Paper Citation Record · LEDGER

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms

As of 16 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2504.13052.

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

pith.paper-citation-record.v1
2504.13052 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:19:43.290503Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

36 of 36 outbound references displayed

verified exact1
verified fuzzy2
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 97ca7d1c-0d5e-4c38-b937-a3c5c8653d16 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.143328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 118e1112-7d1c-4038-9cf1-fce9188c2b53 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Constitutional AI: Harmlessness from AI Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.148647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 811a994f-9aea-4927-95f7-ad8f026b6b9b · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.153378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c7c8c7-4524-4028-a740-2539b93b3b0c · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.158269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d880b1e-11fa-4584-9f35-c8120ce55f4a · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.765797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d3b2548c-b64d-47fb-ba9d-5a0edf2cdb43 · outbound

This paper cites Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:19:43.753505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 652e7996-236d-4768-a90b-9f7bc16bca9d · outbound

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

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.175652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3a3249-ff8b-473c-a62f-25e760b3eceb · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms PaLM: Scaling Language Modeling with Pathways

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.181415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e87f891-c18e-4205-b13f-2a22924b6ac8 · outbound

This paper cites Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:19:43.741468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6015ac9-89f9-4acb-b4b5-84bc9fe685e2 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.726013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d87ae1a4-a71d-4e46-a44c-4e4e780eddf4 · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.193692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9806ca26-e42d-4d14-9dea-65d88ec9637b · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.711933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 266546f7-6626-4e6e-9e03-25fdf72376ca · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.697932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d525fef6-adf0-4d78-b47e-90141a4fa4d7 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.681676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b194a0e7-825a-42a4-bc14-3bccf7c95fbd · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.668986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cd4ef144-6e1c-4893-98e5-78c173712ea7 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.656929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 308f7068-d749-40fe-8af6-a0e05830fabc · outbound

This paper cites Dimensionless Policies based on the Buckingham $\pi$ Theorem: Is This a Good Way to Generalize Numerical Results?.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Dimensionless Policies based on the Buckingham $\pi$ Theorem: Is This a Good Way to Generalize Numerical Results?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.219756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e39b708-40ce-4aa9-96c4-7f7bbfb56129 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.223772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cb12c34-8145-4982-9f69-91fa706c6313 · outbound

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

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.227849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee33961-7857-401f-bb49-9a725cc6d57a · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.635163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7bcdf1c7-5f21-4f98-80ae-771f9ac3ef26 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.621779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ac4a5a95-5af9-498c-a05e-83a84d76d493 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.240112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0ec0796-942a-4426-9333-925076d2bd28 · outbound

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

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.243830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e1b977f-11de-42e1-ad99-21424737cd7a · outbound

This paper cites Red Teaming Language Models with Language Models.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Red Teaming Language Models with Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.247800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92bad072-0b99-4894-a0fc-03834dc80dde · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.251671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6c8530-3350-42f1-9823-34a7cd62de4b · outbound

This paper cites JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.255707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3375a036-5715-4335-8b84-4de6ba3d4ec9 · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.601506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 604df649-8fcc-46de-9a5e-abf9a300014c · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.588791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2672420b-f5dc-4646-9501-7e3f02d6788e · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.574871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ad23a658-881c-4669-861b-e69216d9075b · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:19:43.561752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 350f2fc8-3cbd-4df7-9d0c-666506826f6b · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Jailbroken: How Does LLM Safety Training Fail?

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.278713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f9c0d9b-d5ca-4b42-a2cb-82e98b14aead · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.282682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45a4906-2582-42b8-955e-5885222aea9a · outbound

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

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Intention Analysis Makes LLMs A Good Jailbreak Defender

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.286453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cae675-c0a7-422b-902b-ceca414e8fef · outbound

This paper cites an unresolved cited work.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Unresolved cited work

Reference 34

Resolution: verified exact; raw_fallback, observed 2026-08-16T12:19:43.381976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 60888ade-9167-4b87-9409-905624aa94f1 · outbound

This paper cites In Proceedings of the 7th linguistic annotation workshop and interoperability with discourse.

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms In Proceedings of the 7th linguistic annotation workshop and interoperability with discourse

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.162770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b139c57a-92d3-4950-82f9-dcb1782ef004 · outbound

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

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T12:19:43.267743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.