Paper Citation Record · LEDGER

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

As of 21 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 5 inbound Pith citation observations for arXiv:2506.12430.

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

pith.paper-citation-record.v1
2506.12430 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:57:13.807101Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:01:41.521564Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T08:16:06.518951Z

Reference resolution

33 of 33 outbound references displayed

verified exact3
verified fuzzy3
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f54fb324-a2c2-4622-92b2-cd0a9dbbbada · outbound

This paper cites AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.689552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2592e23-781a-4075-8f1d-cf50b905047c · outbound

This paper cites SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.693926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76826419-df01-434d-9e2f-87d04a9e904a · outbound

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

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.676103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05f04817-a770-4ae9-a563-be7b0d121e73 · outbound

This paper cites Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.702701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c06f9c9-f2db-42b1-9c5b-fb8df3fbfd5f · outbound

This paper cites Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.707276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d8930b-e5f0-4047-b43f-a683871c85f6 · outbound

This paper cites Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.711395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047b88bb-3472-48e1-aab5-69bb68dd4043 · outbound

This paper cites Large spin shuttling oscillations enabling high-fidelity single qubit gates.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Large spin shuttling oscillations enabling high-fidelity single qubit gates

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T00:57:14.270803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1490e152-a044-48dc-a8c0-e666c07c1b53 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 LLaVA-OneVision: Easy Visual Task Transfer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.719507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f17fc3f-73ed-49e7-b3d1-6284028ad93b · outbound

This paper cites Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.723670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 399aa97c-18fe-4305-89cd-308654c59abe · outbound

This paper cites Red pill and blue pill: Controllable website fingerprinting defense via dynamic backdoor learning.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Red pill and blue pill: Controllable website fingerprinting defense via dynamic backdoor learning

Reference 15

Resolution: verified exact; raw_fallback, observed 2026-08-07T00:57:14.209630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8e69c3d7-c8e4-4647-9ce5-9575afcc51e9 · outbound

This paper cites LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.739840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc1aa81f-8116-40cc-bdf6-76e3bc66671e · outbound

This paper cites Visual Instruction Tuning.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Visual Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.743808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47713456-a413-4c7d-9934-b4ecac8b5e06 · outbound

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

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Training language models to follow instructions with human feedback

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.751706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 925b90e8-dbdf-43e8-b2ee-94e35ed6c82c · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.759973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdb5252-2c67-4a4e-afaa-f85f19f35af5 · outbound

This paper cites POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.763982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f774a9d4-d82c-4377-99ac-5ce50c7c1e4f · outbound

This paper cites Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.767811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d64ec6-2de9-4e5a-b235-bc0f4f94626a · outbound

This paper cites Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.747840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a80fabca-9bde-4030-9093-a4157f3c9600 · outbound

This paper cites Safety in Large Reasoning Models: A Survey.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Safety in Large Reasoning Models: A Survey

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.771631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04dfc90-25fc-4837-98a1-7b20cfc5188b · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.779681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87738e8-71f4-41d6-a1ca-80f50c110c1e · outbound

This paper cites Distraction is All You Need for Multimodal Large Language Model Jailbreaking.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Distraction is All You Need for Multimodal Large Language Model Jailbreaking

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:57:13.995549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3f02041a-4b63-4f7e-904c-fb8306e3faa0 · outbound

This paper cites SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.787678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb7a3ac4-85eb-4c0d-9a8e-37721d4c5e1d · outbound

This paper cites A Survey on Trustworthy LLM Agents: Threats and Countermeasures.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 A Survey on Trustworthy LLM Agents: Threats and Countermeasures

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.791531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a76e6f-afc4-4d0e-84de-11b6b2635d1d · outbound

This paper cites Multimodal Chain-of-Thought Reasoning in Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Multimodal Chain-of-Thought Reasoning in Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.795355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 936bf545-aaa9-464c-9b0b-ae57ea48e7c0 · outbound

This paper cites Zhou, Z., Yu, H., Zhang, X., Xu, R., Huang, F., Wang, K., Liu, Y ., Fang, J., and Li, Y.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Zhou, Z., Yu, H., Zhang, X., Xu, R., Huang, F., Wang, K., Liu, Y ., Fang, J., and Li, Y

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.799845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd7c126-5720-4a37-8806-068fde23779c · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.803299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a955208-7a70-4d16-bd12-0ca9b74111d7 · outbound

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

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.807101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c896b4db-e086-417c-99ee-bb679231b378 · outbound

This paper cites GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.775636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b6f4bb-5afc-4a5f-b0a8-a65c255310e3 · outbound

This paper cites Generate more impercepti- ble adversarial examples for object detection.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Generate more impercepti- ble adversarial examples for object detection

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:57:14.416041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 218de7a9-17bd-4f9f-87a0-8b5f770bdce1 · outbound

This paper cites Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.731835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2196c723-a62e-4edc-b08a-5aea255af0fd · outbound

This paper cites Leveraging multimodal llm for inspirational user interface search.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Leveraging multimodal llm for inspirational user interface search

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:57:14.402863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e1fea86c-5706-42b9-ba5c-46f1286240d8 · outbound

This paper cites Unbridled icarus: A survey of the potential perils of image inputs in multimodal large language model security.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Unbridled icarus: A survey of the potential perils of image inputs in multimodal large language model security

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:57:14.429797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 77dcf9e1-d1f8-4a47-be3f-9f06bc13eea7 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Multilingual Jailbreak Challenges in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.680823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11a93f9-8b02-4731-ac6c-08d5e1f7a551 · outbound

This paper cites PRJ: Perception-Retrieval-Judgement for Generated Images.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 PRJ: Perception-Retrieval-Judgement for Generated Images

Reference 2025

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:57:14.333337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation d959c428-ffb2-4b39-a8e2-ed0d461d1b1f · inbound

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models cites this paper.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.973955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5db08660-b4bb-4fc9-ac48-6ec409bfe460 · inbound

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents cites this paper.

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-18T08:16:06.521830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b3ab311e-9aff-4b77-873c-ea444aa4f29d · inbound

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models cites this paper.

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:05:49.310638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b46e91eb-d5d8-4892-a19e-6cdca8a2adfd · inbound

Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems cites this paper.

Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-30T19:40:15.494000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a84e0f-5891-4928-8125-6b618b3d553f · inbound

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense cites this paper.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.521564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.