Paper Citation Record · LEDGER

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs

As of 9 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2507.16773.

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

pith.paper-citation-record.v1
2507.16773 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:07:29.257814Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

19 of 19 outbound references displayed

verified exact0
verified fuzzy7
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 05201edc-d32f-405f-b174-b51f393d33f1 · outbound

This paper cites A survey on evaluation of large language models.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs A survey on evaluation of large language models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:26.934335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a12be6dd-9f33-45b8-b1ed-67b5063f8f8a · outbound

This paper cites Cursor, 2025.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Cursor, 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:30.798122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 746a2c02-ab2c-4aad-a90d-0a0c23d668b1 · outbound

This paper cites Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language Models.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:27.091221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4d6aac-1a30-475a-a933-55b99c5e6fc6 · outbound

This paper cites How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:27.204889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc01643b-1259-4b35-8ed3-4e1de14ba9b6 · outbound

This paper cites Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:27.303078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1cc02ef-74c8-42b0-a8a3-5db8cd6af791 · outbound

This paper cites Github copilot, 2025.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Github copilot, 2025

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:30.535060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a35c2f4c-4dcd-4728-bd46-0ccd0d034b89 · outbound

This paper cites Not what you’ve signed up for: Com- promising real-world llm-integrated applications with indirect prompt injection.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Not what you’ve signed up for: Com- promising real-world llm-integrated applications with indirect prompt injection

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:30.335353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a20a5484-4423-4582-8ce3-44082c259dd8 · outbound

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

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:27.694945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32d4999e-f949-4bcf-ba50-b84d03b796ca · outbound

This paper cites Teaching Large Language Models to Reason with Reinforcement Learning.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Teaching Large Language Models to Reason with Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:27.843871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c597b790-18f1-4496-87ae-5d2a88545d13 · outbound

This paper cites Make a feint to the east while attacking in the west: Blinding llm-based code auditors with flashboom attacks.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Make a feint to the east while attacking in the west: Blinding llm-based code auditors with flashboom attacks

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:30.115723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fb395cd1-6a2a-4b09-a4ad-fc48e0b36391 · outbound

This paper cites Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:28.060649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c8095f4-b35c-40fa-8a9e-3d0625301e79 · outbound

This paper cites If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:28.171464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf1e096-7edc-405b-b48a-cae1380f1281 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Formalizing and benchmarking prompt injection attacks and defenses

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:28.301024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 817a8fe2-1522-4376-aadf-ccb49a530bc6 · outbound

This paper cites o4-mini system card, 2025.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs o4-mini system card, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:29.919600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7fc41eee-d528-4f46-b65c-2bee35710940 · outbound

This paper cites On the Importance of Local Information in Transformer Based Models.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs On the Importance of Local Information in Transformer Based Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:28.675522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbac1ab2-610e-4d79-b9be-2dc1ed8a3144 · outbound

This paper cites Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:29.025940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38c9759-2643-4c25-9676-9bdd527ce024 · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:29.788338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f7f3ea09-6238-4c21-bfb5-087bdff60e54 · outbound

This paper cites On large language models’ resilience to coercive interro- gation.

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs On large language models’ resilience to coercive interro- gation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:07:29.569680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2fc7540c-8fa6-4f35-9582-0abde34b4e65 · outbound

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

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:07:29.257814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.