Pith Number

pith:W2BPVN54

pith:2026:W2BPVN54DJJ4MBSGOPBNYGGSF7

not attested not anchored not stored refs resolved

Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models

Arash Gholami Davoodi, Navid Rezazadeh, Pouya Pezeshkpour, Seyed Pouyan Mousavi Davoudi

Wasserstein distance over token embeddings yields a closed-form truncation rule that balances mass and entropy in LLM decoding.

arxiv:2602.10346 v2 · 2026-02-10 · cs.CL · 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{W2BPVN54DJJ4MBSGOPBNYGGSF7}

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

Our theory yields a simple closed-form structure for the fixed-potential subset update... achieving up to 33.7% improvement.

C2weakest assumption

That Wasserstein distance defined over token-embedding geometry meaningfully captures semantic relationships required for logical coherence during open-ended generation.

C3one line summary

Top-W applies Wasserstein-regularized truncation on token-embedding geometry to create a closed-form optimal crop for LLM sampling that outperforms prior methods by up to 33.7% on GSM8K, GPQA, AlpacaEval, and MT-Bench.

References

21 extracted · 21 resolved · 12 Pith anchors

[1] Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone · arXiv:2404.14219

[2] Mirostat: A perplexity-controlled neural text decoding algorithm 2007

[3] Lan- guage models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 1901

[4] DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models · arXiv:2309.03883

[5] Training Verifiers to Solve Math Word Problems · arXiv:2110.14168

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:16.222671Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b682fab7bc1a53c6064673c2dc18d22ff1b8f33c5a27b44fd4f5f25b0dc6a5c1

Aliases

arxiv: 2602.10346 · arxiv_version: 2602.10346v2 · doi: 10.48550/arxiv.2602.10346 · pith_short_12: W2BPVN54DJJ4 · pith_short_16: W2BPVN54DJJ4MBSG · pith_short_8: W2BPVN54

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/W2BPVN54DJJ4MBSGOPBNYGGSF7 \
  | 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: b682fab7bc1a53c6064673c2dc18d22ff1b8f33c5a27b44fd4f5f25b0dc6a5c1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "93bad57a54f8ed58cfe362360bef037fc26063aa1c94a6c8fcd627c5bb285320",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-02-10T22:36:48Z",
    "title_canon_sha256": "207a25f7eb6e7a84f5dbf714060145fa53a1cf5ee3a311dc9132c9625550e51f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.10346",
    "kind": "arxiv",
    "version": 2
  }
}