Paper Citation Record · LEDGER

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents

As of 11 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2606.27944.

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

pith.paper-citation-record.v1
2606.27944 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T02:04:51.936838Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

38 of 38 outbound references displayed

verified exact13
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ac2d27c2-fee7-41bf-90e5-9b6beaa128ca · outbound

This paper cites Agentharm: A benchmark for measuring harmfulness of llm agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Agentharm: A benchmark for measuring harmfulness of llm agents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a6e93c-4662-4cec-986c-fdee38abdce5 · outbound

This paper cites Claude Sonnet 4.5 System Card.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Claude Sonnet 4.5 System Card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83eb23b0-e9cd-411c-87b5-4f81b52d5739 · outbound

This paper cites Qwen3-VL Technical Report.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Qwen3-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.695552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dda99591-93a4-46ed-ad6d-6e6dd01feed3 · outbound

This paper cites Language models are homer simpson! safety re-alignment of fine-tuned language models through task arithmetic.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Language models are homer simpson! safety re-alignment of fine-tuned language models through task arithmetic

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e01c5d63-bb70-41bb-842f-01c986a79c10 · outbound

This paper cites Vpi-bench: Visual prompt injection attacks for computer-use agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Vpi-bench: Visual prompt injection attacks for computer-use agents

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:25:57.693283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 196e798e-a416-4c22-8bb1-8a39de07d9a2 · outbound

This paper cites GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:25:57.694832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d78e554c-8ac2-4635-87a8-bd78ede18974 · outbound

This paper cites SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d39ce0c8-b3c6-4319-9d78-c8a4298cab6b · outbound

This paper cites Evaluating the robustness of multimodal agents against active environmental injection attacks.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Evaluating the robustness of multimodal agents against active environmental injection attacks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b26a8dea-c7e5-4079-9306-95de3fe8ce03 · outbound

This paper cites Seeclick: Harnessing gui grounding for advanced visual gui agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Seeclick: Harnessing gui grounding for advanced visual gui agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1ecf10-cfda-4d3b-b0ee-5ef6a533cebf · outbound

This paper cites Deepseek-v3.2: Pushing the frontier of open large language models, 2025.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Deepseek-v3.2: Pushing the frontier of open large language models, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d932cf50-de5e-47c8-b8c1-d19c66cb33c7 · outbound

This paper cites Gemini 3.1 Pro: Announcing our latest Gemini AI model.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Gemini 3.1 Pro: Announcing our latest Gemini AI model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a76018a-bc0e-4307-b8d8-486495d41354 · outbound

This paper cites Cogagent: A visual language model for gui agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Cogagent: A visual language model for gui agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9292bede-a0dc-4263-a9d0-45676c946714 · outbound

This paper cites Mvisu-bench: Benchmarking mobile agents for real-world tasks by multi-app, vague, interactive, single-app and unethical instructions.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Mvisu-bench: Benchmarking mobile agents for real-world tasks by multi-app, vague, interactive, single-app and unethical instructions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d71aae62-0ce6-4569-8027-39cf66391658 · outbound

This paper cites Mobileworld: Benchmarking autonomous mobile agents in agent-user interactive, and mcp-augmented environments.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Mobileworld: Benchmarking autonomous mobile agents in agent-user interactive, and mcp-augmented environments

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:25:57.686820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ce22178-bea8-495c-b0e6-36d4a846f34b · outbound

This paper cites Os-harm: A benchmark for measuring safety of computer use agents.Advances in Neural Information Processing Systems, 38, 2026.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Os-harm: A benchmark for measuring safety of computer use agents.Advances in Neural Information Processing Systems, 38, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b23a7ac-eaa5-4974-8c48-6fabcfb08b39 · outbound

This paper cites Mobilesafety- bench: Evaluating safety of autonomous agents in mobile device control.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Mobilesafety- bench: Evaluating safety of autonomous agents in mobile device control

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f74f5399-fa55-4c79-84b4-80fac88627d6 · outbound

This paper cites SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:25:57.684093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 868a0bfc-d8ab-40af-a428-2b1fd6f87e05 · outbound

This paper cites an unresolved cited work.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Unresolved cited work

