Pith Number

pith:VXWVNR5S

pith:2026:VXWVNR5SBDC5UP4KY55VLWA2V2

not attested not anchored not stored refs pending

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

Benjamin Gundersen, Bjoern Menze, Christian Bluethgen, Farhad Nooralahzadeh, Jean-Benoit Delbrouck, Jiwoong Sohn, Julia E. Vogt, Kenneth Styppa, M\'elanie Roschewitz, Michael Krauthammer, Michael Moor, Nicolas Deperrois, Yitian Tao

A tool-using AI agent generates more accurate, robust, and faithful chest CT reports by producing explicit stepwise reasoning traces.

arxiv:2604.15231 v2 · 2026-04-16 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VXWVNR5SBDC5UP4KY55VLWA2V2}

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

RadAgent improves Chest CT report generation over its 3D VLM counterpart, CT-Chat, across three dimensions. Clinical accuracy improves by 6.0 points (36.4% relative) in macro-F1 and 5.4 points (19.6% relative) in micro-F1. Robustness under adversarial conditions improves by 24.7 points (41.9% relative). Furthermore, RadAgent achieves 37.0% in faithfulness, a new capability entirely absent in its 3D VLM counterpart.

C2weakest assumption

That the observed gains in accuracy, robustness, and the new faithfulness metric are attributable to the tool-using stepwise agent architecture rather than differences in training data, model size, or evaluation choices.

C3one line summary

RadAgent generates stepwise, tool-augmented chest CT reports with traceable decisions, improving accuracy, robustness, and adding a 37% faithfulness score absent in standard 3D VLMs.

Receipt and verification

First computed	2026-06-02T02:04:53.193850Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aded56c7b208c5da3f8ac77b55d81aae84c5445ccb6b276c9af7e8ccfae6c19c

Aliases

arxiv: 2604.15231 · arxiv_version: 2604.15231v2 · doi: 10.48550/arxiv.2604.15231 · pith_short_12: VXWVNR5SBDC5 · pith_short_16: VXWVNR5SBDC5UP4K · pith_short_8: VXWVNR5S

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/VXWVNR5SBDC5UP4KY55VLWA2V2 \
  | 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: aded56c7b208c5da3f8ac77b55d81aae84c5445ccb6b276c9af7e8ccfae6c19c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d80392a8ab3c4c347b02b5f97172eddcbbbaef0e2b16d5638dcd298e2b0de0de",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-16T17:09:30Z",
    "title_canon_sha256": "8b2e9178f50041f7b125fc3967615a6794f55fe3adfc62b7e41ca4014443e368"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.15231",
    "kind": "arxiv",
    "version": 2
  }
}