Paper Citation Record · LEDGER

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI

As of 21 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.19433.

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

pith.paper-citation-record.v1
2607.19433 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T15:05:21.556705Z

measured 26 of 26 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 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

26 of 26 outbound references displayed

verified exact2
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 387f6590-271f-417d-a891-d031e8c3d4ec · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.271723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f4b2d42-89a2-4bd2-9810-e4d03ba365bb · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI ReAct: Synergizing Reasoning and Acting in Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.349712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7ae3d69-fd38-49a5-b30d-106000c05d88 · outbound

This paper cites Generative agents: Interactive simulacra of human behavior,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Generative agents: Interactive simulacra of human behavior,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.409490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a9fefd7-6ce8-4dfb-9b79-5fd7a034e6d4 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI MemGPT: Towards LLMs as Operating Systems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.491143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2738f9d0-18af-46bb-b6b6-b54d4bb91579 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.577118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f539b97a-aa33-4733-be60-33718a89f0bb · outbound

This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.672207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b77c8d91-9467-4ad7-8e03-a12259e24fef · outbound

This paper cites Portcullis: A scalable and verifiable privacy gateway for large language models,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Portcullis: A scalable and verifiable privacy gateway for large language models,

Reference 7

Resolution: verified exact; doi, observed 2026-08-01T15:08:29.671575Z

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 56bfe2eb-8ff4-4f73-a846-2a9cc5cca557 · outbound

This paper cites A practical memory injection attack (MINJA) against LLM agents,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI A practical memory injection attack (MINJA) against LLM agents,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:18.958640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57817ecf-41e0-492f-8f00-ac73d5ef9c1e · outbound

This paper cites MemoryGraft: Persistent compromise of LLM agents via poisoned RAG stores,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI MemoryGraft: Persistent compromise of LLM agents via poisoned RAG stores,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.088649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f0e0c8-9843-4f84-b660-f86570905148 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.200461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbac8c23-5a3e-4800-8902-744b1c05b3de · outbound

This paper cites Many-to-one adversarial consensus: Exposing multi-agent collusion risks in AI-based healthcare,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Many-to-one adversarial consensus: Exposing multi-agent collusion risks in AI-based healthcare,

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-08-01T15:08:29.454134Z

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 3bc24c1e-11f6-4de4-b241-7937b170c3f7 · outbound

This paper cites EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.509390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 505ad013-7f23-484f-9bda-a233d4e14e17 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.657830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e7ed87-d93a-463c-a91f-eacdb41cd026 · outbound

This paper cites Mind2Web: Towards a generalist agent for the web,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Mind2Web: Towards a generalist agent for the web,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.760398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec2fb475-28b2-491f-ba41-0be0b89c2614 · outbound

This paper cites ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.842069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5a8ba56-a0b2-4b46-a5c0-101450d055eb · outbound

This paper cites World of workflows: A benchmark for enterprise agent reliability,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI World of workflows: A benchmark for enterprise agent reliability,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:19.986478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 998a80f3-dc34-4e61-aded-6ff2e6477b06 · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI AgentBench: Evaluating LLMs as Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.154953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e45b31e-ba8e-4ec8-90d7-a049dad508d1 · outbound

This paper cites Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.299478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 632580ff-ae0b-4a8b-9b6d-f20f6a855a4a · outbound

This paper cites AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.501360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20ede70-aaba-4674-9906-a5726cc61acf · outbound

This paper cites Agent-C: Enforcing temporal constraints for LLM agents,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Agent-C: Enforcing temporal constraints for LLM agents,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.638883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b33ba695-d87d-4f58-8ec6-4beeaca55500 · outbound

This paper cites AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.767669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6304b3c-d15d-43c0-a168-41fb48666d2f · outbound

This paper cites A-MemGuard: A proactive defense framework against memory injection attacks on LLM agents,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI A-MemGuard: A proactive defense framework against memory injection attacks on LLM agents,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:20.931588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41ded9ec-28dc-4a10-b592-4c97e2f539bc · outbound

This paper cites Confidential LLM inference: Performance and cost,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Confidential LLM inference: Performance and cost,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:21.037533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47bd726-fcca-4de7-ad74-7b4aab047f23 · outbound

This paper cites Geometric dynamics of agentic loops,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI Geometric dynamics of agentic loops,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:21.172287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94fe26af-d272-418c-8955-6719cc22b742 · outbound

This paper cites PAL*M: Property Attestation for Large Generative Models.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI PAL*M: Property Attestation for Large Generative Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:21.391311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e2331cb-8506-4706-b13c-4045654ab88e · outbound

This paper cites MemTrust: A zero-trust architecture for unified AI memory system,.

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI MemTrust: A zero-trust architecture for unified AI memory system,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T15:05:21.556705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.