Paper Citation Record · LEDGER

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

As of 13 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2605.26409.

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

pith.paper-citation-record.v1
2605.26409 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T17:43:47.849960Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

48 of 48 outbound references displayed

verified exact21
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ffcdaba-a0a7-4214-bd80-a1a0ef177f9c · outbound

This paper cites Consistent estimation of generative model representations in the data kernel perspective space.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Consistent estimation of generative model representations in the data kernel perspective space

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T17:53:47.727955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 27ea9924-5daa-4116-b675-c6604d761999 · outbound

This paper cites Intrinsic dimensionality explains the effectiveness of language model fine-tuning.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Intrinsic dimensionality explains the effectiveness of language model fine-tuning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28be538f-c115-42da-b83e-aea023549109 · outbound

This paper cites The Claude 3 model family: Opus, Sonnet, Haiku.Anthropic Technical Report, 2024.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models The Claude 3 model family: Opus, Sonnet, Haiku.Anthropic Technical Report, 2024

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad4c49f3-83f8-4f21-8a70-bc83a643d115 · outbound

This paper cites Threat intelligence report: August 2025.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Threat intelligence report: August 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75c313b-091e-41f4-ac8f-0e6610f4ab70 · outbound

This paper cites Detecting Perspective Shifts in Multi-agent Systems.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Detecting Perspective Shifts in Multi-agent Systems

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T17:53:47.730462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9670a7ff-3b64-40e3-9bc2-59c4932aa31b · outbound

This paper cites Defending against alignment-breaking attacks via robustly aligned LLM.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Defending against alignment-breaking attacks via robustly aligned LLM

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea7e22b8-ebd1-456a-94e7-cbb80d486ec3 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.733021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ea93c1f4-2f95-4cd8-bf16-e9c51938bb39 · outbound

This paper cites JailbreakBench: An open robustness benchmark for jailbreaking large language models.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models JailbreakBench: An open robustness benchmark for jailbreaking large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75bb7aa-f125-41e9-9a1f-c2cf8b4d5f1d · outbound

This paper cites The Llama 3 Herd of Models.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models The Llama 3 Herd of Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.719896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5e16d746-d3c5-4275-9810-4cc619c92cc0 · outbound

This paper cites Comparing Foundation Models using Data Kernels.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Comparing Foundation Models using Data Kernels

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T17:53:47.717515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ccafdda1-119c-418a-92f7-aed052898ef7 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.712029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1326ebda-29dc-45c1-87f0-83ebc5467c31 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Gemma 2: Improving Open Language Models at a Practical Size

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.714752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e6d7840a-6c3a-470e-bb97-64e24ca66567 · outbound

This paper cites Text embeddings API.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Text embeddings API

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e354918-7ef9-4929-a68e-abb6dc2eb98a · outbound

This paper cites Statistical inference on black-box generative models in the data kernel perspective space.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Statistical inference on black-box generative models in the data kernel perspective space

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e58ace2a-1043-4c92-b65c-c9d1370bd8fe · outbound

This paper cites Query-efficient model evaluation using cached responses.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Query-efficient model evaluation using cached responses

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.722345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e9a7939c-67aa-41ee-8e88-f141f6edbe38 · outbound

This paper cites Tracking the perspectives of interacting language models.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Tracking the perspectives of interacting language models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.725100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 22e9386b-000a-4dc3-929e-7761e40ff97c · outbound

This paper cites Best-of-N Jailbreaking.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Best-of-N Jailbreaking

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.735743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eaea15f2-b109-4522-afd8-5fb7cb52460e · outbound

This paper cites The Platonic Representation Hypothesis.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models The Platonic Representation Hypothesis

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.676815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8e58ce07-45c0-4ce9-a507-8f4bc8020ab6 · outbound

This paper cites GPT-4o System Card.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models GPT-4o System Card

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.707201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a2971b19-968a-4803-98d1-a12910032e9b · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.671947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c2b2a110-758f-4fd3-8878-733bfb742f25 · outbound

This paper cites Wiley, 1990.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Wiley, 1990

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211596d7-49e6-495a-b8e2-a082b966ce39 · outbound

This paper cites Similarity of neural network representations revisited.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Similarity of neural network representations revisited

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8700dbc-e229-40d5-a54f-3675741e0069 · outbound

This paper cites Holistic Evaluation of Language Models.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Holistic Evaluation of Language Models

