Pith Number

pith:KSFDUBSL

pith:2024:KSFDUBSLY7LMVAHJXMQ3HSFJKT

not attested not anchored not stored refs resolved

Diffusion Models Are Real-Time Game Engines

Dani Valevski, Moab Arar, Shlomi Fruchter, Yaniv Leviathan

A diffusion model trained on gameplay can serve as a complete real-time game engine for complex environments like DOOM.

arxiv:2408.14837 v2 · 2024-08-27 · cs.LG · cs.AI · 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{KSFDUBSLY7LMVAHJXMQ3HSFJKT}

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

GameNGen is the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality, running at 20 frames per second on a single TPU while remaining stable over extended multi-minute play sessions.

C2weakest assumption

That conditioning augmentations and decoder fine-tuning will continue to prevent error accumulation and visual drift during extended auto-regressive rollouts beyond the tested multi-minute sessions, without additional mechanisms for long-term memory or consistency.

C3one line summary

A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.

References

88 extracted · 88 resolved · 15 Pith anchors

[1] Advances in Neural Information Processing Systems , volume=

[2] Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

[3] Scaling Autoregressive Models for Content-Rich Text-to-Image Generation · arXiv:2206.10789

[4] The Tenth International Conference on Learning Representations, 2022

[8] Fast high-resolution image synthesis with latent adversarial diffusion distillation

Formal links

3 machine-checked theorem links

Cited by

28 papers in Pith

SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models

Simulus: Combining Improvements in Sample-Efficient World Model Agents

PROWL: Prioritized Regret-Driven Optimization for World Model Learning

ReactiveGWM: Steering NPC in Reactive Game World Models

VRAG: Learning World Models for Interactive Video Generation

Receipt and verification

First computed	2026-05-17T23:38:47.941907Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

548a3a064bc7d6ca80e9bb21b3c8a954fdfd5eb51deb516a8bcd3a522f25ae72

Aliases

arxiv: 2408.14837 · arxiv_version: 2408.14837v2 · doi: 10.48550/arxiv.2408.14837 · pith_short_12: KSFDUBSLY7LM · pith_short_16: KSFDUBSLY7LMVAHJ · pith_short_8: KSFDUBSL

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/KSFDUBSLY7LMVAHJXMQ3HSFJKT \
  | 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: 548a3a064bc7d6ca80e9bb21b3c8a954fdfd5eb51deb516a8bcd3a522f25ae72

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "949dd90a855138b0a820eaeaa2a2d9335f808b677fc4a2d6f93d92d21b1ade77",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-08-27T07:46:07Z",
    "title_canon_sha256": "dc4be22f667ff59b3227ecc3e5353ce7a523c23442c7a06f6566d8fedad52ef8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.14837",
    "kind": "arxiv",
    "version": 2
  }
}