pith. sign in
Pith Number

pith:WN5NGGKG

pith:2023:WN5NGGKGWZCNYQJCME6FZ32YDZ
not attested not anchored not stored refs resolved

PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering

Chaoyi Wu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang, Ziheng Zhao

A generative model trained on a 227k-pair medical VQA dataset from literature outperforms prior systems on clinical benchmarks after fine-tuning.

arxiv:2305.10415 v6 · 2023-05-17 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WN5NGGKGWZCNYQJCME6FZ32YDZ}

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

We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef-2019, significantly outperforming existing MedVQA models in generating relevant, accurate free-form answers.

C2weakest assumption

The PMC-VQA dataset constructed from literature sources provides representative coverage of real clinical images and questions without systematic biases from publication practices or selection effects.

C3one line summary

PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.

References

64 extracted · 64 resolved · 9 Pith anchors

[1] Flamingo: a visual language model for few-shot learning 2022
[2] Flamingo: a visual language model for few-shot learning 2022
[3] The medical segmentation decathlon.Nature Communications, 13(1):4128, 2022 2022
[4] Anas Awadalla, Irena Gao, Joshua Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Jenia Jitsev, et al. Openflamingo, 2023 2023
[5] Artificial intelligence in healthcare: transforming the practice of medicine.Future healthcare journal, 8(2):e188–e194, 2021 2021

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:49.836419Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b37ad31946b644dc4122613c5cef581e62ae96a3acbbf656ca39fc598d7a9411

Aliases

arxiv: 2305.10415 · arxiv_version: 2305.10415v6 · doi: 10.48550/arxiv.2305.10415 · pith_short_12: WN5NGGKGWZCN · pith_short_16: WN5NGGKGWZCNYQJC · pith_short_8: WN5NGGKG
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WN5NGGKGWZCNYQJCME6FZ32YDZ \
  | 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: b37ad31946b644dc4122613c5cef581e62ae96a3acbbf656ca39fc598d7a9411
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "814d4467633f689e887d433655429ab04ad7e5dfc245da5ae3c8e4e1774645c4",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-05-17T17:50:16Z",
    "title_canon_sha256": "d54473c845024f3af2c48d2eec48eff4f4ba48a71417a05da866311e26db8ccc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.10415",
    "kind": "arxiv",
    "version": 6
  }
}