Pith Number

pith:PYLO2YHL

pith:2023:PYLO2YHLBEBEZ6KRJMNHBXMKQP

not attested not anchored not stored refs pending

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Dan Busbridge, Etai Littwin, Jason Ramapuram, Jiatao Gu, Josh Susskind, Shuangfei Zhai, Tatiana Likhomanenko, Yizhe Zhang

arxiv:2303.06296 v2 · 2023-03-11 · cs.LG · cs.AI · cs.CL · cs.CV · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PYLO2YHLBEBEZ6KRJMNHBXMKQP}

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

3 papers in Pith

Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation

Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models

Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining

Receipt and verification

First computed	2026-07-05T06:34:28.225428Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7e16ed60eb09024cf9514b1a70dd8a83dd272136e4c855eacec3555438db9fc3

Aliases

arxiv: 2303.06296 · arxiv_version: 2303.06296v2 · doi: 10.48550/arxiv.2303.06296 · pith_short_12: PYLO2YHLBEBE · pith_short_16: PYLO2YHLBEBEZ6KR · pith_short_8: PYLO2YHL

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/PYLO2YHLBEBEZ6KRJMNHBXMKQP \
  | 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: 7e16ed60eb09024cf9514b1a70dd8a83dd272136e4c855eacec3555438db9fc3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f3bb4cc74780264b2ac009e8d332ac2af03acf691bd0549c663d170eedad12d9",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.CV",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-03-11T03:30:47Z",
    "title_canon_sha256": "03a2678f137d44fed0baf035f88f427c81af5f44af6e6384c4ec463d431946f0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2303.06296",
    "kind": "arxiv",
    "version": 2
  }
}