Pith Number

pith:LLGNM4DI

pith:2026:LLGNM4DI7XWZSDLLWRAVB2GUQ2

not attested not anchored not stored refs resolved

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

Andrew F. Luo, Boyu Zhou, Daojie Peng, Fulong Ma, Jiahang Cao, Jian Guo, Jun Ma, Ping Luo, Qiang Zhang, Xupeng Xie

Reweighting robotic action losses by inverse velocity improves foundation model performance on manipulation tasks

arxiv:2605.13548 v1 · 2026-05-13 · cs.RO · 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{LLGNM4DI7XWZSDLLWRAVB2GUQ2}

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

AttenA+ significantly elevates the ceilings of current state-of-the-art models. Specifically, it improves OpenVLA-OFT to 98.6% (+1.5%) on the Libero benchmark and pushes FastWAM to 92.4% (+0.6%) on RoboTwin 2.0.

C2weakest assumption

That reweighting the training objective by the inverse velocity field naturally aligns model learning capacity with the physical demands of manipulation, with velocity serving as the primary proxy for kinematic criticality.

C3one line summary

AttenA+ applies velocity-driven action attention to reweight training objectives toward kinematically critical low-velocity segments, yielding small benchmark gains on Libero and RoboTwin without added parameters.

References

42 extracted · 42 resolved · 22 Pith anchors

[1] OpenVLA: An Open-Source Vision-Language-Action Model 2024 · arXiv:2406.09246

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

[3] Structured observation language for efficient and generalizable vision-language navigation.arXiv preprint arXiv:2603.27577, 2026 2026

[4] RT-1: Robotics Transformer for Real-World Control at Scale 2022 · arXiv:2212.06817

[5] Rt-2: Vision-language-action models transfer web knowledge to robotic control 2023

Receipt and verification

First computed	2026-05-18T02:44:23.854171Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5accd67068fded990d6bb44150e8d486910ffd9bc11485239db2f7828826b2bc

Aliases

arxiv: 2605.13548 · arxiv_version: 2605.13548v1 · doi: 10.48550/arxiv.2605.13548 · pith_short_12: LLGNM4DI7XWZ · pith_short_16: LLGNM4DI7XWZSDLL · pith_short_8: LLGNM4DI

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/LLGNM4DI7XWZSDLLWRAVB2GUQ2 \
  | 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: 5accd67068fded990d6bb44150e8d486910ffd9bc11485239db2f7828826b2bc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "badbc8b7c5bd85f26ecff96f91b954fb4bc45e097f538b476790340cb7c98791",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T13:55:37Z",
    "title_canon_sha256": "b24f31a1c2f838ac58bad655f7d58da827601e42327a07ff79809a91c8431b4f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13548",
    "kind": "arxiv",
    "version": 1
  }
}