Pith Number

pith:U6D47TK2

pith:2026:U6D47TK22EIHFMK2TO2P53OJ6V

not attested not anchored not stored refs resolved

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

Bailing Wang, Bin Yu, Changti Wu, Cong Huang, Haishan Liu, Hang Yuan, Kai Chen, Shijie Lian, Xiaopeng Lin, Yuliang Wei, Zhaolong Shen

FrameSkip improves VLA success rates by training only on high-importance frames from demonstrations.

arxiv:2605.13757 v1 · 2026-05-13 · cs.RO

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U6D47TK22EIHFMK2TO2P53OJ6V}

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

Across RoboCasa-GR1, SimplerEnv, and LIBERO, FrameSkip improves the success-retention trade-off over full-frame training and simpler frame selection variants, achieving a macro-average success rate of 76.15% across the three benchmarks compared with 66.50% for full-frame training while using a compressed trajectory view that retains 20% of unique frames in the main setting.

C2weakest assumption

That the four scoring signals (action variation, visual-action coherence, task-progress priors, gripper-transition preservation) reliably identify manipulation-critical frames without systematic bias or omission of important transitions on unseen tasks.

C3one line summary

FrameSkip improves VLA policy training success from 66.50% to 76.15% by selecting high-importance frames and retaining only 20% of unique frames across three benchmarks.

References

21 extracted · 21 resolved · 14 Pith anchors

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

[2] InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy · arXiv:2510.13778

[3] Robot data curation with mutual information estimators

[4] Thinkact: Vision- language-action reasoning via reinforced visual latent planning · arXiv:2507.16815

[5] $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization · arXiv:2504.16054

Receipt and verification

First computed	2026-05-18T02:44:16.329859Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a787cfcd5ad11072b15a9bb4feedc9f568b28dbd9a568c25a0a659e6293c0fa7

Aliases

arxiv: 2605.13757 · arxiv_version: 2605.13757v1 · doi: 10.48550/arxiv.2605.13757 · pith_short_12: U6D47TK22EIH · pith_short_16: U6D47TK22EIHFMK2 · pith_short_8: U6D47TK2

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/U6D47TK22EIHFMK2TO2P53OJ6V \
  | 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: a787cfcd5ad11072b15a9bb4feedc9f568b28dbd9a568c25a0a659e6293c0fa7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0ce293f0d6783cc86f48b573a291ad47f9f0c6a928490b56ee2ce2c2e82d21fe",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T16:38:05Z",
    "title_canon_sha256": "ca75cf7e7eb25bd7456b6b4e57a31c554a9f19fc03b545918b46b0c431a6d8b0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13757",
    "kind": "arxiv",
    "version": 1
  }
}