Pith Number

pith:CIFBAGXB

pith:2025:CIFBAGXB6DSHLM5PYSIZRSHSOY

not attested not anchored not stored refs resolved

GR-3 Technical Report

Chilam Cheang, Haixin Shi, Hang Li, Hao Niu, Hongtao Wu, Jiafeng Xu, Jiawen Tian, Liqun Huang, Sijin Chen, Tao Kong, Wanli Peng, Wenxuan Ou, Xiao Ma, Xin Xiao, Yichu Yang, Yifeng Li, Yingdong Hu, Yuxiao Liu, Yuyang Xiao, Zeyu Ren, Zhongren Cui

GR-3 is a vision-language-action model that generalizes to novel objects, abstract instructions, and long-horizon dexterous tasks through combined web-scale and robot data training.

arxiv:2507.15493 v2 · 2025-07-21 · cs.RO · 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{CIFBAGXB6DSHLM5PYSIZRSHSOY}

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

GR-3 surpasses the state-of-the-art baseline method, π0, on a wide variety of challenging tasks.

C2weakest assumption

That the multi-faceted training recipe of web-scale vision-language co-training, VR human trajectory data, and robot imitation learning produces the claimed generalization to novel objects, abstract instructions, and long-horizon dexterous tasks without heavy post-hoc tuning or task-specific overfitting.

C3one line summary

GR-3 is a VLA model that generalizes to novel objects, environments, and abstract instructions, outperforms the π0 baseline, and integrates with the new ByteMini bi-manual mobile robot.

References

78 extracted · 78 resolved · 37 Pith anchors

[1] Affordances from human videos as a versatile representation for robotics 2023

[2] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[3] A careful examination of large behavior models for multitask dexterous manipulation 2025

[4] PaliGemma: A versatile 3B VLM for transfer 2024 · arXiv:2407.07726

[5] //arxiv.org/abs/2405.01527 2024

Formal links

2 machine-checked theorem links

Cited by

27 papers in Pith

Point Tracking Improves World Action Models

Action with Visual Primitives

Learning Native Continuation for Action Chunking Flow Policies

Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention

Dynamic Execution Commitment of Vision-Language-Action Models

Receipt and verification

First computed	2026-05-17T23:38:14.637376Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

120a101ae1f0e475b3afc49198c8f276191da960ad08bc5bf7e3687fcc15e680

Aliases

arxiv: 2507.15493 · arxiv_version: 2507.15493v2 · doi: 10.48550/arxiv.2507.15493 · pith_short_12: CIFBAGXB6DSH · pith_short_16: CIFBAGXB6DSHLM5P · pith_short_8: CIFBAGXB

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/CIFBAGXB6DSHLM5PYSIZRSHSOY \
  | 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: 120a101ae1f0e475b3afc49198c8f276191da960ad08bc5bf7e3687fcc15e680

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5ee6562e7038be26845b2d75f72ba35e533effe9e5a823d166c03e11c2c3eef3",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-07-21T10:54:13Z",
    "title_canon_sha256": "966ac5cf5aae66e8f56a341483469b131fda7e9732a72cb2ad9fa207943c0de8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.15493",
    "kind": "arxiv",
    "version": 2
  }
}