Pith Number

pith:IMFNAPE7

pith:2025:IMFNAPE74GOHAKYKLLHZRGMA5N

not attested not anchored not stored refs pending

Qwen3Guard Technical Report

An Yang, Baosong Yang, Bowen Yu, Chen Cheng, Chenhan Yuan, Dayiheng Liu, Fei Huang, Haiquan Zhao, Jialong Tang, Jiandong Jiang, Jianwei Zhang, Jijie Xu, Jingren Zhou, Junyang Lin, Ming Yan, Minmin Sun, Pei Zhang, Pengjun Xie, Qiaoyu Tang, Qin Zhu, Rong Zhang, Shibin Wu, Shuo Zhang, Tao He, Tianyi Tang, Tingyu Xia, Wei Liao, Weizhou Shen, Wenbiao Yin, Wenmeng Zhou, Wenyuan Yu, Xiaobin Wang, Xiaodong Deng, Xiaodong Xu, Xiaomeng Hu, Xinyu Zhang, Yang Liu, Yeqiu Li, Yichang Zhang, Yi Zhang, Yong Jiang, Yu Wan, Yuxin Zhou

Qwen3Guard provides multilingual guardrail models that output tri-class safety labels and monitor generation token by token.

arxiv:2510.14276 v1 · 2025-10-16 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IMFNAPE74GOHAKYKLLHZRGMA5N}

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

Evaluated across English, Chinese, and multilingual benchmarks, Qwen3Guard achieves state-of-the-art performance in both prompt and response safety classification.

C2weakest assumption

The chosen benchmarks and tri-class/streaming formulations accurately reflect real-world safety needs and do not create new failure modes or policy inconsistencies when deployed at scale.

C3one line summary

Qwen3Guard releases generative and streaming safety guard models in 0.6B/4B/8B sizes that deliver tri-class judgments and real-time token-level monitoring across 119 languages while claiming state-of-the-art benchmark results.

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

Boundary-targeted Membership Inference Attacks on Safety Classifiers

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions

PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

Receipt and verification

First computed	2026-05-18T04:15:07.171718Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

430ad03c9fe19c702b0a5acf989980eb7ae1008ce6c3607ddf5585fc1220cb43

Aliases

arxiv: 2510.14276 · arxiv_version: 2510.14276v1 · doi: 10.48550/arxiv.2510.14276 · pith_short_12: IMFNAPE74GOH · pith_short_16: IMFNAPE74GOHAKYK · pith_short_8: IMFNAPE7

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/IMFNAPE74GOHAKYKLLHZRGMA5N \
  | 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: 430ad03c9fe19c702b0a5acf989980eb7ae1008ce6c3607ddf5585fc1220cb43

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5d4577516de4a67ba89213f4e39493936f922e5d0a4db65b1a8a6e8d4c5d6d13",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-10-16T04:00:18Z",
    "title_canon_sha256": "ab0ccf8d585da5e613101ccec325d943c4f32875736af300f67fdcedf5789039"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.14276",
    "kind": "arxiv",
    "version": 1
  }
}