pith:WRQINHTQ
SpanKey: Dynamic Key Space Conditioning for Neural Network Access Control
SpanKey gates neural network inference by conditioning activations on keys from a defined low-dimensional subspace.
arxiv:2604.12254 v2 · 2026-04-14 · cs.CR · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WRQINHTQJSBFK2QZ7NDBYVLAZX}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Subspace key injection with multi-layer design, together with deny losses and margin-tail diagnostics, enables practical key-based gating of neural network inference, as demonstrated by CIFAR-10 ResNet-18 runs and MNIST ablations.
That the network does not absorb the key signal into its weights in a way that collapses separation between valid and invalid keys at deployment scale, despite the analytical Beta-energy split and margin diagnostics provided.
SpanKey injects keys from a learned subspace into network activations via additive or multiplicative maps to enable key-based access control for neural network inference.
Receipt and verification
| First computed | 2026-05-20T00:03:11.158193Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
b460869e704c82556a19fb461c5560cdde6091c939444c956a43667f0cc2cb3b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX \
| 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: b460869e704c82556a19fb461c5560cdde6091c939444c956a43667f0cc2cb3b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "f501051a18f26d8c65a0b78929e5b204998bee6b6bb6bf11e749990433694ffc",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CR",
"submitted_at": "2026-04-14T04:01:34Z",
"title_canon_sha256": "c2e115dbdf0834b2c5db3dc7e4c6d2d63f85a3fcf3c1cf1d5034dea866930118"
},
"schema_version": "1.0",
"source": {
"id": "2604.12254",
"kind": "arxiv",
"version": 2
}
}