Pith Number

pith:J5JQLY7B

pith:2026:J5JQLY7BJ6LUFMDIGL4SUTV2QT

not attested not anchored not stored refs resolved

A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning

Ben Seiyon Lee, Isaac Amouzou

A cubing strategy systematically identifies stable hyperparameter regions for well-calibrated MC dropout in spatial deep learning.

arxiv:2605.16570 v1 · 2026-05-15 · stat.CO · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J5JQLY7BJ6LUFMDIGL4SUTV2QT}

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 open · sign in to claim

4 Citations open

5 Replications open

✓ 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.

Claims

C1strongest claim

Through a simulation study spanning multiple spatial dependence regimes as well as a large remotely-sensed land surface temperature dataset, we demonstrate that our approach produces competitive or superior predictive intervals compared to the baseline model.

C2weakest assumption

The statistical baseline model serves as a reliable calibration anchor when scoring hyperparameter regions for MC dropout performance.

C3one line summary

A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.

References

294 extracted · 294 resolved · 14 Pith anchors

[1] Journal of Machine Learning Research , volume=

[2] Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

[3] IEEE transactions on medical imaging , volume= 2020

[4] Learning representations by back-propagating errors , author=. nature , volume=. 1986 , publisher= 1986

[5] Pathologies of factorised gaussian and mc dropout posteriors in bayesian neural networks , author=. stat , volume=

Receipt and verification

First computed	2026-05-20T00:02:29.713621Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4f5305e3e14f9742b06832f92a4eba84d255f74a0edc98fe9de2a38d8672aa32

Aliases

arxiv: 2605.16570 · arxiv_version: 2605.16570v1 · doi: 10.48550/arxiv.2605.16570 · pith_short_12: J5JQLY7BJ6LU · pith_short_16: J5JQLY7BJ6LUFMDI · pith_short_8: J5JQLY7B

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/J5JQLY7BJ6LUFMDIGL4SUTV2QT \
  | 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: 4f5305e3e14f9742b06832f92a4eba84d255f74a0edc98fe9de2a38d8672aa32

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb23b67df5597df1407ae3b3e87b1e07058545be8b83a97061985d5cbe15abcd",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.CO",
    "submitted_at": "2026-05-15T19:18:39Z",
    "title_canon_sha256": "c00de7b374532c05b7979aa023e99463ed027d5497df15e5e657c406a29d0335"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16570",
    "kind": "arxiv",
    "version": 1
  }
}