Pith Number

pith:5UGMR4BF

pith:2023:5UGMR4BFC23VOTT3536VCKLDOX

not attested not anchored not stored refs resolved

Capabilities of GPT-4 on Medical Challenge Problems

Dean Carignan, Eric Horvitz, Harsha Nori, Nicholas King, Scott Mayer McKinney

GPT-4 exceeds the USMLE passing score by over 20 points without any medical-specific training or prompts.

arxiv:2303.13375 v2 · 2023-03-20 · cs.CL · 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{5UGMR4BFC23VOTT3536VCKLDOX}

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

GPT-4, without any specialized prompt crafting, exceeds the passing score on USMLE by over 20 points and outperforms earlier general-purpose models (GPT-3.5) as well as models specifically fine-tuned on medical knowledge (Med-PaLM).

C2weakest assumption

The official USMLE practice materials used are representative of the actual exam content and difficulty, and the model has not memorized the specific questions during pre-training (probed but not fully detailed in available text).

C3one line summary

GPT-4 exceeds the USMLE passing score by more than 20 points and outperforms both GPT-3.5 and the medically fine-tuned Med-PaLM on the MultiMedQA benchmarks.

References

23 extracted · 23 resolved · 8 Pith anchors

[1] Guidelines for human-AI interaction 2019

[2] Lan- guage models are few-shot learners 1901

[3] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · arXiv:1810.04805

[4] Automated identiﬁcation of adults at risk for in-hospital clinical deterioration 1951

[5] Who goes ﬁrst? Inﬂuences of human-ai workﬂow on decision making in clinical imaging 2022

Formal links

1 machine-checked theorem link

Cited by

40 papers in Pith

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

Towards Expert-Level Medical Question Answering with Large Language Models

Data-Centric Foundation Models in Computational Healthcare: A Survey

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark

Entry-level guide to the use of large language models for medical research

Receipt and verification

First computed	2026-05-17T23:38:52.415467Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ed0cc8f02516b7574e7beefd51296375e3a59b4d753fffbd438f7f2847188086

Aliases

arxiv: 2303.13375 · arxiv_version: 2303.13375v2 · doi: 10.48550/arxiv.2303.13375 · pith_short_12: 5UGMR4BFC23V · pith_short_16: 5UGMR4BFC23VOTT3 · pith_short_8: 5UGMR4BF

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/5UGMR4BFC23VOTT3536VCKLDOX \
  | 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: ed0cc8f02516b7574e7beefd51296375e3a59b4d753fffbd438f7f2847188086

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "38b3de569bb0529923d8389fe1f0282ce3628f0db9ade774bc774476b9ac5af4",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-03-20T16:18:38Z",
    "title_canon_sha256": "cfc8ec73effe4ce55f50dbb8ad31cd9b988236739f35cad6e46b2fc5cdb20ec1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2303.13375",
    "kind": "arxiv",
    "version": 2
  }
}