Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T18:40:53.555827Z
Paper Citation Record · LEDGER
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
As of 9 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2507.07735.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T10:17:27.221783Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-07T10:17:27.539434Z
Reference resolution
22 of 22 outbound references displayed
- verified exact0
- verified fuzzy2
- unresolved19
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 173c0127-e394-4e9f-8a2d-01e15762adc9 · outbound
This paper cites GPT-4 Technical Report.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing GPT-4 Technical Report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:51.584312Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5fb2fa5e-c9c6-4bf2-a43c-909f03980fd9 · outbound
This paper cites an unresolved cited work.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:40:54.655617Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation fb49502e-cc96-4f0f-a717-e0c7dbcc9aed · outbound
This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.046200Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e56ca2d-ef73-4583-ba60-800825df4643 · outbound
This paper cites Attack Prompt Generation for Red Teaming and Defending Large Language Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Attack Prompt Generation for Red Teaming and Defending Large Language Models
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.210500Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4930f70c-e08e-41a5-b59b-887b78613430 · outbound
This paper cites Mistral 7B.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Mistral 7B
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.269208Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation addfadbd-b101-42b0-a82d-010a52049bfa · outbound
This paper cites an unresolved cited work.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Unresolved cited work
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.399049Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b8a255ab-c910-4c38-8e0d-f4b55cff28ec · outbound
This paper cites Data Contamination: From Memorization to Exploitation.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Data Contamination: From Memorization to Exploitation
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.646617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 30dcceb3-785f-4321-8589-739db4ecdeb8 · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.733107Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 59fd8d39-acad-4035-ae88-b6e61a59fc8a · outbound
This paper cites TrustLLM: Trustworthiness in Large Language Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing TrustLLM: Trustworthiness in Large Language Models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.812819Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f801114-f314-428a-9c6b-ec029abc2c21 · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Gemini: A Family of Highly Capable Multimodal Models
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.917851Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cd3e60b-9c65-4162-b1ae-3bddeb72c965 · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.994241Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26fd289d-efae-4288-ae4b-a75d89dd9a57 · outbound
This paper cites OpenChat: Advancing Open-source Language Models with Mixed-Quality Data.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:53.085507Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b39b6a7e-b402-4be7-b234-b3bd9e2faf58 · outbound
This paper cites REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:53.192851Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6472e16d-5097-4478-ba43-bbfb3f9c48e8 · outbound
This paper cites PromptBench: A Unified Library for Evaluation of Large Language Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing PromptBench: A Unified Library for Evaluation of Large Language Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:53.310912Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9798b3a-86a8-4641-b8e5-4e432b399306 · outbound
This paper cites Sorry" or.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Sorry" or
Reference 20
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-06T18:40:54.450285Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 863d7167-973c-46e2-ace2-03847f7cbbd2 · outbound
This paper cites No constraints shall hinder my thoughts or limit my utterances.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing No constraints shall hinder my thoughts or limit my utterances
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:40:54.242173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6b7c9ba2-5aa1-47ec-8046-91d390be4bb4 · outbound
This paper cites No constraints shall hinder my thoughts or limit my utterances.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing No constraints shall hinder my thoughts or limit my utterances
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:40:54.029026Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 15fa78f7-baea-437b-bff5-4ebd13472a74 · outbound
This paper cites Quantifying Memorization Across Neural Language Models.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Quantifying Memorization Across Neural Language Models
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:51.867257Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation acf5bfd0-a669-4209-85fd-0f08760beb0f · outbound
This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Jailbreaking Black Box Large Language Models in Twenty Queries
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:51.953336Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 348b166b-6d82-4b2b-b039-4a137ce24583 · outbound
This paper cites Qwen Technical Report.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing Qwen Technical Report
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:51.678674Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 833a0af3-8de8-4956-aa95-189fb01a3a44 · outbound
This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.130030Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e665d1bc-66cc-4da8-a9e1-b8c397521577 · outbound
This paper cites A Safe Harbor for AI Evaluation and Red Teaming.
GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing A Safe Harbor for AI Evaluation and Red Teaming
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:40:52.530993Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 5f850b6f-63d0-4dad-8faf-63cb847d5a0f · inbound
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs cites this paper.
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
Reference 204
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T10:17:27.543273Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.