Pith Number

pith:EM3FJITN

pith:2021:EM3FJITNE6ISPGXOZDNQ3XXNJG

not attested not anchored not stored refs resolved

Zero-Shot Text-to-Image Generation

Aditya Ramesh, Alec Radford, Chelsea Voss, Gabriel Goh, Ilya Sutskever, Mark Chen, Mikhail Pavlov, Scott Gray

A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale.

arxiv:2102.12092 v2 · 2021-02-24 · cs.CV · 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{EM3FJITNE6ISPGXOZDNQ3XXNJG}

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

With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.

C2weakest assumption

That simply increasing model size and data volume will continue to close the gap to specialized models without introducing new failure modes or requiring additional inductive biases.

C3one line summary

A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.

References

23 extracted · 23 resolved · 0 Pith anchors

[1] Bowman et al 2015

[2] Using a linear annealing schedule for this typically led to divergence

[3] row, column, row, row 2017

[4] Our model uses 128 gradient scales, one for each of its resblocks

[5] In particular, store all gains, biases, embeddings, and unembeddings in 32-bit precision, with 32-bit gradients (including for remote communication) and 32-bit Adam moments

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

Token-to-Token Alignment of Text Embeddings for Semantic Blending

ZIPP:Zero-shot Image Personalization from Personas

Mapping Whisper Representations to Human ECoG Responses with Interpretable Time-Resolved Neural Encoding

DetailCLIP: Injecting Image Details into CLIP's Feature Space

LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging

Receipt and verification

First computed	2026-05-18T04:19:54.694687Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f

Aliases

arxiv: 2102.12092 · arxiv_version: 2102.12092v2 · doi: 10.48550/arxiv.2102.12092 · pith_short_12: EM3FJITNE6IS · pith_short_16: EM3FJITNE6ISPGXO · pith_short_8: EM3FJITN

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/EM3FJITNE6ISPGXOZDNQ3XXNJG \
  | 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: 233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7b1b5ca549ba2968b6bbe3695aa883be7800890084b682e1f3e752983ebc93ab",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-02-24T06:42:31Z",
    "title_canon_sha256": "d8fed5258329bcb50974f59ef498b8b49dee66857162c9241f9695116f4ebbec"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2102.12092",
    "kind": "arxiv",
    "version": 2
  }
}