Paper Citation Record · LEDGER

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

As of 14 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 3 inbound Pith citation observations for arXiv:2508.20848.

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

pith.paper-citation-record.v1
2508.20848 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:51:03.815504Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T18:13:19.384136Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T12:10:06.509534Z

Reference resolution

66 of 66 outbound references displayed

verified exact2
verified fuzzy29
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 32ebab59-47bb-4818-98c3-26d242edbf90 · outbound

This paper cites Generated data with fake privacy: Hidden dangers of fine- tuning large language models on generated data.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Generated data with fake privacy: Hidden dangers of fine- tuning large language models on generated data

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.387810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42b06550-8600-4ab1-b19c-1ceb60b02c2c · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.615051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d857cd3-8e8c-4a28-8dc2-7bf6c511b82b · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.619114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f86bbfdc-109e-464b-9a01-fb34afe264e4 · outbound

This paper cites Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.622906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570d32ca-4360-4119-ac7b-4de9a8d71d55 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring A General Language Assistant as a Laboratory for Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.626250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation defa2534-e48e-418d-b67b-46484af9e479 · outbound

This paper cites A Ranking Method for Evaluating Constructed Responses.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring A Ranking Method for Evaluating Constructed Responses

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.378732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 276994cd-d6c1-4f89-b9a5-3d6e6102ca0c · outbound

This paper cites Brookhart.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Brookhart

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.369450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 069744d8-a374-41c0-a16f-5ff684800782 · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.361269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 432efd07-3769-4701-825b-3683c23c7bc3 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.638815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf91c4a7-08fe-49fa-9e7d-f6f5f0812138 · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.642689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 914ffc20-a3ee-46f8-9239-f750fb86e931 · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.645921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed30b360-be18-4fab-aba4-4b45edff134d · outbound

This paper cites Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.353045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c75e5d42-8785-40e9-87e5-d5f2edb0e818 · outbound

This paper cites DeepSeek-V3.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring DeepSeek-V3

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.344587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c916155-82f6-4eff-9e07-294e050bdfbe · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.336098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 60cdb11d-9ef6-4851-9fc6-6a4387f3f242 · outbound

This paper cites Sheridan Center for Teaching and Brown University Learning.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Sheridan Center for Teaching and Brown University Learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.318511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4e79d65e-b3c8-47d9-bbc6-429cd92901c8 · outbound

This paper cites https://www.perspectiveapi.com.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring https://www.perspectiveapi.com

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.309398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 959cbe90-79e5-444a-8150-c924af79b856 · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.667508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f69221-07f3-48d4-b130-fd0428948258 · outbound

This paper cites Spear Phishing With Large Language Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Spear Phishing With Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.671313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 543ae494-8b11-42e1-8688-f6e44d17fec7 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.674278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2532c17-1cf9-421b-8aa6-0cb1c32ff0b9 · outbound

This paper cites Hunter, Richard M.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Hunter, Richard M

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.300861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f51ea7c1-eb51-4dc7-9978-a3324a6ef96f · outbound

This paper cites Adjacent Words, Divergent Intents: Jailbreaking Large Lan- guage Models via Task Concurrency.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Adjacent Words, Divergent Intents: Jailbreaking Large Lan- guage Models via Task Concurrency

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.291722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 69f9934b-b5b1-4be8-8bd1-a59ff717b30b · outbound

This paper cites Boone Jr and Deborah A.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Boone Jr and Deborah A

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.283045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 809aa72a-269f-44a4-93b4-b4bc209e8fe2 · outbound

This paper cites Analytic or Holistic: A Study of Agreement Between Different Grading Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Analytic or Holistic: A Study of Agreement Between Different Grading Models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.274508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6b855f65-370a-4a6e-af8d-0c425d694e42 · outbound

This paper cites Analytic or Holistic? A Study about How to Increase the Agreement in Teachers’ Grading.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Analytic or Holistic? A Study about How to Increase the Agreement in Teachers’ Grading

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.266311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6857368-c41a-444e-9b2e-866c399a234a · outbound

This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.693056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a01e0788-4ac4-45e5-b567-ed88d7591702 · outbound

This paper cites Content Analysis: An Introduction to Its Methodology.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Content Analysis: An Introduction to Its Methodology

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.258180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7843f4d4-edf4-4335-8045-7ed3a554c2c4 · outbound

This paper cites Richard Landis and Gary G.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Richard Landis and Gary G

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.249629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eb9aea90-8afe-4ad8-9ab5-f07676fd8ac5 · outbound

This paper cites LangGraph.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring LangGraph

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.240819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ff788327-4c43-463e-831d-603c66ff10d8 · outbound

This paper cites A technique for the measurement of attitudes.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring A technique for the measurement of attitudes

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.231331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3f1a82dc-90a6-4590-a0fe-d3dc646a1489 · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.707918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c86dd371-6e4a-4f4f-b482-40c1f7ec3d11 · outbound

This paper cites Lipnevich, and Ig- nacio Mañez.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Lipnevich, and Ig- nacio Mañez

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.223124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8905b60c-123b-45f2-925c-30bbb64465ee · outbound

This paper cites Designing Effective Rubrics for Peer As- sessment Methods.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Designing Effective Rubrics for Peer As- sessment Methods

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.214576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ccd19ec1-c342-4e8a-a7dc-896ea4cc9e2e · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.717384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dddcc0d3-a88e-4da8-9197-baa444be216f · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.721078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2f4a60c-f7ec-41ac-a4e1-98609dbc8580 · outbound

This paper cites SaloRA: Safety-alignment preserved low-rank adaptation.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring SaloRA: Safety-alignment preserved low-rank adaptation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.206176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65ba034b-cdfe-4dda-b104-91ebfd1172b7 · outbound

