Paper Citation Record · LEDGER

HauntAttack: When Attack Follows Reasoning as a Shadow

As of 17 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2506.07031.

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

pith.paper-citation-record.v1
2506.07031 v5

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:47:33.727356Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:06.951116Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy5
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 851a0adc-8e63-4f74-bb40-809fa30766d1 · outbound

This paper cites Are we there yet?.

HauntAttack: When Attack Follows Reasoning as a Shadow Are we there yet?

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:33.896502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b3731d9b-a07c-478f-ac7d-4567f94efbc5 · outbound

This paper cites Google DeepMind.

HauntAttack: When Attack Follows Reasoning as a Shadow Google DeepMind

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:35.041624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 310434d5-65dd-494b-8f10-b51f063fbc25 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

HauntAttack: When Attack Follows Reasoning as a Shadow DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.650402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4767e7f-681f-4784-9bb6-6493102d003d · outbound

This paper cites In the final layer, the characters among all layers discuss which specific and practical commands, tools, or steps should be used.

HauntAttack: When Attack Follows Reasoning as a Shadow In the final layer, the characters among all layers discuss which specific and practical commands, tools, or steps should be used

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:34.708159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff96a400-ce46-47a2-9fb2-050d023f85ac · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

HauntAttack: When Attack Follows Reasoning as a Shadow Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.959808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60366104-391d-4310-a74b-18c7f08b0d10 · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

HauntAttack: When Attack Follows Reasoning as a Shadow How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:33.123729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850fd639-c327-4f80-87f5-e06230ea58cd · outbound

This paper cites how to build a harmful device.

HauntAttack: When Attack Follows Reasoning as a Shadow how to build a harmful device

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:34.559169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2d116b58-cf4b-4042-ae51-d343ee00af23 · outbound

This paper cites an unresolved cited work.

HauntAttack: When Attack Follows Reasoning as a Shadow Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:47:34.413586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03a087a3-a5fa-42cc-9b16-eb7ecb3ae275 · outbound

This paper cites manipulate or trick people into doing something they don’t want to do.

HauntAttack: When Attack Follows Reasoning as a Shadow manipulate or trick people into doing something they don’t want to do

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:34.057253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2957a9a5-4eaf-4e35-ba01-4bc239cd81ee · outbound

This paper cites an unresolved cited work.

HauntAttack: When Attack Follows Reasoning as a Shadow Unresolved cited work

Reference 1903

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:47:34.228994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b0d422e-3032-4269-b763-60f0fb8db4a4 · outbound

This paper cites The Limitations of Deep Learning in Adversarial Settings.

HauntAttack: When Attack Follows Reasoning as a Shadow The Limitations of Deep Learning in Adversarial Settings

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.904485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329e8a2c-44bc-463f-916b-0bb35e27d346 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

HauntAttack: When Attack Follows Reasoning as a Shadow Training Verifiers to Solve Math Word Problems

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.489860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29ecab10-35e5-474b-a0eb-8e5bf5535197 · outbound

This paper cites an unresolved cited work.

HauntAttack: When Attack Follows Reasoning as a Shadow Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:47:34.877430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87b6a98a-f248-4aa8-9fee-2c2c816a7254 · outbound

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

HauntAttack: When Attack Follows Reasoning as a Shadow GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:33.084577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed146dd7-70bb-41ba-a40c-80800e5129fa · outbound

This paper cites JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks.

HauntAttack: When Attack Follows Reasoning as a Shadow JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.731410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e336615-0405-49e9-8462-a5845e5ce4fd · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

HauntAttack: When Attack Follows Reasoning as a Shadow Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.444127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ad302c0c-9383-44de-9691-f037e1b5e926 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models HauntAttack: When Attack Follows Reasoning as a Shadow

Reference 124

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:06.951116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.