pith. sign in

Recoverable Identifier

arXiv:2604.25203 · detector doi_compliance · incontrovertible · 2026-05-19 21:23:33.444201+00:00

advisory doi_compliance recoverable_identifier

DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2106.09685.Hu) was visible in the surrounding text but could not be confirmed against doi.org as printed.

Paper page Integrity report arXiv Try DOI

Evidence text

URL https://aclanthology.org/2025. naacl-long.306/. Han, S., Rao, K., Ettinger, A., Jiang, L., Lin, B. Y ., Lam- bert, N., Choi, Y ., and Dziri, N. Wildguard: Open one- stop moderation tools for safety risks, jailbreaks, and refusals of llms, 2024. URL https://arxiv.org/ abs/2406.18495. Hoover, M., Baherwani, V ., Jain, N., Saifullah, K., Vin- cent, J., Jain, C., Rad, M. K., Bruss, C. B., Panda, A., and Goldstein, T. Dynaguard: A dynamic guardian model with user-defined policies, 2025. URL https: //arxiv.org/abs/2509.02563. Hu, E. J., Shen, Y ., Wallis, P., Allen-Zhu, Z., Li, Y ., Wang, S., Wang, L., and Chen, W. Lora: Low-rank adaptation of large language models. InInternational Conference on Learning Representations, 2022. doi: 10.48550/arXiv. 2106.09685. Hu, J., Dong, Y ., and Huang, X. Trust-oriented adaptive guardrails for large language models, 2025. URLhttps: //arxiv.org/abs/2408.08959. Huang, J., Chen, X., Mishra, S., Zheng, H. S., Yu, A. W., Song, X., and Zhou, D. Large language models can- not self-correct reasoning yet, 2023. URL https: //arxiv.org/abs/2310.01798. Inan, H., Upasani, K., Chi, J., Rungta, R., Iyer, K., Mao, Y ., Tontchev, M., Hu, Q., Fuller, B., Testuggine, D., and Khabsa, M. Llama guard: Llm-based input-output safe- guard for human-ai conversations, 2023. URL https: //arxiv.org/abs/2312.06674. Kang, M. and Li, B. r2-guard: Robust reasoning enabled llm guardrail via knowledge-enhanced logical reason- ing, 2024. URL https://arxiv.org/abs/2407. 05557. 

Evidence payload

{
  "printed_excerpt": "URL https://aclanthology.org/2025. naacl-long.306/. Han, S., Rao, K., Ettinger, A., Jiang, L., Lin, B. Y ., Lam- bert, N., Choi, Y ., and Dziri, N. Wildguard: Open one- stop moderation tools for safety risks, jailbreaks, and refusals of llm",
  "reconstructed_doi": "10.48550/arXiv.2106.09685.Hu",
  "ref_index": 2,
  "resolved_title": null,
  "verdict_class": "incontrovertible"
}