Paper Citation Record · LEDGER

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

As of 21 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 5 inbound Pith citation observations for arXiv:2412.01547.

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

pith.paper-citation-record.v1
2412.01547 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T04:21:32.573063Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:21:58.775054Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-02T17:37:14.863127Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy3
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3765612d-645f-482d-ac6d-150ff3c3944d · outbound

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

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.432719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c929c69c-275c-4b73-9284-94cf08656a6d · outbound

This paper cites write newline.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.440050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd5be9e-dc9c-4e5e-a105-751eb0567bc2 · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.446222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac0c51d-fdcb-4a4d-8782-406bd3c7ccba · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.453742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 496307b9-a0a0-4448-a78a-6ca4684106fd · outbound

This paper cites garak: A Framework for Security Probing Large Language Models.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings garak: A Framework for Security Probing Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.458858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fddb66-35c2-4e6a-9356-fcceaacb07f4 · outbound

This paper cites Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-12T04:21:32.816720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dcb307d9-1a74-4df4-83c4-2f2756da282f · outbound

This paper cites Mistral 7B.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Mistral 7B

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.470368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb867f2-0255-4f0a-83d8-0ec30fce59c2 · outbound

This paper cites Dense Passage Retrieval for Open-Domain Question Answering.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Dense Passage Retrieval for Open-Domain Question Answering

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.475606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e26904-825f-4c07-b216-501dc359a7df · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.482163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1272fbd4-66a2-4e77-b78a-bbad6b853592 · outbound

This paper cites ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.488307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33abaff4-88bb-4a4c-b770-ae09b6674b99 · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-12T04:21:32.969220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation be630a12-56d2-45a4-bcca-c44d509751eb · outbound

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

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.498164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1223064d-ab71-4d52-bab6-456495eccd2c · outbound

This paper cites Embedding And Clustering Your Data Can Improve Contrastive Pretraining.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Embedding And Clustering Your Data Can Improve Contrastive Pretraining

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.502801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df596c98-26b9-49c5-9280-655a2abf603b · outbound

This paper cites S.; and Dean, J.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings S.; and Dean, J

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.507961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a27738ee-e9d9-4a69-a28f-1922a3aa1363 · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-12T04:21:32.939345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 503cdfce-8364-4355-9654-d4fc75b6c598 · outbound

This paper cites NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.527774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b247fdaa-fb24-4e69-ac3b-36cf85a4472e · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-12T04:21:32.921408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0cce9b8b-fbd2-4f3b-a8a2-1809756295a8 · outbound

This paper cites J.; and Fergus, R.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings J.; and Fergus, R

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:21:32.905185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ca03a192-8675-4529-89da-0649a05c8a79 · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.542711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e249e374-5cc3-4801-9747-2528aaab56bd · outbound

This paper cites Defending LLMs against Jailbreaking Attacks via Backtranslation.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Defending LLMs against Jailbreaking Attacks via Backtranslation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.548337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1470620-6bd6-4a41-8776-1b5b2bbbe060 · outbound

This paper cites an unresolved cited work.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-12T04:21:32.887555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a4db5e51-7d0b-4a58-9adc-e394975d13e5 · outbound

This paper cites Fundamental Limitations of Alignment in Large Language Models.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Fundamental Limitations of Alignment in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.557671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fba57223-2d62-4e64-9008-175f9416fdb7 · outbound

This paper cites S.; Brendel, W.; Tramer, F.; and Carlini, N.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings S.; Brendel, W.; Tramer, F.; and Carlini, N

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:21:32.869645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6d581b2c-0d43-4e02-adbd-4902bb1eb018 · outbound

This paper cites Z.; Fredrikson, M.; and Hendrycks, D.

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Z.; Fredrikson, M.; and Hendrycks, D

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:21:32.853119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 956c13dc-f97a-4a7f-990f-587be8770193 · outbound

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

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T04:21:32.573063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 65c83966-1ce6-4228-bb4b-5cfabc2683bf · inbound

JavelinGuard: Low-Cost Transformer Architectures for LLM Security cites this paper.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.376227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6b8fbfe-074b-4a14-bc40-02564e602db2 · inbound

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift cites this paper.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.775054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f3a56b-d971-4121-bf3f-4d75a8a68d17 · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:17.939109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 799fe302-a05b-414f-8f72-414431b54b6a · inbound

Cross-Lingual Jailbreak Detection via Semantic Codebooks cites this paper.

Cross-Lingual Jailbreak Detection via Semantic Codebooks Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:46:21.666210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4922b0cb-cebc-423a-93bc-ba950cbcfb23 · inbound

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics cites this paper.

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:37:14.864659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.