Pith Number

pith:I33NTXR4

pith:2025:I33NTXR426DT44ZDYO5AKMVDTJ

not attested not anchored not stored refs resolved

Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

Chirag Modi, Eric Vanden-Eijnden, Jiequn Han, Joan Bruna

An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone.

arxiv:2512.10857 v2 · 2025-12-11 · 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{I33NTXR426DT44ZDYO5AKMVDTJ}

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

Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data.

C2weakest assumption

The iterative procedure converges to the desired self-consistent transport map under appropriate (unspecified in abstract) conditions on the corruption channel and data distributions.

C3one line summary

SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.

References

18 extracted · 18 resolved · 2 Pith anchors

[1] Stochastic Interpolants: A Unifying Framework for Flows and Diffusions · arXiv:2303.08797

[2] Stochastic interpolants with data-dependent couplings.arXiv preprint arXiv:2310.03725,

[3] Building normalizing flows with stochastic interpolants 2023

[4] Nearlyd-linear convergence bounds for diffusion models via stochastic local- ization.CoRR, abs/2308.03686

[5] arXiv preprint arXiv:2209.11215 , year =

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:32.682284Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e

Aliases

arxiv: 2512.10857 · arxiv_version: 2512.10857v2 · doi: 10.48550/arxiv.2512.10857 · pith_short_12: I33NTXR426DT · pith_short_16: I33NTXR426DT44ZD · pith_short_8: I33NTXR4

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/I33NTXR426DT44ZDYO5AKMVDTJ \
  | 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: 46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0de2b24aeb2a13a3f40cd519c3612eac774ee91b86147128a9b00cef846b768c",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-12-11T17:53:38Z",
    "title_canon_sha256": "31a7b1cdbc63c2ed2a0f561d652afcbf560723f14f3d56370f77f22804d202b2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.10857",
    "kind": "arxiv",
    "version": 2
  }
}