pith. sign in
Pith Number

pith:CBX6EKEY

pith:2026:CBX6EKEYOYF5ZD3PH5S7OTKPLC
not attested not anchored not stored refs resolved

EnvTriCascade: An Environment-Aware Tri-Stage Cascaded Framework for ESDD2 2026 Challenge

Haonan Cheng, Hengyan Huang, Jian Liu, Jiayi Zhou, Long Ye, Qin Zhang, Xiaoxuan Guo, Yuankun Xie

A tri-stage cascaded detector first checks mix consistency then fuses two five-class classifiers via attention to reach 0.8266 Macro-F1 on the ESDD2 test set.

arxiv:2605.18409 v1 · 2026-05-18 · cs.SD

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CBX6EKEYOYF5ZD3PH5S7OTKPLC}

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

Trained exclusively on the official CompSpoofV2 dataset, our system achieves a Macro-F1 score of 0.8266 on the test set, significantly outperforming the official baseline and ranking second in the challenge.

C2weakest assumption

The mix-consistency detector and the two complementary five-class detectors (SSLAM+XLS-R and EAT-large+XLS-R) provide independent and complementary information that, when fused via cross-branch attention, yields robust generalization to the unseen test mixing conditions.

C3one line summary

EnvTriCascade is a tri-stage cascaded framework using mix-consistency detection followed by dual SSL-based five-class classifiers with cross-branch attention and RawBoost augmentation, achieving 0.8266 Macro-F1 on the ESDD2 2026 challenge test set.

References

30 extracted · 30 resolved · 5 Pith anchors

[1] MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control 2026 · arXiv:2604.21164
[2] Text-To-Speech with Chain-of-Details: modeling temporal dynamics in speech generation 2026 · arXiv:2604.19330
[3] X-VC: Zero-shot Streaming Voice Conversion in Codec Space 2026 · arXiv:2604.12456
[4] Emotion-aware prefix: Towards explicit emotion control in voice conversion models, 2026
[5] Speechfake: A large-scale multilingual speech deepfake dataset incorporating cutting-edge generation methods, 2025

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-20T00:05:59.344384Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

106fe22898760bdc8f6f3f65f74d4f58a92626000d2396b840262d759e98f05c

Aliases

arxiv: 2605.18409 · arxiv_version: 2605.18409v1 · doi: 10.48550/arxiv.2605.18409 · pith_short_12: CBX6EKEYOYF5 · pith_short_16: CBX6EKEYOYF5ZD3P · pith_short_8: CBX6EKEY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CBX6EKEYOYF5ZD3PH5S7OTKPLC \
  | 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: 106fe22898760bdc8f6f3f65f74d4f58a92626000d2396b840262d759e98f05c
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "a09748cfbb26a1e33a50d3e67fda17f7e9c68e6d9ef77d08343ef8d86ae8c4a4",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-18T13:48:52Z",
    "title_canon_sha256": "547fd1155152450b3fe83913e91d13c2e898a754874b802f7a56aa931715bfde"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.18409",
    "kind": "arxiv",
    "version": 1
  }
}