Pith Number

pith:C32FX3ZN

pith:2025:C32FX3ZNYSA4UYVQ3E2E3C6UAA

not attested not anchored not stored refs resolved

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

Anthony Hu, Elahe Arani, George Fedoseev, Gianluca Corrado, Jamie Shotton, Lloyd Russell, Lorenzo Bertoni

GAIA-2 generates high-resolution multi-camera driving videos from structured inputs like vehicle dynamics, agent positions, and road semantics.

arxiv:2503.20523 v1 · 2025-03-26 · cs.CV · cs.AI · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{C32FX3ZNYSA4UYVQ3E2E3C6UAA}

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

GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments.

C2weakest assumption

That the generated videos are sufficiently realistic, consistent, and free of artifacts to serve as effective training data for autonomous driving systems without introducing biases or failures when transferred to real vehicles.

C3one line summary

GAIA-2 is a controllable latent diffusion world model that produces spatiotemporally consistent multi-view videos for autonomous driving simulation across diverse geographies.

References

52 extracted · 52 resolved · 2 Pith anchors

[1] D. P. Kingma and M. Welling. Auto-encoding variational bayes.Proceedings of the International Conference on Learning Representations (ICLR) , 2014 2014

[2] Cosmos World Foundation Model Platform for Physical AI 2025 · arXiv:2501.03575

[3] van den Oord, O 2017

[4] P. Esser, R. Rombach, and B. Ommer. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021 2021

[5] GAIA-1: A Generative World Model for Autonomous Driving 2023 · arXiv:2309.17080

Formal links

2 machine-checked theorem links

Cited by

32 papers in Pith

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation

Grounding Driving VLA via Inverse Kinematics

Ozone: A Unified Platform for Transportation Research

Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving

PanoWorld: Geometry-Consistent Panoramic Video World Modeling

Receipt and verification

First computed	2026-05-17T23:38:52.407613Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

16f45bef2dc481ca62b0d9344d8bd40035eaae2c01e698f7c62fd2e37dd2db93

Aliases

arxiv: 2503.20523 · arxiv_version: 2503.20523v1 · doi: 10.48550/arxiv.2503.20523 · pith_short_12: C32FX3ZNYSA4 · pith_short_16: C32FX3ZNYSA4UYVQ · pith_short_8: C32FX3ZN

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/C32FX3ZNYSA4UYVQ3E2E3C6UAA \
  | 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: 16f45bef2dc481ca62b0d9344d8bd40035eaae2c01e698f7c62fd2e37dd2db93

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb599b61127c4e4ed010c5302ce50dd0aec525513754619b7e36da42bc535029",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-03-26T13:11:35Z",
    "title_canon_sha256": "da0c2c4ad3f32678ee5c887c2e1236f46fc1af634d54bd819e57d92fa8043270"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.20523",
    "kind": "arxiv",
    "version": 1
  }
}