V4K}

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

Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.

C2weakest assumption

That assigning independent noise levels to each frame in a diffusion process allows the model to learn a joint-trajectory prior that captures long-horizon dependencies and avoids error accumulation for non-Markovian observations.

C3one line summary

ForcingDAS is a single diffusion-based model for data assimilation that unifies filtering and smoothing regimes via per-frame noise scheduling and reduces long-horizon error accumulation on non-Markovian observations.

References

17 extracted · 17 resolved · 1 Pith anchors

[1] Appa: Bending weather dynamics with latent diffusion models for global data assimilation 2025 · doi:10.48550/arxiv.2504.18720

[2] Sharp failure rates for the bootstrap particle filter in high dimensions 2024

[3] Closed-loop turbulence control: Progress and challenges 2008

[4] Dataassimilation in the geosciences: An overview of methods, issues, and perspectives 2025 · doi:10.1126/sciadv.aea4248

[5] Efficient medical vision-language alignment through adapting masked vision models.IEEE Transactions on Medical Imaging, 44(11):4499–4510, November 2025 1999 · doi:10.1109/tmi

Receipt and verification

First computed	2026-05-17T23:39:10.248725Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573

Aliases

arxiv: 2605.14285 · arxiv_version: 2605.14285v1 · doi: 10.48550/arxiv.2605.14285 · pith_short_12: EWKWJLMRXVAW · pith_short_16: EWKWJLMRXVAW5YBV · pith_short_8: EWKWJLMR

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/EWKWJLMRXVAW5YBV3VNOLV5V4K \
  | 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: 259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9235ac073178336799eb257266eaee1579541f398321039cf17d6ab7d971d59f",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.IV",
    "submitted_at": "2026-05-14T02:34:33Z",
    "title_canon_sha256": "8a47747834d1180158498360f4ce7d9ea9c50abd86059acc879bcd8c53a4a070"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14285",
    "kind": "arxiv",
    "version": 1
  }
}