Pith Number

pith:UN5FDI2D

pith:2026:UN5FDI2DAO7OZBQRRJMQAV7BIH

not attested not anchored not stored refs resolved

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues

Liang Yi, Li Lu, Peng Cheng, Qingcao Li, Qinglong Wang, Zhongjie Ba

A dual-head model that separates paralinguistic from textual toxicity sources raises Macro-F1 by 21 percent in speech detection.

arxiv:2605.15984 v1 · 2026-05-15 · cs.SD · cs.AI · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UN5FDI2DAO7OZBQRRJMQAV7BIH}

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

Leveraging paralinguistic features significantly improves detection performance. Our method consistently outperforms existing baselines across multiple evaluation metrics, with a 21.1% relative improvement in Macro-F1 score and a 13.0% relative gain in accuracy over the strongest baseline.

C2weakest assumption

The human annotations that distinguish textual content toxicity from paralinguistic origins are accurate, consistent, and capture the intended distinction without substantial label noise or annotator bias.

C3one line summary

ToxiAlert-Bench dataset and dual-head neural network detect toxic speech by distinguishing textual versus paralinguistic sources, reporting 21.1% Macro-F1 and 13% accuracy gains over baselines.

References

39 extracted · 39 resolved · 7 Pith anchors

[1] Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices , author=. 2023 , eprint= 2023

[2] Toxic Speech and Speech Emotions: Investigations of Audio-based Modeling and Intercorrelations , year=

[3] URL: https://web

[4] Audio-based Toxic Language Classification using Self-attentive Convolutional Neural Network , year=

[5] Emotion Based Hate Speech Detection using Multimodal Learning , author=. 2022 , eprint= 2022

Receipt and verification

First computed	2026-05-20T00:01:47.730425Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a37a51a34303beec86118a590057e141ea41710a2b239434c1607b3535c65d86

Aliases

arxiv: 2605.15984 · arxiv_version: 2605.15984v1 · doi: 10.48550/arxiv.2605.15984 · pith_short_12: UN5FDI2DAO7O · pith_short_16: UN5FDI2DAO7OZBQR · pith_short_8: UN5FDI2D

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/UN5FDI2DAO7OZBQRRJMQAV7BIH \
  | 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: a37a51a34303beec86118a590057e141ea41710a2b239434c1607b3535c65d86

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f688d55f20f9b84bcbe5499b4bc6f1f94995db945adb06193e936c2415b17266",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-15T14:17:19Z",
    "title_canon_sha256": "2fcbffd859c0b3dc74618da49d89e6b1f258fc52cfd7b40363a59d4fc4e8e800"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15984",
    "kind": "arxiv",
    "version": 1
  }
}