pith. sign in
Pith Number

pith:RCTSOCX7

pith:2026:RCTSOCX7ZGKQ2A7R6ADX5WIJNN
not attested not anchored not stored refs resolved

JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift

Geoffrey Rubin, Joseph Y. Lo, Lavsen Dahal, Yubraj Bhandari

A dual-stream model conditions visual CT embeddings on macro-radiomic priors via anatomically guided gating to improve triage accuracy and reduce false positives under distribution shift.

arxiv:2605.13813 v1 · 2026-05-13 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{RCTSOCX7ZGKQ2A7R6ADX5WIJNN}

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

On the MERLIN test set (N=5082), JANUS attains macro-AUROC 0.88 and AUPRC 0.74, outperforming all reproduced baselines. It generalizes to an external dataset (N=2000; AUROC 0.87), with the largest gains on findings defined by size and attenuation as well as improved calibration on both datasets.

C2weakest assumption

That the macro-radiomic priors extracted in the second stream remain accurate and unbiased under the same distribution shifts that affect the visual stream, and that the gating operation does not suppress true positives at a rate that offsets the reported reduction in false positives.

C3one line summary

JANUS conditions Vision Transformer embeddings on macro-radiomic priors via anatomically guided gating, reaching macro-AUROC 0.88 on an internal test set of 5082 cases and 0.87 on an external set of 2000 cases while improving calibration and reducing high-confidence false positives under domainshift

References

23 extracted · 23 resolved · 4 Pith anchors

[1] arXiv preprint arXiv:2511.17803 (2025) 2025
[2] Research Square pp 2024
[3] arXiv preprint arXiv:2601.13385 (2026) 2026
[4] Medical Image Analysis 103, 103636 (2025) 2025
[5] CT-IDP: Segmentation-Derived Quantitative Phenotypes for Interpretable Abdominal CT Disease Classification 2026 · arXiv:2605.09002

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-18T02:44:15.369715Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

88a7270affc9950d03f1f0077ed9096b6c7b84c172bf53d0a4d4302d46d03807

Aliases

arxiv: 2605.13813 · arxiv_version: 2605.13813v1 · doi: 10.48550/arxiv.2605.13813 · pith_short_12: RCTSOCX7ZGKQ · pith_short_16: RCTSOCX7ZGKQ2A7R · pith_short_8: RCTSOCX7
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RCTSOCX7ZGKQ2A7R6ADX5WIJNN \
  | 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: 88a7270affc9950d03f1f0077ed9096b6c7b84c172bf53d0a4d4302d46d03807
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "ceae1ed2538db74224eaebea526dd2f746d67b63030cbc61e34765cbe6726234",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T17:41:05Z",
    "title_canon_sha256": "a8b314d9c7dc1978ea2091e8a43df908a6ddfe092194b5b5ef4242d548c579d7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13813",
    "kind": "arxiv",
    "version": 1
  }
}