Pith Number

pith:N5PXGTBX

pith:2026:N5PXGTBXQLSZGH7FOGMOPJW5ZB

not attested not anchored not stored refs resolved

StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow

Gurjeet Jagwani, Hiranya Peiris, Sinan Deger, Stephen Thorp

StAD uses the Langevin-Stein operator to learn PF-ODE divergences without ever computing Jacobians.

arxiv:2605.16486 v1 · 2026-05-15 · stat.ML · astro-ph.IM · 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{N5PXGTBXQLSZGH7FOGMOPJW5ZB}

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

We introduce StAD, a new distillation method to predict and learn the divergence of the PF-ODE using the Langevin-Stein operator without ever computing the Jacobian.

C2weakest assumption

Under some regularity conditions these learned vector fields can be made to satisfy the Stein class, enabling generalization across a varied class of generative models.

C3one line summary

StAD distills divergence of PF-ODEs via the Langevin-Stein operator for faster, lower-variance likelihood estimation in generative models without Jacobian costs.

References

29 extracted · 29 resolved · 4 Pith anchors

[1] Monthly Notices of the Royal Astronomical Society428(4), 3121–3138 (2013) https://doi.org/10.1093/mnras/ sts261 2023 · doi:10.1093/mnras/

[2] cc/paper_files/paper/2019/file/ ba7609ee5789cc4dff171045a693a65f- Paper.pdf 2019

[3] cc/paper_files/paper/2023/file/ 9a8eb202c060b7d81f5889631cbcd47e- Paper-Conference.pdf 2023

[4] A downsampled variant of imagenet as an alternative to the CIFAR datasets 2019 · arXiv:1707.08819

[5] NICE: Non-linear Independent Components Estimation 2015 · doi:10.3847/1538-

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:02:24.527174Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6f5f734c3782e5931fe57198e7a6ddc845e92437e2146dfd5a3e51de078519ab

Aliases

arxiv: 2605.16486 · arxiv_version: 2605.16486v1 · doi: 10.48550/arxiv.2605.16486 · pith_short_12: N5PXGTBXQLSZ · pith_short_16: N5PXGTBXQLSZGH7F · pith_short_8: N5PXGTBX

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/N5PXGTBXQLSZGH7FOGMOPJW5ZB \
  | 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: 6f5f734c3782e5931fe57198e7a6ddc845e92437e2146dfd5a3e51de078519ab

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ac45427142cc228dd35365e8f01040870a4867e9ad3232a1e4b846fcd1543587",
    "cross_cats_sorted": [
      "astro-ph.IM",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-05-15T18:00:00Z",
    "title_canon_sha256": "38de342d8664365e65dde26a0ca882eda58d432c151afcab2ee4877689482268"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16486",
    "kind": "arxiv",
    "version": 1
  }
}