pith. sign in
Pith Number

pith:JVXDPZVV

pith:2025:JVXDPZVV23DWI762PNNZNWCRPI
not attested not anchored not stored refs resolved

The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval

David Diaz-Guerra, Jaime Garcia-Martinez, John Anderson, Julio J. Carabias-Orti, Pablo Caba\~nas-Molero, Pedro Vera-Candeas, Ricardo Falcon-Perez, Tuomas Virtanen

The Spheres dataset supplies multitrack orchestral recordings with isolated stems and room impulse responses for classical music source separation.

arxiv:2511.21247 v2 · 2025-11-26 · eess.AS · cs.LG · cs.SD

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{JVXDPZVV23DWI762PNNZNWCRPI}

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 dataset provides isolated stems for supervised training of source separation models and room impulse responses for acoustic characterization, with baseline results using X-UMX models highlighting both potential and challenges of orchestral source separation.

C2weakest assumption

The specific choice of two canonical works, the Colibrì Ensemble, and the 23-microphone setup in one studio produces recordings that generalize to other orchestras, halls, and recording conditions for training robust models.

C3one line summary

The Spheres dataset provides multitrack orchestral recordings with isolated instrument stems and acoustic characterizations to support supervised machine learning for music source separation in the classical domain.

References

43 extracted · 43 resolved · 0 Pith anchors

[1] MUSDB18-HQ - an uncompressed version of musdb18, 2019 · doi:10.5281/zenodo.3338373
[2] Music demixing challenge 2021, 2021
[3] The sound demixing challenge 2023 – music demixing track, 2023
[4] Musical source separation: An introduction, 2019
[5] MTG MASS database. [Online] 2008

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T23:39:17.027753Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

4d6e37e6b5d6c7647fda7b5b96d8517a3e35eff590c402e05cae168c46db4888

Aliases

arxiv: 2511.21247 · arxiv_version: 2511.21247v2 · doi: 10.48550/arxiv.2511.21247 · pith_short_12: JVXDPZVV23DW · pith_short_16: JVXDPZVV23DWI762 · pith_short_8: JVXDPZVV
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/JVXDPZVV23DWI762PNNZNWCRPI \
  | 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: 4d6e37e6b5d6c7647fda7b5b96d8517a3e35eff590c402e05cae168c46db4888
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "2b09bcb2bcf816c9252bc26286f240939e1b647f0a78998ca4c78c678b2a0302",
    "cross_cats_sorted": [
      "cs.LG",
      "cs.SD"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2025-11-26T10:23:15Z",
    "title_canon_sha256": "68b02f670e064d27a233f22546793382400ffbd18aef35ef3a817ef5ac89ffdf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.21247",
    "kind": "arxiv",
    "version": 2
  }
}