pith:UDTFEBXB
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics learns second-order population dynamics directly from observed marginals without specifying the Lagrangian.
arxiv:2605.08550 v3 · 2026-05-08 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UDTFEBXBTWBUSFLNZWJGPRB7MY}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
WLM is the first algorithm that learns these second-order dynamics from observed marginals, without specifying the Lagrangian.
That population dynamics of interest can be accurately described as minimizing a population-level action under a damped Wasserstein Lagrangian.
Wasserstein Lagrangian Mechanics learns second-order population dynamics from observed marginals without specifying the Lagrangian and outperforms gradient flow methods on periodic dynamics like vortex motion and flocking.
Receipt and verification
| First computed | 2026-05-20T00:03:15.291626Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a0e65206e19d8349156dcd9267c43f661e6bc259fe80b7d4233824f69c6cb24c
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY \
| 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: a0e65206e19d8349156dcd9267c43f661e6bc259fe80b7d4233824f69c6cb24c
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a6c75cadde9fda76efe73c240afb120e90fc11055778cb8b6a39ecb8df7af207",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-08T23:21:17Z",
"title_canon_sha256": "0e2e0c5b3586732c24850c70092404de1885fdf22d04331e593d3f0538b663c3"
},
"schema_version": "1.0",
"source": {
"id": "2605.08550",
"kind": "arxiv",
"version": 3
}
}