Paper Citation Record · LEDGER

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

As of 13 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2605.07630.

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

pith.paper-citation-record.v1
2605.07630 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T02:00:17.765986Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

16 of 16 outbound references displayed

verified exact10
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier2
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ce3c76f2-9ee6-4060-9e74-e211edd11f7d · outbound

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

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Agentharm: A benchmark for measuring harmfulness of llm agents

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:46:27.426460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation abf75e8b-cc76-422f-bdc3-592bbf827a98 · outbound

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

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.770633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ad6516a5-bed4-4210-b651-10f98571fd45 · outbound

This paper cites AutoGLM: Autonomous Foundation Agents for GUIs.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents AutoGLM: Autonomous Foundation Agents for GUIs

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T04:00:56.793948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 377dfc56-2591-42af-8622-822a491aaf02 · outbound

This paper cites Mind the Gap: Action Rebinding Attacks against Android GUI Agents.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Mind the Gap: Action Rebinding Attacks against Android GUI Agents

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-16T02:22:32.277203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c7fde410-27de-46a1-ab6e-21b3bf5b8e4e · outbound

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

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.786560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2a4d5afe-d468-4959-b21a-20f23f214a92 · outbound

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

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T12:06:13.928391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 37bb027b-27af-44a9-836e-f985a2854440 · outbound

This paper cites Towards trustworthy gui agents: A survey.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Towards trustworthy gui agents: A survey

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.757685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1f19ccb3-0b86-49bb-9aaf-b658398ff782 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Gemini: A Family of Highly Capable Multimodal Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-11T04:00:56.726372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 23a95f3a-a187-40aa-902d-3ce753d5764a · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Gemini: A Family of Highly Capable Multimodal Models

Reference 10

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T02:00:51.755223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b7a65a44-4fed-4cf5-8098-243b4f69e5b4 · outbound

This paper cites Vijayvargiya, A.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Vijayvargiya, A

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T04:00:56.777244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5bb2d03f-7f1a-4ceb-8250-7c1d7f5d1e78 · outbound

This paper cites GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:55:13.551984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 17b374d4-b844-4cb5-acd9-0db7011ae089 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:46:27.424667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f8130c6f-be8a-44b2-9160-cfc8570ab04e · outbound

This paper cites Mobile-agent-v3.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Mobile-agent-v3

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.752873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2bd2be58-e9cb-47bf-9b50-bbe51e238bf6 · outbound

This paper cites RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.737761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1189d69f-3a2e-4472-9e12-159061c6fc0c · outbound

This paper cites Mai-ui technical report: Real-world centric foundation gui agents.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Mai-ui technical report: Real-world centric foundation gui agents

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:56.721714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ffc256a1-ecda-4e5f-bab2-d7aa90a6562d · outbound

This paper cites Benchmarks such as MobileSafetyBench Lee et al.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Benchmarks such as MobileSafetyBench Lee et al

Reference 17

Resolution: malformed identifier; raw_fallback, observed 2026-05-14T14:46:27.428484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.