Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 53 inbound Pith citation observations for arXiv:2404.05993.
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 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-16T11:24:11.637137Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
3
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation a6f947b2-4071-4765-94e4-06c4f286006f · inbound
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs cites this paper.
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T16:25:14.838539Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a4830859-e41c-4dc6-bde5-aa83c5dc7c11 · inbound
ShieldGemma: Generative AI Content Moderation Based on Gemma cites this paper.
ShieldGemma: Generative AI Content Moderation Based on Gemma AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T13:17:39.492624Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f7e03006-52c6-478e-905c-a08392c8e9a7 · inbound
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations cites this paper.
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T19:41:19.647374Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81b63bbe-3def-4bcb-8c5d-e368e5ec89cf · inbound
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models cites this paper.
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T18:38:43.310566Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1bf5f906-5679-4e01-a3fa-bcb81c063930 · inbound
Granite Guardian cites this paper.
Granite Guardian AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T18:37:09.396207Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff891a96-45b4-400e-b5aa-786d1205030d · inbound
Lightweight Safety Classification Using Pruned Language Models cites this paper.
Lightweight Safety Classification Using Pruned Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T13:11:27.241267Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c38e0513-05f2-4a38-8b44-ff848401c888 · inbound
Cosmos World Foundation Model Platform for Physical AI cites this paper.
Cosmos World Foundation Model Platform for Physical AI AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 56
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T23:38:45.444469Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9640defd-d58e-48b3-a75b-e21cd1545ae2 · inbound
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails cites this paper.
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T20:15:54.707197Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7d7733f-33bc-43aa-8b2e-322d6ba92696 · inbound
Peering Behind the Shield: Guardrail Identification in Large Language Models cites this paper.
Peering Behind the Shield: Guardrail Identification in Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T03:45:21.395850Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation d434f31f-5769-4c1f-9726-52e078753405 · inbound
Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation cites this paper.
Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T11:24:11.637137Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb0c9166-3cda-4a8f-a17b-91d9470880b7 · inbound
Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks cites this paper.
Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 176
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T10:12:00.883032Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 76a37a7c-027f-4957-9b31-ce521c91672a · inbound
Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing cites this paper.
Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T06:00:23.878320Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 700d9382-4c44-45a7-b731-f2836b8734c7 · inbound
Understanding and Mitigating Risks of Generative AI in Financial Services cites this paper.
Understanding and Mitigating Risks of Generative AI in Financial Services AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T10:19:10.418119Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0936b09-a7b3-43ff-8f68-e03761ecaa46 · inbound
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning cites this paper.
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:05:17.363940Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 553144f0-55aa-4cc2-913a-7c5a9c7d1345 · inbound
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs cites this paper.
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:43:22.394650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ee2c05a-9166-4ce2-9426-738d099af967 · inbound
Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon cites this paper.
Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:20:15.911283Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21dc1195-0146-4bcf-875d-07cbab1af98f · inbound
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment cites this paper.
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T11:53:03.538854Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 95622f99-7e3d-4c7f-80f9-95034ad77d4b · inbound
A Red Teaming Roadmap Towards System-Level Safety cites this paper.
A Red Teaming Roadmap Towards System-Level Safety AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:11:19.166188Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9a02c637-236b-48bc-9429-84998efa3c15 · inbound
JavelinGuard: Low-Cost Transformer Architectures for LLM Security cites this paper.
JavelinGuard: Low-Cost Transformer Architectures for LLM Security AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:41:25.380511Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce2e4144-2beb-4ad1-a941-531422c683b6 · 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 AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 71
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T10:17:26.807876Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d563ce13-f171-458d-8fca-4797387eb0e7 · inbound
PL-Guard: Benchmarking Language Model Safety for Polish cites this paper.
PL-Guard: Benchmarking Language Model Safety for Polish AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:49:52.956697Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 86920b5e-5c8a-4613-b743-109ccee0e90b · inbound
GAF-Guard: An Agentic Framework for Risk Management and Governance in Large Language Models cites this paper.
GAF-Guard: An Agentic Framework for Risk Management and Governance in Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T21:16:26.615591Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81ad3d4c-d0db-443f-94ca-c1a3350de80a · inbound
Agentic Web: Weaving the Next Web with AI Agents cites this paper.
Agentic Web: Weaving the Next Web with AI Agents AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 72
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T13:05:34.201626Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b54d9ee7-1675-406f-9fd5-ca2eec46de03 · inbound
Libra: Large Chinese-based Safeguard for AI Content cites this paper.
