Pith Number

pith:J3A7IKJK

pith:2026:J3A7IKJKHEUFOMXUPAGIIEDYET

not attested not anchored not stored refs pending

Generative models for decision-making under distributional shift

Xiuyuan Cheng, Yao Xie, Yunqin Zhu

Generative models construct nominal, stressed, and conditional distributions for decisions under shift using transport maps and guided dynamics.

arxiv:2604.04342 v2 · 2026-04-06 · cs.LG · 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{J3A7IKJKHEUFOMXUPAGIIEDYET}

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

Generative models can be used to learn nominal uncertainty, construct stressed or least-favorable distributions for robustness, and produce conditional or posterior distributions under side information and partial observation, within a unified framework based on pushforward maps, continuity, Fokker-Planck equations, Wasserstein geometry, and optimization in probability space.

C2weakest assumption

That the mathematical tools (transport maps, score fields, guided stochastic dynamics) can be trained and deployed in a way that reliably produces decision-relevant distributions whose properties transfer to the actual deployment distribution under shift.

C3one line summary

Generative models via pushforward maps, Fokker-Planck equations, and Wasserstein geometry enable learning nominal uncertainty, stressed distributions for robustness, and conditional posteriors under distributional shift.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Decision-Focused Learning: When and Why Traditional Prediction Models Fail

Receipt and verification

First computed	2026-06-19T16:11:22.852952Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4ec1f4292a39285732f4780c84107824c99a4e742ada7d13c13b22d91c9488a0

Aliases

arxiv: 2604.04342 · arxiv_version: 2604.04342v2 · doi: 10.48550/arxiv.2604.04342 · pith_short_12: J3A7IKJKHEUF · pith_short_16: J3A7IKJKHEUFOMXU · pith_short_8: J3A7IKJK

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/J3A7IKJKHEUFOMXUPAGIIEDYET \
  | 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: 4ec1f4292a39285732f4780c84107824c99a4e742ada7d13c13b22d91c9488a0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c6b15e0abe93afeb2a9a0ad0bbb157002db00a27490974ca3c93813d11c33a6c",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-06T01:35:13Z",
    "title_canon_sha256": "f65cd7671df6949ddabd80f2af4a481e2f6b1e84fbb073c726694df3533639e8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.04342",
    "kind": "arxiv",
    "version": 2
  }
}