Pith Number

pith:DSFUPISW

pith:2026:DSFUPISWMNBSL46J4WUYD2YRZS

not attested not anchored not stored refs resolved

FSD50K-Solo: Automated Curation of Single-Source Sound Events

Bryce Irvin, Li-Chia Yang, Marko Stamenovic, Ningyuan Yang, Shuo Zhang, Sile Yin, Xiao Quan

A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo.

arxiv:2605.13931 v1 · 2026-05-13 · eess.AS

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DSFUPISWMNBSL46J4WUYD2YRZS}

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 show that our framework achieves strong performance on a human expert-curated test set.

C2weakest assumption

The pre-trained audio encoder and discriminative classifier can reliably distinguish single-source from multi-source samples when trained on diffusion-generated mixtures.

C3one line summary

The authors present a scalable curation method that combines diffusion-based mixture synthesis with a discriminative classifier to automatically extract single-source sound events from FSD50K and release the cleaned FSD50K-Solo subset.

References

27 extracted · 27 resolved · 3 Pith anchors

[1] Pseldnets: Pre-trained neural networks on a large-scale synthetic dataset for sound event localization and detection, 2025

[2] Hissnet: Sound event detection and speaker identification via hierarchical prototypical networks for low-resource headphones, 2023

[3] Conette: An efficient audio captioning system leveraging multiple datasets with task embedding, 2024

[4] Wavcaps: A chatgpt-assisted weakly-labelled au- dio captioning dataset for audio-language multimodal research, 2024

[5] Real-time target sound extraction, 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.978417Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f

Aliases

arxiv: 2605.13931 · arxiv_version: 2605.13931v1 · doi: 10.48550/arxiv.2605.13931 · pith_short_12: DSFUPISWMNBS · pith_short_16: DSFUPISWMNBSL46J · pith_short_8: DSFUPISW

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/DSFUPISWMNBSL46J4WUYD2YRZS \
  | 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: 1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6fd4fd1153ce42a214604c87155603399c2bcd1f5461f6e9aff336891341ffb9",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-05-13T16:04:12Z",
    "title_canon_sha256": "7f0629ab88b1e4ef9a7109420dbebfcf0a21949cbf7e679c1095d9ff8fe8f41a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13931",
    "kind": "arxiv",
    "version": 1
  }
}