Pith Number

pith:GJMQ5GP2

pith:2024:GJMQ5GP2U5QTVEPIHYPZLCNJVY

not attested not anchored not stored refs pending

To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability

Byeongwook Kim, Dongsoo Lee, Jeongin Bae, Joonhyung Lee, Se Jung Kwon

arxiv:2405.18710 v2 · 2024-05-29 · cs.LG · 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{GJMQ5GP2U5QTVEPIHYPZLCNJVY}

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

6 papers in Pith

From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

PowLU: An Activation Function for Stable Pre-Training of LLMs

GNMR: Runtime Stability Control for Low-Precision Large Language Model Training

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs

From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

Receipt and verification

First computed	2026-07-05T10:38:33.595692Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

32590e99faa7613a91e83e1f9589a9ae22ad3403f1c302db6ca8d00efa39e730

Aliases

arxiv: 2405.18710 · arxiv_version: 2405.18710v2 · doi: 10.48550/arxiv.2405.18710 · pith_short_12: GJMQ5GP2U5QT · pith_short_16: GJMQ5GP2U5QTVEPI · pith_short_8: GJMQ5GP2

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/GJMQ5GP2U5QTVEPIHYPZLCNJVY \
  | 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: 32590e99faa7613a91e83e1f9589a9ae22ad3403f1c302db6ca8d00efa39e730

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a027307c17817dd5b3516a3e08c79639cae4b4b890f20a99fdcaea5cef275d07",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-05-29T02:42:23Z",
    "title_canon_sha256": "40edecbc098c84edb25b2c58a1eaf2924475511ca40a1f111d2f6dfb9a3a33fe"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2405.18710",
    "kind": "arxiv",
    "version": 2
  }
}