Libra: Large Chinese-based Safeguard for AI Content AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:17:38.660420Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85c84855-85be-479e-8369-f623731c2b37 · inbound
YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models cites this paper.
YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T19:55:56.480656Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2d13794-9a2b-4399-9469-ee2f79f5efd0 · inbound
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses cites this paper.
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T09:25:40.793268Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 002e1da3-e29d-4e38-b67c-429527881c69 · inbound
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming cites this paper.
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T11:43:31.089245Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5819d180-8c54-4462-b410-c1dc3ff3402e · inbound
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs cites this paper.
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T06:46:39.716726Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a88c7e97-5595-458c-9bd9-36baa95ad573 · inbound
Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines cites this paper.
Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T06:20:58.822366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5d61a91f-2d50-47b3-a9f9-22c53dd92841 · inbound
LLM Safety From Within: Detecting Harmful Content with Internal Representations cites this paper.
LLM Safety From Within: Detecting Harmful Content with Internal Representations AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T12:20:23.127272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3fca799b-5bf6-498a-af1d-062c65e400b3 · inbound
Cross-Lingual Jailbreak Detection via Semantic Codebooks cites this paper.
Cross-Lingual Jailbreak Detection via Semantic Codebooks AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T23:46:20.039365Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0da1d02d-669c-4eaf-b5fb-cd6613cb3ea7 · inbound
From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning cites this paper.
From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-09T06:45:44.124627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation fa870234-32f9-4df3-a03e-649212b29865 · inbound
Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMs cites this paper.
Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMs AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T18:33:38.095886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 8f713945-cf5e-4164-9073-3935e0655052 · inbound
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content cites this paper.
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T09:13:15.967694Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 208241d1-dd44-482d-82a3-02cdc8d0bedc · inbound
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails cites this paper.
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-06-28T23:12:46.502677Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c7ee5234-4cd9-43d3-90ec-657f22eb2075 · inbound
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety cites this paper.
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 31
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-28T19:42:35.873281Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3f84cf0d-8e05-47bc-b092-04ecd60e5129 · inbound
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails cites this paper.
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 13
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T12:26:57.042339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 04344fb7-64f4-4e58-aee5-ded80df070a2 · inbound
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective cites this paper.
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T20:57:23.096909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 13e6fd3d-7253-4416-89b6-1fee6d31ee95 · inbound
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety cites this paper.
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T16:59:58.605211Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c98e7043-5b28-4831-809f-a3f1306651e1 · inbound
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety cites this paper.
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T18:03:48.828247Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 6a33beb2-2e8f-466e-889a-a105d40632a1 · inbound
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety cites this paper.
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T00:52:55.775115Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 18c20757-5dd1-4e3f-8368-602d7b340dde · inbound
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 80
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T17:35:51.361175Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 636c13d0-a4cb-41e9-a88b-a04100941816 · inbound
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 32
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-30T09:34:34.450551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 342689fb-6e32-49e4-9c78-1949b8e33380 · inbound
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing cites this paper.
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T06:34:18.840560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5eb61755-d7b1-40cf-92ce-9670233dc6cb · inbound
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail cites this paper.
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T10:04:51.444702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 73d0fa2d-a920-49ff-a1d6-3683f8d3d691 · inbound
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models cites this paper.
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T05:21:30.132993Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7171ac90-634b-41f6-ae0b-ab4cbebbfe30 · inbound
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows cites this paper.
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T07:06:18.415677Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a908996-fc3e-49fb-9ad0-651b6a13bb62 · inbound
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space cites this paper.
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T23:52:51.607980Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4ff3818-7ec1-4014-badf-d67bcb19da28 · inbound
A Dual-Hypothesis Reasoning Framework for LLM Guardrails cites this paper.
A Dual-Hypothesis Reasoning Framework for LLM Guardrails AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T17:41:11.392807Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eef59a7f-3937-4d71-a4f2-47736b47e2bf · inbound
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation cites this paper.
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T07:36:56.254253Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 785bc3e8-0cbc-4a7b-9825-9c96f929dccf · inbound
Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed cites this paper.
Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 143
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T09:24:20.717521Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7990e189-4df8-472c-9ac3-9fdd6c542790 · inbound
Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production cites this paper.
Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-14T04:39:30.012200Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a6409d7-b35c-4e40-8c46-af18add6e315 · inbound
HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails cites this paper.
HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-14T04:40:07.488669Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.