Pith Number

pith:EQMMM6FJ

pith:2026:EQMMM6FJF22BF3HHNM6OVIMY4P

not attested not anchored not stored refs pending

MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support

Akhil Arora, Alexandra Kulinkina, David Sasu, Fay Elhassan, Jiayi Ma, Julien Stalhandske, Lars Klein, Mary-Anne Hartley, Yena Chang, Yusuf Kesmen

Separating language from reasoning in medical AI allows a Bayesian engine to deliver calibrated diagnosis and beat larger standalone models.

arxiv:2604.20022 v2 · 2026-04-21 · cs.LG · cs.AI · 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{EQMMM6FJF22BF3HHNM6OVIMY4P}

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

This separation yields three properties no autonomous LLM can offer: calibrated selective diagnosis with a continuously adjustable accuracy-coverage tradeoff, a statistical separation gap where even a cheap sensor paired with the engine outperforms a frontier standalone model from the same family at a fraction of the cost, and robustness to adversarial patient communication styles that cause standalone doctors to collapse.

C2weakest assumption

That an LLM used only as a sensor can reliably convert natural language into accurate structured evidence without systematic errors that the Bayesian engine cannot correct, and that the knowledge bases (empirical or LLM-generated) supply priors and likelihoods sufficient for the claimed performance gains.

C3one line summary

BMBE separates LLM language handling from a standalone Bayesian diagnostic engine, producing calibrated selective diagnosis, a performance gap over frontier LLMs, and robustness to adversarial inputs.

Receipt and verification

First computed	2026-05-20T02:05:43.436516Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2418c678a92eb412ece76b3ceaa198e3dda189c58edf55ac74a9da69374ea331

Aliases

arxiv: 2604.20022 · arxiv_version: 2604.20022v2 · doi: 10.48550/arxiv.2604.20022 · pith_short_12: EQMMM6FJF22B · pith_short_16: EQMMM6FJF22BF3HH · pith_short_8: EQMMM6FJ

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/EQMMM6FJF22BF3HHNM6OVIMY4P \
  | 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: 2418c678a92eb412ece76b3ceaa198e3dda189c58edf55ac74a9da69374ea331

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4f8db9369fe22c7321438f57c509168fffaee8b7e0c9e16a250a60ad34cb404e",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-21T21:59:57Z",
    "title_canon_sha256": "26ab8e4c96eb874a9fa9dab3844fec69a305ef9ee71c90093236a075c8e9e7bc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.20022",
    "kind": "arxiv",
    "version": 2
  }
}