Pith Number

pith:Q4O5LULE

pith:2026:Q4O5LULEOMMCUSYUHYXYHNBUY6

not attested not anchored not stored refs pending

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

Jiyeon Kim, Minjoon Seo, Moontae Lee, Sungik Choi, Yongrae Jo

Proximity bias in non-autoregressive diffusion language models makes the full generation trajectory depend on the position of the first unmasked token.

arxiv:2604.10567 v2 · 2026-04-12 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Q4O5LULEOMMCUSYUHYXYHNBUY6}

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 uncover an inherent failure mode in confidence-based non-autoregressive generation stemming from a strong proximity bias-the tendency for the denoising order to concentrate on spatially adjacent tokens. This local dependency leads to spatial error propagation, rendering the entire trajectory critically contingent on the initial unmasking position.

C2weakest assumption

That the observed proximity bias is the dominant cause of poor non-autoregressive performance and that a lightweight planner plus temperature annealing will reliably correct it across tasks without introducing new failure modes or significant overhead.

C3one line summary

Non-autoregressive diffusion language models have an inherent proximity bias in token unmasking that causes spatial error propagation, which a minimal planner and annealing strategy can mitigate for better reasoning performance.

Receipt and verification

First computed	2026-05-28T01:04:39.941034Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

871dd5d16473182a4b143e2f83b434c7b4e3f6a1b433ab029c79fc2fcd7ec660

Aliases

arxiv: 2604.10567 · arxiv_version: 2604.10567v2 · doi: 10.48550/arxiv.2604.10567 · pith_short_12: Q4O5LULEOMMC · pith_short_16: Q4O5LULEOMMCUSYU · pith_short_8: Q4O5LULE

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/Q4O5LULEOMMCUSYUHYXYHNBUY6 \
  | 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: 871dd5d16473182a4b143e2f83b434c7b4e3f6a1b433ab029c79fc2fcd7ec660

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4eb935cda19702d74549a85de843af8a867fe59d846e7091674c1394005bbbb7",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-12T10:26:41Z",
    "title_canon_sha256": "3126823eead0555446e3cf9cb37fef1b3fcbefe7600e35a8e924695cd8f1619b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.10567",
    "kind": "arxiv",
    "version": 2
  }
}