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T17:53:47.673611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2c8b9c67-fa27-44c9-a4a6-6b8b708f1a28 · outbound

This paper cites The detection of disease clustering and a generalized regression approach.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models The detection of disease clustering and a generalized regression approach

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb1afa9-4ffa-4c4a-b624-8181bdf162ab · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.679296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1ec4a496-26fb-4f6c-8f40-4f4edf2fd2c0 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.704818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 06fc51e2-8089-4760-91c0-f4199eea8fd7 · outbound

This paper cites Nomic Embed: Training a Reproducible Long Context Text Embedder.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Nomic Embed: Training a Reproducible Long Context Text Embedder

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.699732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 025e4852-7ad9-475a-9783-70c7319d16f4 · outbound

This paper cites New embedding models and API updates.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models New embedding models and API updates

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9fd866-2e9c-4eea-85d1-fc364e488b15 · outbound

This paper cites GPT-4 Technical Report.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models GPT-4 Technical Report

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.709554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6a7eff41-0214-4883-be25-505085d2153c · outbound

This paper cites Ignore previous prompt: Attack techniques for language models.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Ignore previous prompt: Attack techniques for language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a5e0d8c-2f6b-44be-b38d-36c804db62f5 · outbound

This paper cites LLM self defense: By self examination, LLMs know they are being tricked.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models LLM self defense: By self examination, LLMs know they are being tricked

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa01361-75d2-4f56-a12e-30cdb76ff703 · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models tinyBenchmarks: evaluating LLMs with fewer examples

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T17:53:47.703641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a86b13a9-36f5-4eda-9ca5-e5821dafed7d · outbound

This paper cites SVCCA: Singu- lar vector canonical correlation analysis for deep learning dynamics and interpretability.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models SVCCA: Singu- lar vector canonical correlation analysis for deep learning dynamics and interpretability

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9f9578-9876-4d22-aba4-d6f74d5cd1f5 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.696426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a1980723-2644-476c-9a39-f864704f56ea · outbound

This paper cites Great, now write an article about that: The Crescendo multi-turn LLM jailbreak attack.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Great, now write an article about that: The Crescendo multi-turn LLM jailbreak attack

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a19d41-325d-4348-a32c-b929caee1f59 · outbound

This paper cites MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.689060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation df09e9e9-f305-45f1-91f8-e5987fe832c9 · outbound

This paper cites Continuous Multidimensional Scaling.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Continuous Multidimensional Scaling

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.694100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8debb42c-9a4f-40c7-8424-b9fb3797cc4e · outbound

This paper cites Anchor points: Benchmarking models with much fewer examples.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Anchor points: Benchmarking models with much fewer examples

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7b21712-285f-4302-9305-078551f9c0ff · outbound

This paper cites Jailbroken: How does LLM safety training fail? InAdvances in Neural Information Processing Systems, volume 36, 2024.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Jailbroken: How does LLM safety training fail? InAdvances in Neural Information Processing Systems, volume 36, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c766b4e8-3c80-4acc-acc4-12cc8b8205e3 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.699039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4130fe60-de60-4e94-b365-732c0eb031c6 · outbound

This paper cites C-Pack: Packaged resources to advance general Chinese embedding, 2023.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models C-Pack: Packaged resources to advance general Chinese embedding, 2023

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59dd70bd-65d8-4975-8d99-7b2f0935931d · outbound

This paper cites Defending ChatGPT against jailbreak attack via self-reminders.Nature Machine Intelligence, 5:1486–1496, 2023.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Defending ChatGPT against jailbreak attack via self-reminders.Nature Machine Intelligence, 5:1486–1496, 2023

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f71a068b-f6e5-4020-9789-91be10400736 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.702101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7d4cad6a-e56d-413b-b317-5a8a43f7c4f9 · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.691753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 43dba919-3e6e-41fb-869b-99376f07e4e2 · outbound

This paper cites Intention analysis makes LLMs a good jailbreak defender.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Intention analysis makes LLMs a good jailbreak defender

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f52704-ff77-4012-acd7-e721434d8c61 · outbound

This paper cites Judging LLM-as-a-judge with MT-bench and chatbot arena.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Judging LLM-as-a-judge with MT-bench and chatbot arena

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05bfefe7-ad51-43a9-bd0d-989098d2d46f · outbound

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

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:47.694100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f5d487d5-9201-4adc-a7bd-b2162d66541f · outbound

This paper cites {attack}.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models {attack}

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-29T17:43:47.849960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.