Pith Number
pith:ZVFD7TXT
pith:2021:ZVFD7TXTS4KJKY3GRXW4D666B2
not attested
not anchored
not stored
refs pending
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective
arxiv:2106.08453 v2 · 2021-06-15 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{ZVFD7TXTS4KJKY3GRXW4D666B2}
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.
Cited by
Receipt and verification
| First computed | 2026-07-05T04:39:59.816121Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
cd4a3fcef397149563668dedc1fbde0ebd39c2eb481de9cd5705789dc4570d40
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/ZVFD7TXTS4KJKY3GRXW4D666B2 \
| 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: cd4a3fcef397149563668dedc1fbde0ebd39c2eb481de9cd5705789dc4570d40
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a9c2d6546a478b7c681153daa55405ffb6a22ebcf25c2c09d0a92250b260507f",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2021-06-15T21:56:38Z",
"title_canon_sha256": "98c29a1981b5c354029c9ee3f99d5ade9290637d77b392570db1b9876f7efe53"
},
"schema_version": "1.0",
"source": {
"id": "2106.08453",
"kind": "arxiv",
"version": 2
}
}