Pith Number

pith:OHFKPDAC

pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL

not attested not anchored not stored refs pending

BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection

Hanshu Rao, Nguyen Anh Khoa Tran, Qiunan Zhang, Saukun Thika You, Wesley K. Marizane, Xiaolei Huang

A multi-agent debate system augmented with hybrid retrieval detects terminology substitution errors in clinical notes more accurately than single-agent RAG or debate-only approaches.

arxiv:2604.10389 v2 · 2026-04-12 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{OHFKPDACWGFMCM6VNH2VQYBYIL}

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

BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines.

C2weakest assumption

The clinical terminology substitution detection benchmark used for evaluation is representative of real-world clinical notes and error distributions, and the two domain-expert agents possess sufficient clinical knowledge to produce reliable independent analyses without introducing new hallucinations.

C3one line summary

BLUEmed combines hybrid RAG with structured multi-agent debate and a safety filter to detect terminology substitution errors in clinical notes, reaching 69.13% accuracy under few-shot prompting and outperforming single-agent and debate-only baselines.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-06-12T01:09:27.657935Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777

Aliases

arxiv: 2604.10389 · arxiv_version: 2604.10389v2 · doi: 10.48550/arxiv.2604.10389 · pith_short_12: OHFKPDACWGFM · pith_short_16: OHFKPDACWGFMCM6V · pith_short_8: OHFKPDAC

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/OHFKPDACWGFMCM6VNH2VQYBYIL \
  | 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: 71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "df0b16d226b9e8703846c617cea9577bc0fa594669e77312fed5591a66016ef4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-12T00:30:31Z",
    "title_canon_sha256": "92f2597d0e1a77b6948f0c95dec79d41b28001950cc23bc8ebf7d2943a1fff5a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.10389",
    "kind": "arxiv",
    "version": 2
  }
}