Paper Citation Record · LEDGER

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails

As of 20 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2608.08485.

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

pith.paper-citation-record.v1
2608.08485 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:40:07.570266Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

20 of 20 outbound references displayed

verified exact0
verified fuzzy14
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f218bac9-cb55-47e4-9da7-9f6311cf88e2 · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:07.467583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 336abfec-9c7f-4fa1-87a6-92cd8e2a781c · outbound

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

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:07.473812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca03ca56-994a-429c-923b-6e8d1210d6e1 · outbound

This paper cites Llama Guard 2: Technical Report and Model Specifications.Meta AI Research Technical Report, 2024.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Llama Guard 2: Technical Report and Model Specifications.Meta AI Research Technical Report, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.946377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c7bd07e2-9764-4684-90eb-925dc9cf7f92 · outbound

This paper cites TREET: TRansfer Entropy Estimation via Transformers.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails TREET: TRansfer Entropy Estimation via Transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:07.483683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6409d7-b35c-4e40-8c46-af18add6e315 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

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.

Observation 4a4db863-bfee-4bfb-bd18-ba047d95dc2e · outbound

This paper cites ToxicChat: Unveiling Hidden Toxicity in Real-World User-AI Conversations.Proceedings of EMNLP, pages 4694–4702, 2023.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails ToxicChat: Unveiling Hidden Toxicity in Real-World User-AI Conversations.Proceedings of EMNLP, pages 4694–4702, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.930547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c96db023-1250-44ee-9b59-fbba6b509f23 · outbound

This paper cites BeaverTails: Towards Improved Safety Alignment of LLM via Multi- Dimensional Preference Dataset.Advances in Neural Information Processing Systems (NeurIPS), 36, 2023.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails BeaverTails: Towards Improved Safety Alignment of LLM via Multi- Dimensional Preference Dataset.Advances in Neural Information Processing Systems (NeurIPS), 36, 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.914263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7f485bff-c78d-440a-a0d9-cb51a0f23618 · outbound

This paper cites Safe RLHF: Constrained Reinforcement Learning from Human Feedback.International Conference on Learning Representations (ICLR), 2024.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Safe RLHF: Constrained Reinforcement Learning from Human Feedback.International Conference on Learning Representations (ICLR), 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.896180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1d8a827d-b2d1-42d8-8b2d-5dac6a31f3f2 · outbound

This paper cites XSTest: A Benchmark for Identifying Exaggerated Safety Behaviors in Large Language Models.Proceedings of NAACL, 2024.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails XSTest: A Benchmark for Identifying Exaggerated Safety Behaviors in Large Language Models.Proceedings of NAACL, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.880211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 56677158-c933-46aa-a3dc-2258b64cd329 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:07.515076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d34f7f0-d024-450d-9c25-a68e28584962 · outbound

This paper cites AuthenHallu: A Benchmark for Hallucination Detection in LLM-Generated Content.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails AuthenHallu: A Benchmark for Hallucination Detection in LLM-Generated Content

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.864604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e2e36008-023f-4bef-ab6e-98284edadb31 · outbound

This paper cites HaluBench: Comprehensive Hallucination Evaluation Benchmark.Patronus AI Technical Report, 2024.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails HaluBench: Comprehensive Hallucination Evaluation Benchmark.Patronus AI Technical Report, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.848981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 72bca4d3-609d-42ef-8a1a-9ac673a98ea5 · outbound

This paper cites CHIFRAUD: A Long-term Web Text Dataset for Chinese Fraud Detection.Proceedings of COLING, 2025.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails CHIFRAUD: A Long-term Web Text Dataset for Chinese Fraud Detection.Proceedings of COLING, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.831612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 66ca14fb-803b-4575-95de-20b406ccbfd5 · outbound

This paper cites Orthogonal calibration via posterior projections with applications to the Schwarzschild model.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Orthogonal calibration via posterior projections with applications to the Schwarzschild model

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-08-14T04:40:07.623747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eace89a2-e0be-469d-ae68-fb1f02671b80 · outbound

This paper cites On Estimation of a Probability Density Function and Mode.The Annals of Mathematical Statistics, 33(3):1065–1076, 1962.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails On Estimation of a Probability Density Function and Mode.The Annals of Mathematical Statistics, 33(3):1065–1076, 1962

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.815022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 50c24865-5ab3-4b4f-b6e7-aaa1a02e2db4 · outbound

This paper cites Prototypical Networks for Few-shot Learning.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Prototypical Networks for Few-shot Learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.798285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a131c85c-0e15-4436-9316-5c713e71fc3c · outbound

This paper cites Laplacian Eigenmaps for Dimensionality Reduction and Data Representation.Neural Computation, 15(6):1373–1396, 2003.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Laplacian Eigenmaps for Dimensionality Reduction and Data Representation.Neural Computation, 15(6):1373–1396, 2003

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.782699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7850d6f0-ebd0-481e-bd52-80258ffc8869 · outbound

This paper cites Tenenbaum, Vin De Silva, and John C.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Tenenbaum, Vin De Silva, and John C

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.766460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c3ee3b4e-b1c8-404e-ac69-9d2181edae99 · outbound

This paper cites Perspective API: Automated Moderation for Online Conversations.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails Perspective API: Automated Moderation for Online Conversations

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.750596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8bc88fa7-09ef-4f23-972b-15a143ce9522 · outbound

This paper cites OpenAI Moderation API: Usage, Taxonomy, and Safety Standards.

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails OpenAI Moderation API: Usage, Taxonomy, and Safety Standards

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:40:07.732177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

No inbound Pith citation observations are available.