Pith Number
pith:J3QPRZNS
pith:2026:J3QPRZNSIGZBNFFYACBNDQS3TH
not attested
not anchored
not stored
refs pending
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe
arxiv:2606.20381 v1 · 2026-06-18 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{J3QPRZNSIGZBNFFYACBNDQS3TH}
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
· sign in to
claim
4
Citations
5
Replications
✓
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.
Receipt and verification
| First computed | 2026-06-19T16:13:11.027940Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
4ee0f8e5b241b21694b80082d1c25b99d9a6fe461cff5924752904c3d8cbf853
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/J3QPRZNSIGZBNFFYACBNDQS3TH \
| 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: 4ee0f8e5b241b21694b80082d1c25b99d9a6fe461cff5924752904c3d8cbf853
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "014a66f4291de939e377f32b4350aa8aa05c5cb0bf1a09e3a57b9a477efbda6b",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-06-18T15:40:51Z",
"title_canon_sha256": "191b801f45a19d35e451ff65d446780c75643c88a2c16a2f4b3175676a986426"
},
"schema_version": "1.0",
"source": {
"id": "2606.20381",
"kind": "arxiv",
"version": 1
}
}