Pith Number

pith:D4K4N5SV

pith:2026:D4K4N5SVHOISP3FWI4ZYRO3PEB

not attested not anchored not stored refs resolved

SPLIT: Separating Physical-Contact via Latent Arithmetic in Image-Based Tactile Sensors

Nicol\'as Navarro-Guerrero, Wadhah Zai El Amri

Latent arithmetic in a learned space separates contact geometry from the optical properties of image-based tactile sensors.

arxiv:2604.24449 v1 · 2026-04-27 · cs.RO · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{D4K4N5SVHOISP3FWI4ZYRO3PEB}

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

Central to our approach is a latent space arithmetic strategy that explicitly disentangles contact geometry from sensor-specific optical properties... this disentanglement allows SPLIT to adapt to diverse DIGIT backgrounds and even transfer data to distinct sensors like the GelSight R1.5 without full model retraining.

C2weakest assumption

That arithmetic operations in the learned latent space cleanly isolate geometry from optics with negligible crosstalk or reconstruction artifacts, and that the calibrated FEM mesh accurately captures real-world soft-body deformations under contact.

C3one line summary

SPLIT disentangles physical contact geometry from optical effects via latent arithmetic for adaptable, efficient simulation of tactile sensors.

References

2 extracted · 2 resolved · 0 Pith anchors

[1] The Objectfolder Benchmark: Multisensory Learning with Neural and Real Objects, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17276–17286. Zai El Amri and Navarro-Guer 2016 · doi:10.5254/1.3542351

[2] IEEE Robot Autom Lett 5, 3838–3845 2020 · doi:10.1109/lra.2020.2977257

Receipt and verification

First computed	2026-06-12T01:09:28.060160Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1f15c6f6553b9127ecb6473388bb6f205762c0f7b4bd0a5c9768db6bc2cf260f

Aliases

arxiv: 2604.24449 · arxiv_version: 2604.24449v1 · doi: 10.48550/arxiv.2604.24449 · pith_short_12: D4K4N5SVHOIS · pith_short_16: D4K4N5SVHOISP3FW · pith_short_8: D4K4N5SV

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/D4K4N5SVHOISP3FWI4ZYRO3PEB \
  | 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: 1f15c6f6553b9127ecb6473388bb6f205762c0f7b4bd0a5c9768db6bc2cf260f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9d74b99c346b35b9af73b2fa2e824c9ed187ed470b7941a0d03f7d9d6043d075",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-04-27T13:13:58Z",
    "title_canon_sha256": "07c54a9bf8de83d13e6a8edde7e8cd2c41eeb84481ee6531b39acfeb93b61f3b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.24449",
    "kind": "arxiv",
    "version": 1
  }
}