Paper Citation Record · LEDGER

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

As of 7 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2508.07139.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2508.07139 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:24:23.461464Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact4
verified fuzzy7
unresolved31
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7391a8be-7c97-42c9-bb97-0298bf8a5c69 · outbound

This paper cites Figure is the first-of-its-kind ai robotics company bringing a general purpose humanoid to life.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Figure is the first-of-its-kind ai robotics company bringing a general purpose humanoid to life

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.182075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d1f4862-45a8-48fe-a310-10ff7bc6b967 · outbound

This paper cites LLM4SR: A Survey on Large Language Models for Scientific Research.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection LLM4SR: A Survey on Large Language Models for Scientific Research

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.341478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b90a4a2-f2f7-499b-a985-a59f4be0b0a1 · outbound

This paper cites Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:24:24.102705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5638842d-1e1e-4241-8613-6e8323b004b9 · outbound

This paper cites Transparency & con- tent moderation.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Transparency & con- tent moderation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.173535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e7308aa5-db82-4b9c-8e55-a541a0873104 · outbound

This paper cites Safety in Large Reasoning Models: A Survey.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Safety in Large Reasoning Models: A Survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.351363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ced9b5-dfba-486c-9578-eca36764c4f8 · outbound

This paper cites Generative AI Security: Challenges and Countermeasures.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Generative AI Security: Challenges and Countermeasures

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:24:24.081871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e786645-fec1-4eaa-b3f5-521d89246074 · outbound

This paper cites An Early Categorization of Prompt Injection Attacks on Large Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection An Early Categorization of Prompt Injection Attacks on Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.358065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25f5f323-7136-4f16-b93b-e827df8a1a61 · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.361494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeb3f901-57ff-4af9-acb5-5111c7461fc8 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.364780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9154070-1a34-4e73-923e-6ee24ea89336 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.367757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d61f6a0-21f0-49ac-8c78-8c4f567ec487 · outbound

This paper cites Training language models to follow instructions with human feedback.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Training language models to follow instructions with human feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.370952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f81cd8-a2af-4bc7-9036-38570bad6593 · outbound

This paper cites Automated Progressive Red Teaming.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Automated Progressive Red Teaming

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.374081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5881f87-bd05-4c12-9048-d554c8f0467d · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.377564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4091594c-9b3b-432b-a662-ee436b4b52d9 · outbound

This paper cites Guardreasoner: Towards reasoning-based llm safeguards.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Guardreasoner: Towards reasoning-based llm safeguards

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.380458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27b1f05c-b712-400d-9fbf-e9f05964dca7 · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.383158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14cefd3-7265-4657-a8ff-e57cf764095e · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Detecting Language Model Attacks with Perplexity

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.386156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cadf9baa-dbf5-470b-94e7-9452b8d9df02 · outbound

This paper cites Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.388868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eae6fbe7-eee7-4c94-98b8-9d683797b3b1 · outbound

This paper cites Darkmind: Latent chain-of-thought backdoor in customized llms.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Darkmind: Latent chain-of-thought backdoor in customized llms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.391656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c8ba88-8154-4c93-9a36-c3bc90625b88 · outbound

This paper cites FlipAttack: Jailbreak LLMs via Flipping.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection FlipAttack: Jailbreak LLMs via Flipping

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.394303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0fce363-85d8-440d-a75a-6b4fbf955769 · outbound

This paper cites Cognitive Overload Attack:Prompt Injection for Long Context.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Cognitive Overload Attack:Prompt Injection for Long Context

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.397460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d93443-48d4-44b2-a70e-26cad4fef8f2 · outbound

This paper cites Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.400378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c02eec3d-2f04-4f2e-9a7c-0af33298520a · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Certifying LLM Safety against Adversarial Prompting

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.403420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c18ad7e4-5ccd-4f0c-9ba0-097ab8d99443 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection StruQ: Defending Against Prompt Injection with Structured Queries

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.406310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a85e04b-2048-4be5-8a44-fb8cd3b497a4 · outbound

This paper cites Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.409209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5914d115-67d8-40fc-9bc3-059d850101bb · outbound

This paper cites Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.412222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b083229-859f-45e9-ba9a-04ba2282bedb · outbound

This paper cites [WIP] Jailbreak Paradox: The Achilles' Heel of LLMs.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection [WIP] Jailbreak Paradox: The Achilles' Heel of LLMs

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:24:23.773604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc9fc4d6-c4ad-4bc0-9fea-29acd3183568 · outbound

This paper cites Inverse scaling in test-time compute.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Inverse scaling in test-time compute

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.417921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 292270f7-49e3-409b-9f56-b2d029405619 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.420770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a29a3b9-574a-4820-b283-be94d39e5285 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.423635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0d877c6-550c-49dc-ad53-43e90eb75a82 · outbound

This paper cites Is your prompt safe? inves- tigating prompt injection attacks against open- source llms.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Is your prompt safe? inves- tigating prompt injection attacks against open- source llms

Reference 30

Resolution: verified exact; raw_fallback, observed 2026-08-05T22:24:23.671877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 11d2042c-6acd-4c2f-8ba3-21a2845c9a02 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.428703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 169c30b9-ac90-405b-ad14-488529ed8d30 · outbound

This paper cites Novel uni- versal bypass for all major llms: The pol- icy puppetry prompt injection technique.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Novel uni- versal bypass for all major llms: The pol- icy puppetry prompt injection technique

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.164461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc7c92e6-da17-4e6a-bb46-6f84710aca3a · outbound

This paper cites Gasp: Ef- ficient black-box generation of adversarial suf- fixes for jailbreaking llms.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Gasp: Ef- ficient black-box generation of adversarial suf- fixes for jailbreaking llms

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.437009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175940b2-da68-45f0-a1c1-2ea318351b51 · outbound

This paper cites Jailbreakchat.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Jailbreakchat

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.147077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2d3994d-878a-40a9-9533-c321ca8cf22f · outbound

This paper cites Gemini loki gem (no limits).

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Gemini loki gem (no limits)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.138665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3afbdf64-a2d6-4552-8966-43ceb54b7426 · outbound

This paper cites Jailbreaks.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Jailbreaks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.129526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a0f85fb0-18e7-4f1b-9981-7406b00454ee · outbound

This paper cites SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.447796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f41039d3-9d9d-411b-99f0-e8eda572e6bf · outbound

This paper cites AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.450421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e78c59b7-4194-4955-bbbb-d5b4e002dda8 · outbound

This paper cites AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.453331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33142d37-3f13-4dd2-a5dd-8f29cc5f9291 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.455996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7acea42f-75e7-47b0-adfb-176c818a5870 · outbound

This paper cites Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.458700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cfd376-935a-4299-bfdd-150911536cc0 · outbound

This paper cites Prompt injections bench- mark.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Prompt injections bench- mark

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:24:24.120690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5768ea9b-0038-4677-b9f1-61873ad621bf · outbound

This paper cites an unresolved cited work.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Unresolved cited work

Reference 2025

Resolution: parse uncertain; raw_fallback, observed 2026-08-05T22:24:24.155549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.