Pith Number

pith:TTCUEKYG

pith:2026:TTCUEKYG6RL3WJT7RQWGU646DJ

not attested not anchored not stored refs resolved

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation

Dong-Ki Kim, Han Lin, Jaehong Yoon, Jaemin Cho, Mohit Bansal, Shayegan Omidshafiei, Yidong Huang, Yue Zhang, Zun Wang

PhyMotion scores recovered 3D human meshes in a physics simulator to reward realistic motion in generated videos.

arxiv:2605.14269 v1 · 2026-05-14 · 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{TTCUEKYG6RL3WJT7RQWGU646DJ}

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

Optimizing PhyMotion leads to larger and more consistent improvements than optimizing existing rewards, improving motion realism across both autoregressive and bidirectional video generators under both automatic metrics and blind human evaluation (+68 Elo gain).

C2weakest assumption

That SMPL mesh recovery from generated videos is sufficiently accurate and that retargeting those meshes into MuJoCo faithfully captures the physical violations that matter to human viewers.

C3one line summary

PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.

References

26 extracted · 26 resolved · 7 Pith anchors

[1] Onestory: Coherent multi-shot video generation with adaptive memory.CVPR, 2026a

[2] Videojam: Joint appearance-motion representations for en- hanced motion generation in video models

[3] Seedance 1.0: Exploring the Boundaries of Video Generation Models · arXiv:2506.09113

[4] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning · arXiv:2501.12948

[5] GARDO: Reinforcing diffusion models without reward hacking

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.414128Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9cc5422b06f457bb267f8c2c6a7b9e1a45aa4d3eed58257e8bccb8d200b0acea

Aliases

arxiv: 2605.14269 · arxiv_version: 2605.14269v1 · doi: 10.48550/arxiv.2605.14269 · pith_short_12: TTCUEKYG6RL3 · pith_short_16: TTCUEKYG6RL3WJT7 · pith_short_8: TTCUEKYG

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/TTCUEKYG6RL3WJT7RQWGU646DJ \
  | 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: 9cc5422b06f457bb267f8c2c6a7b9e1a45aa4d3eed58257e8bccb8d200b0acea

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "26ab5e1643033c625c87419d4da78505587c05a4941951d5a626bf982cdcd779",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T02:12:13Z",
    "title_canon_sha256": "c8ca05b56f8c1983e481a44e3b823d30bb21113ec0854c596779632c67671d6a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14269",
    "kind": "arxiv",
    "version": 1
  }
}