pith. sign in
Pith Number

pith:QASTZ5UY

pith:2026:QASTZ5UYRGLGABPMFC4LN53GUC
not attested not anchored not stored refs resolved

SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants

Pietro Li\`o, Santanu Subhash Rathod, Xiao Zhang

SplineFlow uses B-spline interpolation to build stable conditional paths for flow matching in dynamical systems.

arxiv:2601.23072 v2 · 2026-01-30 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{QASTZ5UYRGLGABPMFC4LN53GUC}

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 SplineFlow, a theoretically grounded flow matching algorithm that jointly models conditional paths across observations via B-spline interpolation. Specifically, SplineFlow exploits the smoothness and stability of B-spline bases to learn the complex underlying dynamics in a structured manner while ensuring the multi-marginal requirements are met.

C2weakest assumption

That B-spline bases of appropriate order can capture higher-order dynamics from irregular observations without introducing instability or violating the required multi-marginal constraints, an assumption stated in the abstract but not derived in detail here.

C3one line summary

SplineFlow uses B-spline interpolation inside flow matching to jointly construct stable conditional paths that satisfy multi-marginal constraints for dynamical systems with irregular observations.

References

19 extracted · 19 resolved · 5 Pith anchors

[1] Building Normalizing Flows with Stochastic Interpolants · arXiv:2209.15571
[2] Random dynamical systems 1994
[3] Good approximation by splines with variable knots 1973
[4] A survey of the
[5] Flow matching meets biology and life science: A survey.arXiv preprint arXiv:2507.17731,

Formal links

1 machine-checked theorem link

Receipt and verification
First computed 2026-05-17T23:39:04.485178Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

80253cf69889966005ec28b8b6f766a0ba2e24ad0980eb42b8f32dc45533e1e6

Aliases

arxiv: 2601.23072 · arxiv_version: 2601.23072v2 · doi: 10.48550/arxiv.2601.23072 · pith_short_12: QASTZ5UYRGLG · pith_short_16: QASTZ5UYRGLGABPM · pith_short_8: QASTZ5UY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/QASTZ5UYRGLGABPMFC4LN53GUC \
  | 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: 80253cf69889966005ec28b8b6f766a0ba2e24ad0980eb42b8f32dc45533e1e6
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "fb2c0a5350542755a15645c04fe9d0e1bf2ac6ef09c480dd020e1888a2c4689a",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-01-30T15:19:48Z",
    "title_canon_sha256": "a7695c957929ee02bc848a7ad4e12299bac5919c7761e4edfea2b6f392ed753a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.23072",
    "kind": "arxiv",
    "version": 2
  }
}