Pith Number

pith:6BBITQMB

pith:2025:6BBITQMBZFXIS5BUMBL2H22W5T

not attested not anchored not stored refs pending

Optimizing Large Language Model Training Using FP4 Quantization

Baining Guo, Guoshuai Zhao, Peng Cheng, Ruizhe Wang, Xiao Liu, Yeyun Gong, Zhengjun Zha, Ziyue Yang

arxiv:2501.17116 v2 · 2025-01-28 · cs.LG · 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{6BBITQMBZFXIS5BUMBL2H22W5T}

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.

Cited by

10 papers in Pith

Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling

Pretraining large language models with MXFP4 on Native FP4 Hardware

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale

Receipt and verification

First computed	2026-05-20T00:00:17.404117Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f04289c181c96e8974346057a3eb56ececd38686d9bd0cfca475676ebba66ee6

Aliases

arxiv: 2501.17116 · arxiv_version: 2501.17116v2 · doi: 10.48550/arxiv.2501.17116 · pith_short_12: 6BBITQMBZFXI · pith_short_16: 6BBITQMBZFXIS5BU · pith_short_8: 6BBITQMB

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/6BBITQMBZFXIS5BUMBL2H22W5T \
  | 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: f04289c181c96e8974346057a3eb56ececd38686d9bd0cfca475676ebba66ee6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "531b8ff0db66be5054d0fe89ba71a312d154718432ab36a2317d0afd930526af",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-01-28T18:04:50Z",
    "title_canon_sha256": "5fa5ccf226a058f442e77cc37a69241ad3c7a00c95ca276cb50805274ba60dde"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2501.17116",
    "kind": "arxiv",
    "version": 2
  }
}