Pith Number

pith:MBW4CJ3V

pith:2026:MBW4CJ3V2OKVXNOQMDQVO5U4OK

not attested not anchored not stored refs resolved

Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes

Jeffrey J. Nirschl, Uma Meleti

Spectral-normalized neural Gaussian processes deliver accurate biomedical image classification with improved uncertainty estimates for out-of-distribution inputs.

arxiv:2602.02370 v2 · 2026-02-02 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MBW4CJ3V2OKVXNOQMDQVO5U4OK}

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

SNGP has comparable in-distribution performance while significantly improving uncertainty estimation and OOD detection.

C2weakest assumption

The chosen OOD test sets accurately represent the distribution shifts that occur in real clinical pathology workflows.

C3one line summary

SNGP models match deterministic neural network accuracy on biomedical images while providing superior uncertainty calibration and OOD rejection across six datasets.

References

17 extracted · 17 resolved · 1 Pith anchors

[1] Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes 2026 · arXiv:2602.02370

[2] Bayesian neural networks provide a formal approach to uncertainty estimation but are compu- tationally impractical for large architectures

[3] Datasets All datasets are publicly available from the original authors or MicroBench [10] 2020

[4] RESULTS Tab.1 summarizes the OOD detection performance of all methods trained on the Acevedo dataset. SNGP achieved near-perfect OOD-AUROC across all external OOD datasets (0.97–1.00), while maintaini

[5] Across multiple datasets, it maintains strong calibration and in- distribution accuracy while substantially improving OOD detection over deterministic and Monte Carlo methods

Cited by

1 paper in Pith

Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes

Receipt and verification

First computed	2026-06-19T16:11:20.290882Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

606dc12775d3955bb5d060e157769c72bddc10e800cc7a01d0cd460148f217dd

Aliases

arxiv: 2602.02370 · arxiv_version: 2602.02370v2 · doi: 10.48550/arxiv.2602.02370 · pith_short_12: MBW4CJ3V2OKV · pith_short_16: MBW4CJ3V2OKVXNOQ · pith_short_8: MBW4CJ3V

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/MBW4CJ3V2OKVXNOQMDQVO5U4OK \
  | 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: 606dc12775d3955bb5d060e157769c72bddc10e800cc7a01d0cd460148f217dd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "87f060829eb484dfcae582a6aa2db9781245df1c8d8abc16360133f95968fbca",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-02-02T17:35:10Z",
    "title_canon_sha256": "b80ebb44087e3ed3b1a20bae3db47efdabbe99fa02b5d08ed825e5c19a776428"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.02370",
    "kind": "arxiv",
    "version": 2
  }
}