Pith Number

pith:QYMWILLL

pith:2026:QYMWILLLFNVSRRI27HUZ4JTQHU

not attested not anchored not stored refs resolved

ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin

Jaeyung Kim, Youngjoon Yoo

ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion.

arxiv:2605.13517 v1 · 2026-05-13 · cs.CV · 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{QYMWILLLFNVSRRI27HUZ4JTQHU}

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 proposed SAMP consists of Ball-Bounded Norm Regularization... and ArcCosine Additive Margin Loss... This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization.

C2weakest assumption

That the combination of time-dependent ball constraint and arc-cosine margin will reliably increase angular separability and utilization without harming training stability or reconstruction quality on the target datasets.

C3one line summary

ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.

References

15 extracted · 15 resolved · 2 Pith anchors

[1] Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation · arXiv:1308.3432

[2] Hyper- spherical variational auto-encoders

[3] Fast decoding in se- quence models using discrete latent variables 2026

[4] Crafting papers on machine learning 2000

[5] Unitok: A unified tokenizer for visual generation and understanding

Receipt and verification

First computed	2026-05-18T02:44:24.427031Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c

Aliases

arxiv: 2605.13517 · arxiv_version: 2605.13517v1 · doi: 10.48550/arxiv.2605.13517 · pith_short_12: QYMWILLLFNVS · pith_short_16: QYMWILLLFNVSRRI2 · pith_short_8: QYMWILLL

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/QYMWILLLFNVSRRI27HUZ4JTQHU \
  | 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: 8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "910fd1d6fe463497dab3b91f103ddd2f9230533bb55babdd1400f62a323d9caa",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T13:35:16Z",
    "title_canon_sha256": "441d62555c829aede8009bc3e8dee6882634f159ddd147f17f276ac0fe80ea9e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13517",
    "kind": "arxiv",
    "version": 1
  }
}