Pith Number

pith:D2WMPN36

pith:2026:D2WMPN36J55TYCQTRWTNLACTNL

not attested not anchored not stored refs pending

HAFM: Hierarchical Autoregressive Foundation Model for Music Accompaniment Generation

Cheng Luo, Jianwei Cui, Jian Zhu, Jun Sun, Shihao Chen, Yubang Zhang, Yunlong Xue

A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization.

arxiv:2604.09054 v3 · 2026-04-10 · cs.SD · 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{D2WMPN36J55TYCQTRWTNLACTNL}

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

Experiments on MUSDB18 demonstrate that HAFM achieves a Fréchet Audio Distance (FAD) of 2.08 on isolated vocal inputs, outperforming retrieval baselines and matching prior state-of-the-art systems with fewer parameters.

C2weakest assumption

The dual-rate codec tokenization scheme using HuBERT at 50 Hz for vocals and EnCodec at 75 Hz for instrumentals, combined with the three-stage hierarchical autoregressive architecture, produces time-aligned and coherent accompaniments without needing additional explicit alignment or synchronization steps.

C3one line summary

HAFM uses a hierarchical autoregressive model with dual-rate HuBERT and EnCodec tokens to generate coherent instrumental music from vocals, achieving FAD 2.08 on MUSDB18 while matching prior systems with fewer parameters.

Cited by

1 paper in Pith

HAFM: Hierarchical Autoregressive Foundation Model for Music Accompaniment Generation

Receipt and verification

First computed	2026-06-23T01:13:05.066943Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce

Aliases

arxiv: 2604.09054 · arxiv_version: 2604.09054v3 · doi: 10.48550/arxiv.2604.09054 · pith_short_12: D2WMPN36J55T · pith_short_16: D2WMPN36J55TYCQT · pith_short_8: D2WMPN36

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/D2WMPN36J55TYCQTRWTNLACTNL \
  | 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: 1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "504e6d6be6200a27b168d7e58240be2e74f7d4e79e0bf51b5133400e7c9c40fe",
    "cross_cats_sorted": [
      "cs.MM"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-04-10T07:27:55Z",
    "title_canon_sha256": "d8e0e9ad02905b9131b216d81008c5232ddcab7166f0a470850d29f86a7e4ce9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.09054",
    "kind": "arxiv",
    "version": 3
  }
}