Pith Number

pith:M2JUNQY3

pith:2026:M2JUNQY3ILYDQRFJPG77JONQLH

not attested not anchored not stored refs resolved

A Unified Non-Parametric and Interpretable Point Cloud Analysis via t-FCW Graph Representation

Benjamin Ng, Bowen Liu, Chan-Tong Lam, Haijian Lai, Jo\~ao Macedo, Man Xu, Sio-Kei Im

An empowered t-FCW graph representation embeds point clouds non-parametrically into a metric space while inheriting surface robustness and supplying dimension-wise interpretability.

arxiv:2605.15475 v1 · 2026-05-14 · cs.CV · cs.MM

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{M2JUNQY3ILYDQRFJPG77JONQLH}

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 empowered t-FCW inherits robustness from surface descriptors, provides interpretability through dimension-wise relations, and enables a highly efficient and interpretable network that processes ModelNet40 classification in approximately 7 seconds on an NVIDIA RTX A5000 GPU while functioning as a standalone baseline or plug-in.

C2weakest assumption

That the properties of the empowered t-FCW graph representation are sufficient to support accurate classification, part segmentation, and semantic segmentation when used exclusively as feature extractors without additional learned components or post-processing.

C3one line summary

Empowered t-FCW graph representation provides a unified non-parametric and interpretable method for point cloud analysis with high efficiency on ModelNet40 classification.

References

40 extracted · 40 resolved · 0 Pith anchors

[1] A comprehensive overview of deep learning techniques for 3d point cloud classification and semantic segmentation, 2024

[2] Deep learning-based 3d point cloud classification: A systematic survey and outlook, 2023

[3] Advancements in point cloud-based 3d defect classification and segmentation for industrial systems: A comprehensive survey, 2024

[4] Fast graph representation learning with PyTorch Geometric, 2019

[5] Torch-points3d: A modular multi-task framework for reproducible deep learning on 3d point clouds, 2020

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:00.526438Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

669346c31b42f03844a979bff4b9b059e210b4880a8da2d2f70150faf49313c2

Aliases

arxiv: 2605.15475 · arxiv_version: 2605.15475v1 · doi: 10.48550/arxiv.2605.15475 · pith_short_12: M2JUNQY3ILYD · pith_short_16: M2JUNQY3ILYDQRFJ · pith_short_8: M2JUNQY3

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/M2JUNQY3ILYDQRFJPG77JONQLH \
  | 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: 669346c31b42f03844a979bff4b9b059e210b4880a8da2d2f70150faf49313c2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ecc7b0579aa15a6f14f74052a4f3be43d23aa402527050930f292afdc7dc6a65",
    "cross_cats_sorted": [
      "cs.MM"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T23:30:27Z",
    "title_canon_sha256": "411462b62505743f9d4c3dad35d933a5670bc34fc548d37ca200ba2f4026d840"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15475",
    "kind": "arxiv",
    "version": 1
  }
}