Pith Number

pith:SGZ4SGJV

pith:2022:SGZ4SGJVXWZXRTENYLEDTU2CHY

not attested not anchored not stored refs resolved

Phenaki: Variable Length Video Generation From Open Domain Textual Description

Dumitru Erhan, Han Zhang, Hernan Moraldo, Julius Kunze, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Pieter-Jan Kindermans, Ruben Villegas, Santiago Castro

Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes.

arxiv:2210.02399 v1 · 2022-10-05 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SGZ4SGJVXWZXRTENYLEDTU2CHY}

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

Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.

C2weakest assumption

That joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets.

C3one line summary

Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.

References

61 extracted · 61 resolved · 12 Pith anchors

[1] Vivit: A video vision transformer 2021

[2] Stochastic variational video prediction 2018

[3] Fitvid: Overﬁtting in pixel-level video prediction 2020

[4] Frozen in time: A joint video and image encoder for end-to-end retrieval 2021

[5] Con- ditional gan with discriminative ﬁlter generation for text-to-video synthesis 2019

Formal links

2 machine-checked theorem links

Cited by

20 papers in Pith

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls

Scaling Robot Learning with Semantically Imagined Experience

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

Receipt and verification

First computed	2026-05-17T23:38:45.945602Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f

Aliases

arxiv: 2210.02399 · arxiv_version: 2210.02399v1 · doi: 10.48550/arxiv.2210.02399 · pith_short_12: SGZ4SGJVXWZX · pith_short_16: SGZ4SGJVXWZXRTEN · pith_short_8: SGZ4SGJV

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/SGZ4SGJVXWZXRTENYLEDTU2CHY \
  | 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: 91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "28d83a4fde64ee7902ee14407e1415779ff182497a5c65ca4b48e0014bdead28",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2022-10-05T17:18:28Z",
    "title_canon_sha256": "c54beac000dad91c668bfb816e68d68aa9de9253c2b195eef3f845ca76408f71"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2210.02399",
    "kind": "arxiv",
    "version": 1
  }
}