Pith Number

pith:LW2MF4YF

pith:2026:LW2MF4YFBQDLCPV323T4XDNFC2

not attested not anchored not stored refs resolved

SkiP: When to Skip and When to Refine for Efficient Robot Manipulation

Chunjie Chen, Feng Yan, Guanqi Peng, Liang Lin, Lingbo Liu, Mingtong Dai, Xinyu Wu, Yongjie Bai

SkiP lets a single robot policy learn to skip low-information steps by relabeling actions to the next key segment.

arxiv:2605.15536 v1 · 2026-05-15 · 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{LW2MF4YFBQDLCPV323T4XDNFC2}

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

The resulting Skip Policy (SkiP) dynamically leaps over skip segments and intensively refines actions in key segments, within a single unified network requiring no learned skip planner or hierarchical structure.

C2weakest assumption

That replacing the behavior cloning target at each timestep in a skip segment with the action at the entrance of the next key segment still produces a policy that can be executed safely and successfully in closed-loop control without additional safety mechanisms or recovery behaviors.

C3one line summary

SkiP introduces action relabeling and Motion Spectrum Keying to skip redundant steps in robot trajectories, cutting executed steps by 15-40% while maintaining success rates across 72 simulated and 3 real tasks.

References

43 extracted · 43 resolved · 10 Pith anchors

[1] Sail: Faster-than-demonstration ex- ecution of imitation learning policies 2025

[2] Learning to see and act: Task-aware virtual view exploration for robotic manipulation, 2025 2025

[3] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control 2024 · arXiv:2410.24164

[4] RT-1: Robotics Transformer for Real-World Control at Scale 2023 · doi:10.15607/rss.2023.xix.025

[5] Diffusion policy: Visuomotor policy learning via action diffusion,

Receipt and verification

First computed	2026-05-20T00:01:04.089484Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5db4c2f3050c06b13ebbd6e7cb8da516a3f3902ef963ceb44b563d19b101d77a

Aliases

arxiv: 2605.15536 · arxiv_version: 2605.15536v1 · doi: 10.48550/arxiv.2605.15536 · pith_short_12: LW2MF4YFBQDL · pith_short_16: LW2MF4YFBQDLCPV3 · pith_short_8: LW2MF4YF

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/LW2MF4YFBQDLCPV323T4XDNFC2 \
  | 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: 5db4c2f3050c06b13ebbd6e7cb8da516a3f3902ef963ceb44b563d19b101d77a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "58d303fb09aedd932f07f820c45dd6454e7cb4d53d143b466b00c606e9e7c0aa",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-15T02:16:34Z",
    "title_canon_sha256": "173048e56d0a7b73aa755ddbda2f4b4ace439114a051037b04a2788348b1bb78"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15536",
    "kind": "arxiv",
    "version": 1
  }
}