Pith Number

pith:MMMH3ZIP

pith:2019:MMMH3ZIPPYIA4PRKN3P3QYSQGI

not attested not anchored not stored refs resolved

The Curious Case of Neural Text Degeneration

Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin Choi

Nucleus sampling draws from the dynamic high-probability set to generate more diverse and coherent text than beam search or top-k methods.

arxiv:1904.09751 v2 · 2019-04-22 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MMMH3ZIPPYIA4PRKN3P3QYSQGI}

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

By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence.

C2weakest assumption

That the model's learned probability distribution is sufficiently well-calibrated that low-probability tokens in the tail are reliably lower quality, so truncating them improves rather than harms the output.

C3one line summary

Nucleus sampling draws from the smallest set of tokens whose cumulative probability exceeds threshold p, yielding more human-like diversity and coherence than beam search or full-distribution sampling.

References

16 extracted · 16 resolved · 2 Pith anchors

[1] Neural machine translation by jointly learning to align and translate 2015

[2] Language gans falling short 2018

[3] Language GANs falling short 2018

[4] Elizabeth Clark, Yangfeng Ji, and Noah A. Smith. Neural text generation in stories using entity rep- resentations as context. In Proceedings of the 2018 Conference of the North American Chapter of the 2018

[5] Hierarchical neural story generation 2020

Formal links

2 machine-checked theorem links

Cited by

121 papers in Pith

Synthetic Consumer Insight Generation with Large Language Models

RubriQ: Rubric-Guided Group Relative Policy Optimization for Constraint-Aware Quantum Circuit Synthesis

Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation

Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation

Receipt and verification

First computed	2026-07-05T00:40:54.934288Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

63187de50f7e100e3e2a6edfb862503203212d19850bc74f103d3ea21a3fa124

Aliases

arxiv: 1904.09751 · arxiv_version: 1904.09751v2 · doi: 10.48550/arxiv.1904.09751 · pith_short_12: MMMH3ZIPPYIA · pith_short_16: MMMH3ZIPPYIA4PRK · pith_short_8: MMMH3ZIP

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/MMMH3ZIPPYIA4PRKN3P3QYSQGI \
  | 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: 63187de50f7e100e3e2a6edfb862503203212d19850bc74f103d3ea21a3fa124

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0865715a7c2b1b50ff1338569cfaabd8b7b13c833b5130585c2667f391fad78f",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2019-04-22T07:17:18Z",
    "title_canon_sha256": "129d205975a35cd33688c24c44d313f3ae68ca6cbc7d1714e8be66e73effee3e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1904.09751",
    "kind": "arxiv",
    "version": 2
  }
}