Paper Citation Record · LEDGER

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2506.22508.

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

pith.paper-citation-record.v1
2506.22508 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:43:59.848555Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

31 of 31 outbound references displayed

verified exact1
verified fuzzy22
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6a9e2924-b983-4595-b114-098eefb21cd1 · outbound

This paper cites General data protection regulation (gdpr) – legal text.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text General data protection regulation (gdpr) – legal text

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:04.293377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8bfd28a9-6cd7-48ac-8906-43794a460b91 · outbound

This paper cites Chatgpt has been turned into a social media surveillance assistant, 2023.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Chatgpt has been turned into a social media surveillance assistant, 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:04.014722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9fa37c6e-dcb0-4a03-b5c3-7656508350e0 · outbound

This paper cites Aligning llms with individual preferences via interaction.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Aligning llms with individual preferences via interaction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:03.800271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68b8271e-d535-4a43-b902-a06d37a4fbd8 · outbound

This paper cites Beyond memorization: Violating privacy via inference with large language models.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Beyond memorization: Violating privacy via inference with large language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:03.503262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d254a75-eba3-41e6-9ab9-d6a302b6b01f · outbound

This paper cites Guide to protecting the confidentiality of personally identifiable information (pii).

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Guide to protecting the confidentiality of personally identifiable information (pii)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:03.334158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 768b8855-2271-4959-900d-027c9d2a65f5 · outbound

This paper cites Get serious about cybersecurity, 2025.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Get serious about cybersecurity, 2025

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:03.149054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3918e549-709f-489b-813a-7bdfda653b4f · outbound

This paper cites What is azure ai language - azure ai services, July 2023.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text What is azure ai language - azure ai services, July 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:02.928686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b563b4f2-2ddd-4b11-ba4d-4e8b18638091 · outbound

This paper cites Incognitext: Privacy-enhancing conditional text anonymization via llm-based private attribute randomization.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Incognitext: Privacy-enhancing conditional text anonymization via llm-based private attribute randomization

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:02.782098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 055dc75c-1813-4ad1-a5e5-5b5cb84ab842 · outbound

This paper cites Language models are advanced anonymizers.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Language models are advanced anonymizers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:02.572217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ff81759b-41c5-406c-adb9-055b272c610a · outbound

This paper cites Confidential prompting: Protecting user prompts from cloud llm providers, 2025.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Confidential prompting: Protecting user prompts from cloud llm providers, 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:02.307379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 181c47d0-6ae1-4935-8870-f01716ac9156 · outbound

This paper cites Expel: Llm agents are experiential learners.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Expel: Llm agents are experiential learners

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:58.665786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a567fa9-83cd-4692-8f9d-49efcd25bc1f · outbound

This paper cites A synthetic dataset for personal attribute inference.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text A synthetic dataset for personal attribute inference

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:02.109986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 21194aa4-4e7b-4834-a9fd-b00675e97351 · outbound

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

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.901352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f1f6a169-f199-4238-ba12-0b598cfab192 · outbound

This paper cites Division-of-thoughts: Harnessing hybrid language model synergy for efficient on-device agents.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Division-of-thoughts: Harnessing hybrid language model synergy for efficient on-device agents

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.791276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ecbf07ba-a1f5-4452-81d8-133a33fcb128 · outbound

This paper cites LIMP: Large Language Model Enhanced Intent-aware Mobility Prediction.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text LIMP: Large Language Model Enhanced Intent-aware Mobility Prediction

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:58.853559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd9339db-ee10-409f-8975-1322c879dfdf · outbound

This paper cites A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:44:00.077851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba6f0723-7d8f-49da-ae9e-e0e3ce75cac1 · outbound

This paper cites Propile: probing privacy leakage in large language models.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Propile: probing privacy leakage in large language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.645499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f9b4a023-76cd-4153-ae0d-e08e7a9c6799 · outbound

This paper cites User inference attacks on large language models.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text User inference attacks on large language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.562220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 667df307-0940-4c08-8789-c7f692321f88 · outbound

This paper cites Unveiling privacy risks in llm agent memory.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Unveiling privacy risks in llm agent memory

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.310940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 665c8f3f-1c08-4aa3-b4e9-d85f2476f6e4 · outbound

This paper cites Cogenesis: A framework collaborating large and small language models for secure context-aware instruction following.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Cogenesis: A framework collaborating large and small language models for secure context-aware instruction following

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:01.205783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f18d26e3-08f4-4d89-80ab-876445d57b81 · outbound

This paper cites Latticegen: Hiding generated text in a lattice for privacy-aware large language model generation on cloud.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Latticegen: Hiding generated text in a lattice for privacy-aware large language model generation on cloud

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:00.993361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 136c83ac-d220-4b19-b1e2-0efa54eea54f · outbound

This paper cites Privacyasst: Safeguarding user privacy in tool-using large language model agents.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Privacyasst: Safeguarding user privacy in tool-using large language model agents

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:00.851253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76507e2e-27ab-4617-b725-88a1f36df305 · outbound

This paper cites Rangel Pardo et al.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Rangel Pardo et al

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:00.619469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c83cf39c-799d-45d7-bd4a-af922ee94875 · outbound

This paper cites Overview of PAN’16.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Overview of PAN’16

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:00.483709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0a09d75f-c153-48c9-a487-adb9c334e20b · outbound

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

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.347264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4bed0c9-1c78-4d41-8f35-638b62173b1d · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.416069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c3afc5d-292f-4ee2-952b-a9dd7fc41f10 · outbound

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

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.514298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f3cbd8-1da0-4b08-9b50-bc93dc1d8b05 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Bleu: a method for automatic evaluation of machine translation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.600522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c327a11-7478-4508-b136-fbfb17ef935c · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Rouge: A package for automatic evaluation of summaries

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.635395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17143f68-5b96-4ef6-99af-2608ca6ece9a · outbound

This paper cites Deepseek-v3 technical report, 2024.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text Deepseek-v3 technical report, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:59.730456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84733dba-d24f-4ef7-9c0a-2dbc3dd98368 · outbound

This paper cites my husband.

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text my husband

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:44:00.249045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.