Paper Citation Record · LEDGER

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles

As of 8 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2508.01306.

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

pith.paper-citation-record.v1
2508.01306 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:43:40.073275Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

25 of 25 outbound references displayed

verified exact1
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1ded64d4-720e-4ae0-b944-13a5e4d83283 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:36.985106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5902e9-e4ab-49e3-96ec-3085f0fd59f8 · outbound

This paper cites write newline.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:37.145293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d4818d0-96fb-4f56-9267-1e08446fcad8 · outbound

This paper cites GPT-4 Technical Report.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:37.259038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306c4112-9423-4524-b2fd-da3b8f8d556b · outbound

This paper cites an unresolved cited work.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:43:41.638288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5274f1ab-7551-49ac-b328-aec473bfe692 · outbound

This paper cites J.; Tramer, F.; et al.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles J.; Tramer, F.; et al

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:37.496644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aae5566-d2cd-4bd7-ba3d-75872c183f40 · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:37.671700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20626c28-3676-48d8-8e7c-7ee741253a55 · outbound

This paper cites an unresolved cited work.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Unresolved cited work

Reference 7

Resolution: verified exact; raw_fallback, observed 2026-08-06T05:43:40.651218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dd5cf14c-233b-454d-97ab-be7e62c3d86b · outbound

This paper cites The Llama 3 Herd of Models.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:37.961217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e04c14-b2c2-4c78-976c-287080a5fe3a · outbound

This paper cites an unresolved cited work.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:43:41.393847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2680fa61-a108-431c-80c6-0be934b876f9 · outbound

This paper cites an unresolved cited work.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:43:41.081716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7daf07f2-c6e9-4324-8584-e96186493675 · outbound

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

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.331010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7139482d-8116-4518-91a9-7a73e1b4c6c1 · outbound

This paper cites an unresolved cited work.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.472218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43329b81-ca3c-4e53-a62a-df8da321c8a6 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.589420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e775e1-0bf0-41c7-9cd1-cc4b41e33072 · outbound

This paper cites RAIN: Your Language Models Can Align Themselves without Finetuning.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles RAIN: Your Language Models Can Align Themselves without Finetuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.741656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1692130-ce9c-4065-b12e-ec1ff9b6cbfe · outbound

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

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.853734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c278c508-d352-450b-818b-b5d8de7982a3 · outbound

This paper cites FlipAttack: Jailbreak LLMs via Flipping.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles FlipAttack: Jailbreak LLMs via Flipping

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:38.965371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dbded75-3cce-4949-a41f-f03d92c62a78 · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.041036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7ae8ca-cbcb-4d08-b552-bae941816007 · outbound

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

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.140111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b0038ec-f6a8-402a-905d-a7765bdb8bc4 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Gemini: A Family of Highly Capable Multimodal Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.238090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 218856ef-8017-4313-b7d8-3c4288aa9d6f · outbound

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

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.293986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 639dec63-bc50-4249-b2cf-74d0d7b6919f · outbound

This paper cites SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.465663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af484381-9d39-4ae6-8e77-2f660dd1f53c · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.612853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b6d11f3-dffd-46e9-91d9-fd8f4ce197b0 · outbound

This paper cites Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.775290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9484f7-ecd8-451b-bb82-0e30f3a21d51 · outbound

This paper cites EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.916404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d008524b-2600-43f7-aabf-d8db455af81e · outbound

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

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:40.073275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.