Pith Number

pith:2FHILI26

pith:2026:2FHILI267UZDXHDMH4EXHKEU62

not attested not anchored not stored refs resolved

Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization

Cong Tran, Cuong Pham, Hai Nguyen, Tung Vu, Yen Nguyen

Partial speech inpainting at word granularity evades existing deepfake detectors, but a new iterative method recovers the tampered regions.

arxiv:2605.02223 v1 · 2026-05-04 · cs.SD · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2FHILI267UZDXHDMH4EXHKEU62}

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

Zero-shot evaluation reveals that partial inpainting at word granularity remains unsolved by existing deepfake detectors: utterance-level classifiers trained on fully synthesized speech assign near zero fake probability to MIST utterances where only 2-7% of content is manipulated. ISA consistently outperforms non-iterative baselines in this challenging setting.

C2weakest assumption

The generated MIST utterances with LLM-guided semantic replacement and neural voice cloning accurately represent realistic adversarial partial tampering, and the gap-tolerant region proposal plus boundary refinement in ISA can recover all regions without prior knowledge of their number.

C3one line summary

A new dataset, iterative coarse-to-fine localization framework, and segment-level IoU F1 metric tackle the open problem of detecting multiple unknown word-level inpainted regions in speech.

References

12 extracted · 8 resolved · 3 Pith anchors

[1] A V- Deepfake1M: A large-scale LLM-driven audio-visual deepfake dataset.arXiv preprint arXiv:2311.15308

[2] CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens · arXiv:2407.05407

[3] CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training · arXiv:2505.17589

[4] LlamaPartialSpoof: An LLM-driven fake speech dataset simulating disinformation generation.arXiv preprint arXiv:2409.14743

[5] ASVspoof 2019: Spoofing countermeasures for the detection of synthesized, converted and replayed speech 2019

Receipt and verification

First computed	2026-05-20T01:05:15.238799Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d14e85a35efd323b9c6c3f0973a894f697f55e54454072e7307450bb8f112b7c

Aliases

arxiv: 2605.02223 · arxiv_version: 2605.02223v1 · doi: 10.48550/arxiv.2605.02223 · pith_short_12: 2FHILI267UZD · pith_short_16: 2FHILI267UZDXHDM · pith_short_8: 2FHILI26

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/2FHILI267UZDXHDMH4EXHKEU62 \
  | 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: d14e85a35efd323b9c6c3f0973a894f697f55e54454072e7307450bb8f112b7c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b8dcb68be4e3e27756e17e96db747026ee29c853c6ed33dcdbd962242dc96fbe",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-04T04:54:29Z",
    "title_canon_sha256": "f26301377312b6624a01700500d96cc01136b28875ec794f41b5ca3b4f04b704"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.02223",
    "kind": "arxiv",
    "version": 1
  }
}