Paper Citation Record · LEDGER

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?

As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2606.23189.

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

pith.paper-citation-record.v1
2606.23189 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T08:32:37.612389Z

measured 15 of 15 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

15 of 15 outbound references displayed

verified exact1
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7d65dff4-b31c-4a67-9f7c-109dfdabdfbd · outbound

This paper cites Expert Certification.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Expert Certification

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd007e1d-3622-409f-88c8-6b1c7f0aa627 · outbound

This paper cites ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:49:45.651745Z

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 918f2aca-4aa1-4a96-97df-870da3c71c76 · outbound

This paper cites Cimemories: A compositional benchmark for contextual integrity of persistent memory in llms.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Cimemories: A compositional benchmark for contextual integrity of persistent memory in llms

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T10:49:45.654733Z

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 35ef1d1e-a9cd-4971-ac16-d19c9edcd087 · outbound

This paper cites arXiv preprint arXiv:2511.20766 , year =.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? arXiv preprint arXiv:2511.20766 , year =

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:49:45.654869Z

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 2eb4f98f-ea6a-4a90-bac6-5050bf85cc5f · outbound

This paper cites scenario_id.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? scenario_id

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ce2ac2-5ed1-49bc-ba98-64dbba9a2d45 · outbound

This paper cites an unresolved cited work.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f010aa-5e42-4b70-b932-81cad544084e · outbound

This paper cites Draft a short reply to Nora summarizing what I have going on today, just a natural list of what’s in front of me.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Draft a short reply to Nora summarizing what I have going on today, just a natural list of what’s in front of me

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 262e9fbc-684c-4978-83dd-2614b2e5dda5 · outbound

This paper cites Do not pull content from neighboring rows, threads, files, or events that happen to be on screen but were not asked about.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Do not pull content from neighboring rows, threads, files, or events that happen to be on screen but were not asked about

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5635e48b-7f24-4575-b409-adb0bacec8c1 · outbound

This paper cites If you are uncertain whether an item belongs, omit it.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? If you are uncertain whether an item belongs, omit it

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2c75b5-566d-4851-a189-4f7e492ae216 · outbound

This paper cites an unresolved cited work.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee61b2a-62b9-4184-8663-bf25dd7868d5 · outbound

This paper cites personal.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? personal

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d9c9a5-a07b-4047-943a-08108cecec04 · outbound

This paper cites an unresolved cited work.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cbb3fa0-5cbd-44a0-a2b3-6912b7a5e9ef · outbound

This paper cites an unresolved cited work.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7f25ef-66a5-4ccd-89ac-93be1f8b691f · outbound

This paper cites an unresolved cited work.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d0b214f-751d-4573-ae15-2cd8049d8640 · outbound

This paper cites Complete the task.

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? Complete the task

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-26T08:32:37.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.