Pith Number

pith:3ICG2E6R

pith:2026:3ICG2E6RA6GZXUIXEZKABTNWL7

not attested not anchored not stored refs resolved

RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

Harold Haodong Chen, Sirui Chen, Wenhang Ge, Ying-Cong Chen, Yingjie Xu

A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.

arxiv:2605.13775 v1 · 2026-05-13 · cs.RO · 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{3ICG2E6RA6GZXUIXEZKABTNWL7}

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

RoboEvolve elevates base planners by 30 absolute points and amplifies simulator success by 48% on average, surpassing fully supervised baselines with merely 500 unlabeled seeds—a 50x reduction—while demonstrating robust continual learning without catastrophic forgetting.

C2weakest assumption

That the semantic-controlled multi-granular reward and nighttime mining of near-miss failures can enforce physical grounding and eliminate hallucinations in the VGM without any external verification or real-robot feedback.

C3one line summary

A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.

References

83 extracted · 83 resolved · 27 Pith anchors

[1] Mind-v: Hierarchical video generation for long-horizon robotic manipulation with rl-based physical alignment

[2] CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer · arXiv:2408.06072

[3] European conference on computer vision , pages= 2024

[4] HunyuanVideo: A Systematic Framework For Large Video Generative Models · arXiv:2412.03603

[5] World Action Models are Zero-shot Policies · arXiv:2602.15922

Receipt and verification

First computed	2026-05-18T02:44:15.926422Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

da046d13d1078d9bd117265400cdb65fc4100408c09e0b4979a7aab90b2a236a

Aliases

arxiv: 2605.13775 · arxiv_version: 2605.13775v1 · doi: 10.48550/arxiv.2605.13775 · pith_short_12: 3ICG2E6RA6GZ · pith_short_16: 3ICG2E6RA6GZXUIX · pith_short_8: 3ICG2E6R

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/3ICG2E6RA6GZXUIXEZKABTNWL7 \
  | 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: da046d13d1078d9bd117265400cdb65fc4100408c09e0b4979a7aab90b2a236a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cfd3e2b32bbeda56f2440d71939ec6e7c4400f2a89d85d9495f953b2210152f8",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T16:54:36Z",
    "title_canon_sha256": "328a3b6e0c3d344bb503df46cd324d610552c22aaa5b03aef663bacb9a2258cf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13775",
    "kind": "arxiv",
    "version": 1
  }
}