Pith Number

pith:E2U6PLHN

pith:2026:E2U6PLHN7XP36L6LYE3BROPQ3H

not attested not anchored not stored refs resolved

Discrete Stochastic Localization for Non-autoregressive Generation

Evangelos E. Papalexakis, Greg Ver Steeg, Jiayi Cheng, Longxuan Yu, Partha Thakuria, Rob Brekelmans, Yunshu Wu

Discrete Stochastic Localization makes one network handle any per-token noise path for sequence generation.

arxiv:2605.12836 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{E2U6PLHN7XP36L6LYE3BROPQ3H}

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

One trained network then supports an entire family of per-token SNR paths, with endpoint masked-diffusion paths as a special case. Fine-tuning a pretrained MDLM checkpoint with DSL substantially improves distributional faithfulness (MAUVE) on OpenWebText across all step budgets from T=128 to T=1024.

C2weakest assumption

The Bayes-optimal denoiser is invariant to the nominal signal-to-noise ratio under the localization channel when using unit-sphere token embeddings; this invariance is presented as enabling the single-network property but its validity depends on the specific channel definition.

C3one line summary

Discrete Stochastic Localization provides a continuous-state framework with SNR-invariant denoisers on unit-sphere embeddings, enabling one network to support multiple per-token noise paths and improving MAUVE on OpenWebText.

References

34 extracted · 34 resolved · 6 Pith anchors

[1] Structured denoising diffusion models in discrete state-spaces.Advances in Neural Information Processing Systems, 34:17981–17993, 2021 2021

[2] Continuous diffusion for categor- ical data 2022

[3] Likelihood-based diffusion language models 2023

[4] Mutual information and minimum mean- square error in gaussian channels.IEEE transactions on information theory, 51(4):1261–1282, 2005 2005

[5] Denoising diffusion probabilistic models.Advances in Neural Information Processing Systems, 33:6840–6851 2020

Receipt and verification

First computed	2026-05-18T03:09:12.028533Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

26a9e7acedfddfbf2fcbc13618b9f0d9cc874631cfa3e65f29bd3d595031ef23

Aliases

arxiv: 2605.12836 · arxiv_version: 2605.12836v1 · doi: 10.48550/arxiv.2605.12836 · pith_short_12: E2U6PLHN7XP3 · pith_short_16: E2U6PLHN7XP36L6L · pith_short_8: E2U6PLHN

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/E2U6PLHN7XP36L6LYE3BROPQ3H \
  | 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: 26a9e7acedfddfbf2fcbc13618b9f0d9cc874631cfa3e65f29bd3d595031ef23

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bb86625d4a1f1edefcadd008797997e3e5f67d4090b0b66b76d2a0ee79e53276",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T00:12:24Z",
    "title_canon_sha256": "f32051e8cb979e2a912a731bc27d5c130f166ee1aef51e7e3f4c1da64bd9ff63"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12836",
    "kind": "arxiv",
    "version": 1
  }
}