Pith Number

pith:GRKOU2FD

pith:2025:GRKOU2FDDY7KB3YHAANYSD63CS

not attested not anchored not stored refs resolved

FCBV-Net: Category-Level Robotic Garment Smoothing via Feature-Conditioned Bimanual Value Prediction

Jing Qiu, Mohammed Daba

Conditioning bimanual action values on frozen 3D geometric features lets robots smooth unseen garments with far smaller performance loss than baselines.

arxiv:2508.05153 v2 · 2025-08-07 · 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{GRKOU2FDDY7KB3YHAANYSD63CS}

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 decoupling of geometric understanding from bimanual action value learning enables better category-level generalization

C2weakest assumption

That pre-trained and frozen dense geometric features extracted from 3D point clouds remain sufficiently informative and robust across intra-category variations in the CLOTH3D dataset without any task-specific fine-tuning or adaptation.

C3one line summary

FCBV-Net achieves superior category-level generalization for bimanual garment smoothing by conditioning value prediction on static pre-trained dense geometric features from point clouds, showing only 11.5% efficiency drop on unseen garments versus much larger drops in baselines.

References

27 extracted · 27 resolved · 1 Pith anchors

[1] Ide ntifying the potential for robotics to assist older adults in differe nt living environments 2014

[2] Managing activity difﬁculties at ho me: A survey of medicare beneﬁciaries 2008

[3] Challenges and outlook in robotic manipula tion of deformable objects 2022

[4] Unigarmentman ip: A uniﬁed framework for category-level garment manipulatio n via dense visual correspondence 2024

[5] Speedfolding: Learning efﬁcient bimanual folding of garm ents 2022

Receipt and verification

First computed	2026-06-09T01:05:08.595273Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3454ea68a31e3ea0ef07001b890fdb1491e2d9ee404af276d914ceaa1bbfaa93

Aliases

arxiv: 2508.05153 · arxiv_version: 2508.05153v2 · doi: 10.48550/arxiv.2508.05153 · pith_short_12: GRKOU2FDDY7K · pith_short_16: GRKOU2FDDY7KB3YH · pith_short_8: GRKOU2FD

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/GRKOU2FDDY7KB3YHAANYSD63CS \
  | 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: 3454ea68a31e3ea0ef07001b890fdb1491e2d9ee404af276d914ceaa1bbfaa93

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9dbca35915c0a469d47c61ed136fa3183a416cd41729c4d625e76370284a4251",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-08-07T08:37:45Z",
    "title_canon_sha256": "5ffbed46c4d371a255ba967e1a0e07f87a393a9292ee5429aa75487db22645f4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.05153",
    "kind": "arxiv",
    "version": 2
  }
}