Pith Number

pith:EJIVFRXU

pith:2023:EJIVFRXU6P2MSHA7YTIQRPXXRC

not attested not anchored not stored refs resolved

ViperGPT: Visual Inference via Python Execution for Reasoning

Carl Vondrick, D\'idac Sur\'is, Sachit Menon

ViperGPT uses code generation to create Python programs that combine vision models for answering complex visual queries without training.

arxiv:2303.08128 v1 · 2023-03-14 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EJIVFRXU6P2MSHA7YTIQRPXXRC}

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 simple approach requires no further training, and achieves state-of-the-art results across various complex visual tasks.

C2weakest assumption

That a code-generation model can reliably produce correct, executable compositions of the provided vision modules for arbitrary queries without systematic errors in program logic or API usage.

C3one line summary

ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.

References

66 extracted · 66 resolved · 12 Pith anchors

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

[2] Neural module networks 2016

[3] arXiv preprint arXiv:1811.12889 , year= 2019 · arXiv:1811.12889

[4] The Consciousness Prior, Dec 2019

[5] Bravo, Sudhanshu Mittal, Simon Ging, and Thomas Brox 2022

Formal links

1 machine-checked theorem link

Cited by

23 papers in Pith

Chat Modeling: Interaction-Enhanced Agent Framework for Visualizing Literature-Grounded Biological Structures

What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction

Grounded Reinforcement Learning for Visual Reasoning

PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models

PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications

Receipt and verification

First computed	2026-05-17T23:38:13.427145Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

225152c6f4f3f4c91c1fc4d108bef788a12aea3102ff5ebaa7da712a657626ac

Aliases

arxiv: 2303.08128 · arxiv_version: 2303.08128v1 · doi: 10.48550/arxiv.2303.08128 · pith_short_12: EJIVFRXU6P2M · pith_short_16: EJIVFRXU6P2MSHA7 · pith_short_8: EJIVFRXU

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/EJIVFRXU6P2MSHA7YTIQRPXXRC \
  | 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: 225152c6f4f3f4c91c1fc4d108bef788a12aea3102ff5ebaa7da712a657626ac

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c2e103dccd0a0f4cdf6a0868e0ac08d507e2a78eaf6cae4a8431e4e07a4e19f3",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-03-14T17:57:47Z",
    "title_canon_sha256": "898de40b5c3a0c4369f3ad602ee1292bf94bf954d63805c955271fb60fc783da"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2303.08128",
    "kind": "arxiv",
    "version": 1
  }
}