pith:NCWDAHP6
Uncertainty Estimation via Hyperspherical Confidence Mapping
Hyperspherical Confidence Mapping captures uncertainty as the violation of a unit hypersphere constraint on network outputs.
arxiv:2605.05964 v2 · 2026-05-07 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NCWDAHP62XGEZ3RH4F5ZQGX4NP}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments across diverse benchmarks and real-world industrial tasks demonstrate that HCM matches or surpasses ensemble and evidential approaches, with far lower inference cost and stronger confidence-error alignment.
That uncertainty can be reliably captured by the degree of violation of the unit-hypersphere constraint on the normalized direction vector, without needing distributional assumptions or sampling.
HCM turns neural outputs into magnitude plus unit hypersphere vector and treats uncertainty as the geometric violation of that unit constraint, yielding deterministic estimates for regression and classification that match ensembles at lower cost.
Receipt and verification
| First computed | 2026-05-29T01:05:11.941033Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
68ac301dfed5cc4cee27e17b981afc6bf4120e1d57d067f311b2f3331762c9af
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NCWDAHP62XGEZ3RH4F5ZQGX4NP \
| 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: 68ac301dfed5cc4cee27e17b981afc6bf4120e1d57d067f311b2f3331762c9af
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "84dd3ba8d7143e21bc00f2ad419cc5f4f8d6f9d5574cf60e8a69f0482c7facf8",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-07T10:11:01Z",
"title_canon_sha256": "f2b0bd49892481c801702bb89aee8cc7801097957c1790e0ed1698cc9b3c6a66"
},
"schema_version": "1.0",
"source": {
"id": "2605.05964",
"kind": "arxiv",
"version": 2
}
}