Paper Citation Record · LEDGER

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling

As of 22 July 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2605.24552.

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

pith.paper-citation-record.v1
2605.24552 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T13:10:44.728498Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-21T06:31:05.380196+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

37 of 37 outbound references displayed

verified exact20
verified fuzzy12
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 66f9ff6a-f9c5-414c-a2ce-b53ad352c548 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling LLaMA: Open and Efficient Foundation Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.756189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 7cbb8d6e-8f7d-4f55-b68f-8ff17d02f887 · outbound

This paper cites GPT-4 Technical Report.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling GPT-4 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.751161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 9b839605-2ba6-4cdd-afb9-2882689faaea · outbound

This paper cites Qwen Technical Report.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Qwen Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.787899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation f2c32fc5-ea25-4a6b-a2cc-ce1a2bcc4821 · outbound

This paper cites Iron: Private inference on transformers,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Iron: Private inference on transformers,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.789682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e7009b8e-179e-4b2e-a7b0-4f9001eb36a8 · outbound

This paper cites Efficient and privacy-enhanced federated learning for industrial artificial intelligence,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Efficient and privacy-enhanced federated learning for industrial artificial intelligence,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.791615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 1ed14c9d-57af-4055-abd8-2c57a6db02a8 · outbound

This paper cites Scalable zero-knowledge proofs for non- linear functions in machine learning,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Scalable zero-knowledge proofs for non- linear functions in machine learning,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.810468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 6d7bd4e5-f224-4f25-9f7d-392cdf37fedf · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.753641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 0da2d368-c72f-430b-a695-23e48690a1f1 · outbound

This paper cites Improving alignment and robustness with circuit breakers,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Improving alignment and robustness with circuit breakers,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.793385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 6738ebac-6b5c-473d-87e3-9a19f3832e4d · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T13:14:40.774910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 4a2d8890-698d-46fa-8e2b-87f6a233a4f9 · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 10

Resolution: malformed identifier; doi_truncated, observed 2026-06-30T13:14:40.139833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 3f33ee8f-6323-4855-b9ce-f31cbcaaa09e · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Refusal in Language Models Is Mediated by a Single Direction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.777200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 96c08b32-767b-41ff-af22-78225efc3502 · outbound

This paper cites Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T13:14:40.137665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 787c580f-fa62-4ea7-8498-103ca5608e79 · outbound

This paper cites Programming refusal with conditional activation steering,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Programming refusal with conditional activation steering,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.802702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e6acd177-c323-4a13-a90f-da37e12766dc · outbound

This paper cites Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.795327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 5c988fe2-ee8a-4724-ac32-bb8ab070abe3 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.779901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 5e76621a-efc1-4cc6-a561-8e29d4346fbd · outbound

This paper cites Harmbench: A standardized evaluation framework for automated red teaming and robust refusal,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Harmbench: A standardized evaluation framework for automated red teaming and robust refusal,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.804758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation c2478fe6-46c1-482e-a782-bb14b8478eb3 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.772111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e956a31d-3298-4ea6-a5dc-fcbcff75ef51 · outbound

This paper cites Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.146333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 12679439-e34b-427d-8426-6114c5c3f11a · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.767029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation c63dfc51-94c3-4b1c-b58a-251dc347d6bf · outbound

This paper cites Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.790523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 189a7923-0a41-4483-96b4-d2d9afc73e86 · outbound

This paper cites Intention Analysis Makes LLMs A Good Jailbreak Defender.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Intention Analysis Makes LLMs A Good Jailbreak Defender

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.769734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e350e98a-7ff1-4695-bae7-8e31ec4cfa57 · outbound

This paper cites Gradient cuff: De- tecting jailbreak attacks on large language models by exploring refusal loss landscapes,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Gradient cuff: De- tecting jailbreak attacks on large language models by exploring refusal loss landscapes,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.806746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 72079b08-d575-4918-8322-b0684af56dca · outbound

This paper cites Gradsafe: detect- ing unsafe prompts for llms via safety-critical gradient analysis,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Gradsafe: detect- ing unsafe prompts for llms via safety-critical gradient analysis,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.808662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation fb30514a-9658-4349-b973-ed6aac1a3696 · outbound

This paper cites HSF: defending against jailbreak attacks with hidden state filtering,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling HSF: defending against jailbreak attacks with hidden state filtering,

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.151343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 3e5f59c0-d23d-40ff-9cfd-ffe795a5403c · outbound

This paper cites Baek, Ziming Liu, Riya Tyagi, and Max Tegmark.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Baek, Ziming Liu, Riya Tyagi, and Max Tegmark

Reference 25

Resolution: metadata mismatch; doi, observed 2026-06-30T13:14:40.148577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 1e219939-6b53-4830-9fc1-71018045e041 · outbound

This paper cites Mistral 7B.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Mistral 7B

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.792670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 522ad08a-4cc6-442c-b16b-1c38ecfecd42 · outbound

This paper cites Qwen2.5 Technical Report.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Qwen2.5 Technical Report

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.761444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e1c22f8a-a0b5-4814-b676-2385c7bcaed1 · outbound

This paper cites The llama 3 herd of models,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling The llama 3 herd of models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.798753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 5aa09186-f3eb-4524-a800-e5bdb1d3e6b1 · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 29

Resolution: verified exact; doi, observed 2026-06-30T13:14:40.153395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation f6e404d2-9cc3-49c1-973c-c28f3f0bb8dd · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Measuring Massive Multitask Language Understanding

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.794813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation d885efbe-c1bc-4caf-b63a-ad50a0c9d7f6 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena,.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Judging llm-as-a-judge with mt-bench and chatbot arena,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.800620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation f70e6c42-70d1-4495-bf42-2f56ba16b76d · outbound

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

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.759014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 48f37ce3-dba9-498c-8446-234245b03938 · outbound

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

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.763893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 792f2e33-c6c4-4264-bddb-fbb3f4442747 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T13:14:40.143359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 2ba87403-be47-45ff-9a48-ef667f99bdc1 · outbound

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

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:14:40.782609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 45616518-6eed-41c7-a109-0f4380a57d96 · outbound

This paper cites an unresolved cited work.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Unresolved cited work

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:15:57.797016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 6276978e-d001-481d-be42-dc3be8e20b39 · outbound

This paper cites Alphasteer: Learn- ing refusal steering with principled null-space constraint.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling Alphasteer: Learn- ing refusal steering with principled null-space constraint

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.785170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Pith citing papers

No inbound Pith citation observations are available.