Pith Number

pith:EIQJJ4XW

pith:2026:EIQJJ4XWI4KAFI3M6JBEF5M44Z

not attested not anchored not stored refs resolved

Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation

Guochen Yu, Xiaotao Gu, Xingyu Ma, Yuqing Cheng

BandTok turns music into a 2D time-frequency token grid from a single shared codebook, reducing sequential dependencies for autoregressive generation.

arxiv:2605.15831 v1 · 2026-05-15 · cs.SD · 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{EIQJJ4XWI4KAFI3M6JBEF5M44Z}

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

BandTok yields a physically interpretable time-frequency token grid with a more independent token structure, making it better suited for autoregressive modeling than residual-codebook tokenizers.

C2weakest assumption

The residual hierarchy in existing high-fidelity codecs imposes strong sequential dependencies that amplify error accumulation during autoregressive generation after sequence flattening; the single shared codebook in BandTok avoids this while preserving reconstruction quality.

C3one line summary

BandTok tokenizes Mel-spectrograms as independent time-frequency band tokens from a single codebook and pairs it with 2D RoPE in an autoregressive model to improve music generation over residual multi-codebook tokenizers.

References

33 extracted · 33 resolved · 6 Pith anchors

[1] Soundstream: An end-to-end neural audio codec, 2021

[2] High Fidelity Neural Audio Compression 2022 · arXiv:2210.13438

[3] High-fidelity audio compression with improved rvqgan, 2023

[4] Audiolm: a language modeling approach to audio generation, 2023

[5] MusicLM: Generating Music From Text 2023 · arXiv:2301.11325

Receipt and verification

First computed	2026-05-20T00:01:20.748003Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

222094f2f6471402a36cf24242f59ce6789cb804c2f7c74151660059a3ecc68c

Aliases

arxiv: 2605.15831 · arxiv_version: 2605.15831v1 · doi: 10.48550/arxiv.2605.15831 · pith_short_12: EIQJJ4XWI4KA · pith_short_16: EIQJJ4XWI4KAFI3M · pith_short_8: EIQJJ4XW

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/EIQJJ4XWI4KAFI3M6JBEF5M44Z \
  | 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: 222094f2f6471402a36cf24242f59ce6789cb804c2f7c74151660059a3ecc68c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5a796fd442792dd585c6372960d188aea1fb81a5273d71638182b88600ea5c08",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-15T10:35:49Z",
    "title_canon_sha256": "ec5f07fdea99f6f7f8c5ec81374e48a37f6d08a0f354945307c1c131a428c9f1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15831",
    "kind": "arxiv",
    "version": 1
  }
}