Pith Number

pith:XYRW52VE

pith:2022:XYRW52VEY4L236AVZCPU5VWAUR

not attested not anchored not stored refs resolved

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Adrian Wong, Andy Zeng, Aveek Purohit, Brian Ichter, Federico Tombari, Johnny Lee, Krzysztof Choromanski, Maria Attarian, Michael Ryoo, Pete Florence, Stefan Welker, Vikas Sindhwani, Vincent Vanhoucke

Pretrained models can be composed zero-shot through multimodal prompting to exchange information and gain new multimodal capabilities without finetuning.

arxiv:2204.00598 v2 · 2022-04-01 · cs.CV · cs.AI · cs.CL · 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{XYRW52VEY4L236AVZCPU5VWAUR}

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

multiple pretrained models may be composed zero-shot i.e., via multimodal-informed prompting, to exchange information with each other and capture new multimodal capabilities, without requiring finetuning

C2weakest assumption

That distinct capabilities stored in separately trained foundation models can be reliably accessed and combined through prompting alone, without finetuning or task-specific adaptation that would break the zero-shot property.

C3one line summary

Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.

References

142 extracted · 142 resolved · 17 Pith anchors

[1] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2018 · arXiv:1810.04805

[2] T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information process 1901

[3] A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, et al. Learning transferable visual models from natural language supervision. In Internati 2021

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

[5] J. Li, R. Selvaraju, A. Gotmare, S. Joty, C. Xiong, and S. C. H. Hoi. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processi 2021

Formal links

1 machine-checked theorem link

Cited by

26 papers in Pith

LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting

STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval

From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning

BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections

Receipt and verification

First computed	2026-05-17T23:38:48.286458Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

be236eeaa4c717adf815c89f4ed6c0a4718b32bca204501fa8988d1d841daea7

Aliases

arxiv: 2204.00598 · arxiv_version: 2204.00598v2 · doi: 10.48550/arxiv.2204.00598 · pith_short_12: XYRW52VEY4L2 · pith_short_16: XYRW52VEY4L236AV · pith_short_8: XYRW52VE

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/XYRW52VEY4L236AVZCPU5VWAUR \
  | 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: be236eeaa4c717adf815c89f4ed6c0a4718b32bca204501fa8988d1d841daea7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "577a8a3b32c6a40980cc97108847a1f07fcfe408cc83e3df4277ff16066621c8",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2022-04-01T17:43:13Z",
    "title_canon_sha256": "6c6ab2fbb224c4add86a606e514200ffee80459270e2a6a79154866871bd8d58"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2204.00598",
    "kind": "arxiv",
    "version": 2
  }
}