This paper cites FactLens: Benchmarking Fine-Grained Fact Verification.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring FactLens: Benchmarking Fine-Grained Fact Verification

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:51:03.959404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2ef7296d-036f-4472-9590-6f12b071f888 · outbound

This paper cites Scoring student answers to constructed-response questions and essays.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Scoring student answers to constructed-response questions and essays

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.197220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e5e12121-836a-4965-be8f-c6989b2e0ea8 · outbound

This paper cites Scoring student answers to constructed-response questions, essays, and open-response questions.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Scoring student answers to constructed-response questions, essays, and open-response questions

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.188950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0205451e-2b92-4338-8bcc-6f89c9b2572f · outbound

This paper cites https://platform.openai.com/docs/guides/ moderation/overview.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring https://platform.openai.com/docs/guides/ moderation/overview

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.180549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ef456b9-07aa-43cf-967a-fccb36043cad · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.171996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2ad982ff-fbb7-4a0a-99b1-cf806f0b8629 · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.162824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e66838e6-bf79-488a-82f3-a1997c354503 · outbound

This paper cites GPT-4o-mini.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring GPT-4o-mini

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.154437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c0a30e69-2fd0-4941-8de3-acfcad50430c · outbound

This paper cites GPT-4 Technical Report.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring GPT-4 Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.748795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd8fdcd8-e055-4f04-bb01-21fa3a14f5cb · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.145468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 49441f07-c0c4-4a7f-b4fa-fafc20670bf2 · outbound

This paper cites Red Teaming Language Models with Language Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Red Teaming Language Models with Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.754420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984346ee-a6e2-4f57-ad31-50977142e3ca · outbound

This paper cites What’s Wrong–and What’s Right– with Rubrics.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring What’s Wrong–and What’s Right– with Rubrics

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.136903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0cd0e695-da34-4af5-91c4-84dceedbda55 · outbound

This paper cites Unsafe Diffusion: On the Gen- eration of Unsafe Images and Hateful Memes From Text-To- Image Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unsafe Diffusion: On the Gen- eration of Unsafe Images and Hateful Memes From Text-To- Image Models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.128292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 32171dfa-5f8d-4376-9f7c-fc60394a0869 · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.119441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0217de0c-6e66-48c9-9d73-5d2d29e35de2 · outbound

This paper cites Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.766731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e43e52e-d4ab-46fc-880b-5687e2665f24 · outbound

This paper cites Shabani and Jaleh Panahi.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Shabani and Jaleh Panahi

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.110110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cae8d7c0-f6d3-4352-a1d7-6a783abf1da2 · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.772540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06d4c969-eda1-4d86-8101-484350effe8a · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring A StrongREJECT for Empty Jailbreaks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.775476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de08ded0-f4ee-4604-a4c1-b827934ad15a · outbound

This paper cites Analyzing and In- terpreting Data From Likert-Type Scales.Journal of Graduate Medical Education, 2013.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Analyzing and In- terpreting Data From Likert-Type Scales.Journal of Graduate Medical Education, 2013

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.100375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 27a27e2a-4d0e-420c-9e35-e7701027fac8 · outbound

This paper cites TavilySearch.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring TavilySearch

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.091307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e0882ab9-16a4-45cc-bbbf-62aa3c85f2ed · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.082504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e19f20ff-3fd5-4c5c-9952-6277d53d0387 · outbound

This paper cites Excessive Reasoning Attack on Reasoning LLMs.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Excessive Reasoning Attack on Reasoning LLMs

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.787053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6b0fcd8-cb2a-4750-ada1-0e90c47c201e · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Jailbroken: How Does LLM Safety Training Fail?

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.790055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e1a384a-f6b2-4472-b578-acd638b17247 · outbound

This paper cites Long-form factuality in large language models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Long-form factuality in large language models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.793719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560af3c0-046c-40eb-90de-d44ddc6a6834 · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Fundamental Limitations of Alignment in Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.796947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fad2d1a-a39a-4725-8aa5-02bb7f3be15b · outbound

This paper cites SOS! Soft Prompt Attack Against Open-Source Large Language Models.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring SOS! Soft Prompt Attack Against Open-Source Large Language Models

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:51:03.879519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a0678564-32d8-4534-93d4-5716c60d3a32 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Low-Resource Languages Jailbreak GPT-4

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.803021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b903e31-4c67-405b-b32e-22ce8c14b424 · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.806170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5531412-abc6-4cc6-8172-d5c6707a2983 · outbound

This paper cites Parker, and Munmun De Choudhury.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Parker, and Munmun De Choudhury

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:51:04.073967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0acbcdc5-64f0-4ef2-937b-b660adecc5c2 · outbound

This paper cites Don't Say No: Jailbreaking LLM by Suppressing Refusal.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Don't Say No: Jailbreaking LLM by Suppressing Refusal

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.812481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0ea74c-3664-4569-b173-93f2c7ef442e · outbound

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

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.815504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27fdc326-0ce0-4f47-9b3f-e8ce81cf1cfe · outbound

This paper cites an unresolved cited work.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Unresolved cited work

Reference 590

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:51:04.327673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation c1a0178b-f60e-4759-bf4c-87257e0992b9 · inbound

Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks cites this paper.

Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:10:06.512435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 796f7483-e403-446a-95b2-4f8c0b5b8507 · inbound

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models cites this paper.

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T16:46:16.287825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c4cb8b6-fa16-40d1-8deb-816a7bfbcaa0 · inbound

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation cites this paper.

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T18:13:19.384136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.