pith:6RASYPHO
An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification
Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration.
arxiv:2603.02719 v4 · 2026-03-03 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{6RASYPHO7UT6FTWBAKNPXDV3TE}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
selective prediction can substantially degrade performance despite strong standard evaluation metrics. This failure is driven by severe class-dependent miscalibration, whereby models assign high uncertainty to correct predictions and low uncertainty to incorrect ones, particularly for underrepresented clinical conditions.
The assumption that the tested unimodal and multimodal models and the specific ICU dataset splits are representative enough to generalize the miscalibration failure mode to broader clinical deployment scenarios.
Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration that assigns high uncertainty to correct predictions and low uncertainty to incorrect ones.
Formal links
Receipt and verification
| First computed | 2026-05-25T02:01:16.410236Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE \
| 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: f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "ea305a5cea27fb3d5703ffed1c72aee4ca1dbc2475c67d50f32bc61297b262a6",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-03-03T08:16:44Z",
"title_canon_sha256": "5e02b3714c0b0fb9b21434dc387c6521ff0d270d6dba06fe3ddeb9f511df5d91"
},
"schema_version": "1.0",
"source": {
"id": "2603.02719",
"kind": "arxiv",
"version": 4
}
}