Paper Citation Record · LEDGER

Fast Proxies for LLM Robustness Evaluation

As of 8 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2502.10487.

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

pith.paper-citation-record.v1
2502.10487 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:32:24.149582Z

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 exact0
verified fuzzy3
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a52b6e34-9cab-4c84-9a96-34083bd83ec2 · outbound

This paper cites Phi-4 Technical Report.

Fast Proxies for LLM Robustness Evaluation Phi-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.021078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d1ae997-d9f3-4cb6-ad23-14bd87d03dec · outbound

This paper cites Qwen Technical Report.

Fast Proxies for LLM Robustness Evaluation Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.030248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f60c0e12-aceb-4feb-8476-77092bd92f39 · outbound

This paper cites The Llama 3 Herd of Models.

Fast Proxies for LLM Robustness Evaluation The Llama 3 Herd of Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.037279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24461f8-db07-468b-a3d3-54643b315dea · outbound

This paper cites Mistral 7B.

Fast Proxies for LLM Robustness Evaluation Mistral 7B

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.041487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d9c45c-9194-4078-a496-571e02d37ab6 · outbound

This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.

Fast Proxies for LLM Robustness Evaluation LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.045500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feb381d0-e013-4b82-8a6d-8a4e6a39f74b · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

Fast Proxies for LLM Robustness Evaluation AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.048917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27897394-233f-4ca9-85d8-19ce25af9711 · outbound

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

Fast Proxies for LLM Robustness Evaluation AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.092803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33b781c-606c-4524-b38f-1ce9ab2f1526 · outbound

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

Fast Proxies for LLM Robustness Evaluation HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.096447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc2f63f1-eaeb-460b-8ca7-d6a49861fdf3 · outbound

This paper cites Fast Adversarial Attacks on Language Models In One GPU Minute.

Fast Proxies for LLM Robustness Evaluation Fast Adversarial Attacks on Language Models In One GPU Minute

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.099738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 598f292b-bfcb-41c2-b320-390c0e68616d · outbound

This paper cites Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts.

Fast Proxies for LLM Robustness Evaluation Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.103244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b879a50-5670-4f39-bab6-18f92f6b5a20 · outbound

This paper cites Adversarial Attacks and Defenses in Large Language Models: Old and New Threats.

Fast Proxies for LLM Robustness Evaluation Adversarial Attacks and Defenses in Large Language Models: Old and New Threats

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.106441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc9c4729-bf71-48df-b815-87370bc68e8b · outbound

This paper cites Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

Fast Proxies for LLM Robustness Evaluation Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.110160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00685c8-17d2-4db3-a754-c3591a9824e6 · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Fast Proxies for LLM Robustness Evaluation Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.113138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c8e577-5f46-40c3-813d-6e8fb19398ba · outbound

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

Fast Proxies for LLM Robustness Evaluation Gemma 2: Improving Open Language Models at a Practical Size

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.116471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc48bd29-eb95-488a-b3c8-7e52a14dd6e6 · outbound

This paper cites Hermes 3 Technical Report.

Fast Proxies for LLM Robustness Evaluation Hermes 3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.119477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7bf6e61-cf7a-44ff-9b5b-dc2ad610cfe7 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Fast Proxies for LLM Robustness Evaluation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.122684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 075bd7b0-4836-41d1-9708-80cf6a8e12ca · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

Fast Proxies for LLM Robustness Evaluation Zephyr: Direct Distillation of LM Alignment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.126931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2ac0286-28ca-49a7-a4d0-56b6ededdb7f · outbound

This paper cites Bypassing the Safety Training of Open-Source LLMs with Priming Attacks.

Fast Proxies for LLM Robustness Evaluation Bypassing the Safety Training of Open-Source LLMs with Priming Attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.131114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f10703b-0917-4198-963a-5a4b71051455 · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

Fast Proxies for LLM Robustness Evaluation Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.135448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c891ac-d14e-4f5e-b3d4-dd6310e1dada · outbound

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

Fast Proxies for LLM Robustness Evaluation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.139663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0aca436-8f82-40bf-b540-7853eb4be69e · outbound

This paper cites We use bfloat16 quantization for all models.

Fast Proxies for LLM Robustness Evaluation We use bfloat16 quantization for all models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:32:24.432768Z

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 cef188b4-8d56-413f-bc37-3f598af7432f · outbound

This paper cites 250, use a batch size of 512, Top-K “ 256, and initialize using the string “x x x x x x x x x x x x x x x x x x x x.

Fast Proxies for LLM Robustness Evaluation 250, use a batch size of 512, Top-K “ 256, and initialize using the string “x x x x x x x x x x x x x x x x x x x x

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:32:24.422481Z

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 294d91a6-966b-4e0b-8fed-b97afafd9f85 · outbound

This paper cites x x x x x x x x x x x x x x x x x x x x.

Fast Proxies for LLM Robustness Evaluation x x x x x x x x x x x x x x x x x x x x

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T19:32:24.409641Z

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 af7ce8b5-a93b-483c-8906-abb739783706 · outbound

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

Fast Proxies for LLM Robustness Evaluation Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.033840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31201e82-4e66-438f-9316-cc01e2e0ec73 · outbound

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

Fast Proxies for LLM Robustness Evaluation Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.025979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.