Pith Number

pith:4SOQHN6W

pith:2023:4SOQHN6WTX5XVVLWJQWKF57RTI

not attested not anchored not stored refs resolved

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Anas Awadalla, Gabriel Ilharco, Irena Gao, Jack Hessel, Jenia Jitsev, Josh Gardner, Kalyani Marathe, Ludwig Schmidt, Mitchell Wortsman, Pang Wei Koh, Samir Gadre, Shiori Sagawa, Simon Kornblith, Wanrong Zhu, Yonatan Bitton, Yusuf Hanafy

OpenFlamingo delivers open-source vision-language models that reach 80-89 percent of Flamingo performance across seven datasets.

arxiv:2308.01390 v2 · 2023-08-02 · cs.CV · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4SOQHN6WTX5XVVLWJQWKF57RTI}

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

On seven vision-language datasets, OpenFlamingo models average between 80 - 89% of corresponding Flamingo performance.

C2weakest assumption

That the reported performance numbers were obtained under comparable evaluation conditions to the original Flamingo models and that the shared code and data suffice for independent reproduction of those numbers.

C3one line summary

OpenFlamingo provides open-source autoregressive vision-language models that achieve 80-89% of Flamingo performance on seven vision-language datasets.

References

48 extracted · 48 resolved · 13 Pith anchors

[1] Cm3: A causal masked multimodal model of the internet 2022

[2] Lawrence Zitnick, Devi Parikh, and Dhruv Batra 2015

[3] Flamingo: a visual language model for few-shot learning 2022

[4] Clip retrieval: Easily compute clip embeddings and build a clip re- trieval system with them 2022

[5] On the Opportunities and Risks of Foundation Models 2021 · arXiv:2108.07258

Formal links

2 machine-checked theorem links

Cited by

55 papers in Pith

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

Adapting Foundation Vision-Language Models to Medical Diagnosis via Query-Driven Expert Bridging

Receipt and verification

First computed	2026-05-18T02:47:22.656989Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e49d03b7d69dfb7ad5764c2ca2f7f19a12eb8486bb5217b1d952e72685c51805

Aliases

arxiv: 2308.01390 · arxiv_version: 2308.01390v2 · doi: 10.48550/arxiv.2308.01390 · pith_short_12: 4SOQHN6WTX5X · pith_short_16: 4SOQHN6WTX5XVVLW · pith_short_8: 4SOQHN6W

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/4SOQHN6WTX5XVVLWJQWKF57RTI \
  | 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: e49d03b7d69dfb7ad5764c2ca2f7f19a12eb8486bb5217b1d952e72685c51805

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1e893f201ce5c83c112cc1fd0d64167708aebb6e3f48e085afb530af8d87cfaf",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-08-02T19:10:23Z",
    "title_canon_sha256": "63c2f0843e42723e3598388b6146c56e7fbea819e120db01a141efebbe7c2583"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2308.01390",
    "kind": "arxiv",
    "version": 2
  }
}