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-29T05:33:10.637896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 69c53847-a711-4aa8-80ec-ba29dc84d92b · outbound

This paper cites AutoGLM: Autonomous Foundation Agents for GUIs.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents AutoGLM: Autonomous Foundation Agents for GUIs

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T18:25:57.678199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0db984f9-4ba4-4dca-a529-d08407179507 · outbound

This paper cites Guiodyssey: A comprehensive dataset for cross- app gui navigation on mobile devices.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Guiodyssey: A comprehensive dataset for cross- app gui navigation on mobile devices

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0d65b1-ea22-4e5b-88f5-6b0fde01b8d5 · outbound

This paper cites Efficient large-scale language model training on gpu clusters using megatron-lm.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Efficient large-scale language model training on gpu clusters using megatron-lm

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9152caa6-0f71-4e20-bb54-f5cc3ee70808 · outbound

This paper cites GPT-5.4Model.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents GPT-5.4Model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97cdef5e-1b06-480a-b839-831edd7e80cd · outbound

This paper cites an unresolved cited work.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26abcd04-9bd9-43c8-8cb0-a1ee1da2d3ea · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.681401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7a984a82-cab9-450d-941d-0d87ce7dce6d · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Qwen3.5: Towards native multimodal agents, February 2026

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60163094-3e13-43a3-8c34-5ad3e2182b3b · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.685809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dbac41ec-f270-4286-be99-aec53cf7c28f · outbound

This paper cites Emotion Concepts and their Function in a Large Language Model.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Emotion Concepts and their Function in a Large Language Model

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.688134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 355d80cf-d960-4ce8-ac35-084d4e64a24a · outbound

This paper cites OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-28T02:22:24.218945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e41e5933-2ef2-4250-891f-a204902a06e9 · outbound

This paper cites Multi-source templates learning for real-time aerial tracking.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Multi-source templates learning for real-time aerial tracking

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e2e711-f700-48b2-b181-e44587a7b26b · outbound

This paper cites Chattracker: Enhancing visual tracking performance via chatting with multi- modal large language model.Advances in Neural Information Processing Systems, 37:39303–39324, 2024.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Chattracker: Enhancing visual tracking performance via chatting with multi- modal large language model.Advances in Neural Information Processing Systems, 37:39303–39324, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e60535a-d848-4c02-8b21-1114e26b6ae0 · outbound

This paper cites Smartsight: Mitigating hallucination in video-llms without compromising video understanding via temporal attention collapse.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Smartsight: Mitigating hallucination in video-llms without compromising video understanding via temporal attention collapse

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3871f45b-5878-41e1-9046-8f5b856f8e8e · outbound

This paper cites Doubao-Seed-2.0-Pro.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Doubao-Seed-2.0-Pro

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e9be98-84f8-4984-89c9-b015c397ac92 · outbound

This paper cites Mobile-agent-v3.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Mobile-agent-v3

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:25:57.683324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1289ed92-642e-4fd4-9200-409f74ef80cc · outbound

This paper cites Lasm: Layer-wise scaling mechanism for defending pop-up attack on gui agents.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Lasm: Layer-wise scaling mechanism for defending pop-up attack on gui agents

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83eba11-7211-4a8e-824d-7f7805889ae9 · outbound

This paper cites Mobile-Agent-v3: Fundamental Agents for GUI Automation.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Mobile-Agent-v3: Fundamental Agents for GUI Automation

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.666753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9fbfcdad-1da6-4a25-bcd4-af94fc8b82e3 · outbound

This paper cites Naturalreasoning: Reasoning in the wild with 2.8 m challenging questions.Advances in Neural Information Processing Systems, 38, 2026.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Naturalreasoning: Reasoning in the wild with 2.8 m challenging questions.Advances in Neural Information Processing Systems, 38, 2026

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea7710d-9427-4011-9b4d-91144cd44c2f · outbound

This paper cites Chattracker: Enhancing visual tracking via llm-driven iterative description refinement.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Chattracker: Enhancing visual tracking via llm-driven iterative description refinement.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-29T02:04:51.936838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96b1a98-5d70-4779-a6a1-7abf5db9ce23 · outbound

This paper cites Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization.

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-07-01T18:25:57.669351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.