Pith Number

pith:ICPMUVYH

pith:2026:ICPMUVYHWT5GLCG6JK5IMWF7DU

not attested not anchored not stored refs pending

On the Wasserstein Gradient Flow Interpretation of Drifting Models

Alexandre Galashov, Arnaud Doucet, Arthur Gretton, James Thornton, Li Kevin Wenliang, Valentin De Bortoli

Generative Modeling via Drifting targets fixed points of Wasserstein gradient flows on smoothed divergences.

arxiv:2605.05118 v2 · 2026-05-06 · cs.LG · cs.AI · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ICPMUVYHWT5GLCG6JK5IMWF7DU}

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

GMD can be thought of as directly targeting a fixed point of a specific WGF flow. One algorithm corresponds to the limiting point of a WGF on the KL divergence with Parzen smoothing; the implemented algorithm resembles the fixed point of a WGF on the Sinkhorn divergence.

C2weakest assumption

The claimed correspondences between GMD procedures and WGF fixed points hold exactly once Parzen smoothing and implementation details are accounted for, without hidden discrepancies in discretization or optimization.

C3one line summary

GMD algorithms correspond to limiting points of Wasserstein gradient flows on the KL divergence with Parzen smoothing and bear resemblance to Sinkhorn divergence fixed points, with extensions to MMD and other divergences.

Cited by

1 paper in Pith

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

Receipt and verification

First computed	2026-05-22T02:04:41.726416Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

409eca5707b4fa6588de4aba8658bf1d1ee4b16227b717e34dc1c36c937f5a6d

Aliases

arxiv: 2605.05118 · arxiv_version: 2605.05118v2 · doi: 10.48550/arxiv.2605.05118 · pith_short_12: ICPMUVYHWT5G · pith_short_16: ICPMUVYHWT5GLCG6 · pith_short_8: ICPMUVYH

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/ICPMUVYHWT5GLCG6JK5IMWF7DU \
  | 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: 409eca5707b4fa6588de4aba8658bf1d1ee4b16227b717e34dc1c36c937f5a6d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "650d1ce5a167b0dec3f37c1784580def85ccf8a8da63193d8b46139cebbe50df",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-06T16:48:46Z",
    "title_canon_sha256": "2aa42cb08fdfe86e9e59105dfa5bdf2d804668481f31ce0e4a354d97e0b74b17"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.05118",
    "kind": "arxiv",
    "version": 2
  }
}