Pith Number
pith:N7SBMGE6
pith:2025:N7SBMGE6XTVSQJ3P65VADYXCSN
not attested
not anchored
not stored
refs pending
The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
arxiv:2507.05644 v2 · 2025-07-08 · cs.LG · cs.AI · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{N7SBMGE6XTVSQJ3P65VADYXCSN}
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 | 2026-07-05T12:05:18.638176Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6fe416189ebceb28276ff76a01e2e29353f9e0f5440e2e3e99ccfab4c10b6124
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/N7SBMGE6XTVSQJ3P65VADYXCSN \
| 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: 6fe416189ebceb28276ff76a01e2e29353f9e0f5440e2e3e99ccfab4c10b6124
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "3c8e392d2d631d763fbbe5f0e08f5f8ccd27abf04e7f78f407256623cff353e4",
"cross_cats_sorted": [
"cs.AI",
"stat.ML"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-07-08T03:52:48Z",
"title_canon_sha256": "f298f954e520def34bbe1e34bda282802ac9984791d2462ead93983097e73696"
},
"schema_version": "1.0",
"source": {
"id": "2507.05644",
"kind": "arxiv",
"version": 2
}
}