Paper Citation Record · LEDGER

Agent-Computer Observation Interfaces Enable Dynamic Computer Use

As of 13 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2606.29472.

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

pith.paper-citation-record.v1
2606.29472 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T06:59:20.295818Z

measured 28 of 28 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T08:40:18.802325Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact23
verified fuzzy0
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fafe9e8c-346f-4e40-80f0-b4fccdaf35e1 · outbound

This paper cites Surfer 2: The Next Generation of Cross-Platform Computer Use Agents.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Surfer 2: The Next Generation of Cross-Platform Computer Use Agents

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.207564Z

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 e76aec3b-0ff4-4e92-aa77-34ff97391f58 · outbound

This paper cites Fara-7b: An efficient agentic model for computer use.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Fara-7b: An efficient agentic model for computer use

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.240823Z

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 a37563a1-7ac9-4f71-8dd7-60dab032627b · outbound

This paper cites GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.292013Z

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 bc3c3b4b-a24a-4833-ac48-ba572f871c6f · outbound

This paper cites CUA-Suite: 55 hours of real computer-use recordings for agent benchmarking.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use CUA-Suite: 55 hours of real computer-use recordings for agent benchmarking

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.289181Z

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 e4cb1efb-2938-4492-97fc-32951f249075 · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.271928Z

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 faf685c3-b637-4d5e-af29-40189bfb5659 · outbound

This paper cites VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.275140Z

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 81b25636-f242-4594-9589-f514260a601d · outbound

This paper cites ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.281734Z

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 90ca9dee-c60b-4540-b6bf-5b25301cf44c · outbound

This paper cites Microsoft.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Microsoft

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-30T06:59:20.295818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ab089b-df95-4fc4-94cc-ad7637006646 · outbound

This paper cites Towards trustworthy agentic IoEV: AI agents for explainable cy- berthreat mitigation and state analytics.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Towards trustworthy agentic IoEV: AI agents for explainable cy- berthreat mitigation and state analytics

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:04:21.285260Z

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 dc3c6d0c-8ff1-470e-a201-2abe63c3863e · outbound

This paper cites Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.262807Z

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 987d17ef-dc00-4771-8dc0-ae679ffff429 · outbound

This paper cites Qwen3-VL Technical Report.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Qwen3-VL Technical Report

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.260942Z

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 b180ca19-ffa7-4399-be24-72d4b84c2609 · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Robust Speech Recognition via Large-Scale Weak Supervision

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.251162Z

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 b4c9233d-e46f-4ea6-ad4b-79a0ddb332aa · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Learning Transferable Visual Models From Natural Language Supervision

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.244606Z

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 3cc8b0ba-134c-4aad-ab77-09449ba259d2 · outbound

This paper cites Coact-1: Computer-using agents with coding as actions.arXiv preprint arXiv:2508.03923, 2025a.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Coact-1: Computer-using agents with coding as actions.arXiv preprint arXiv:2508.03923, 2025a

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.254559Z

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 8667bad7-9aa9-4bce-ba1e-b0844f27b9c9 · outbound

This paper cites Cradle: Empowering Foundation Agents Towards General Computer Control.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Cradle: Empowering Foundation Agents Towards General Computer Control

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:04:21.247649Z

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 c6a83721-15f9-4a6d-bcd5-146ea0611902 · outbound

This paper cites Adaptive Keyframe Sampling for Long Video Understanding.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Adaptive Keyframe Sampling for Long Video Understanding

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.259945Z

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 4a0bb389-216f-4111-b4a6-2e1f9a323639 · outbound

This paper cites UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.282341Z

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 90aa53f0-1a45-4f9c-988b-3726014708b1 · outbound

This paper cites OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.271037Z

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 aff560cd-5b19-4293-aaf7-abbf6c49236f · outbound

This paper cites StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.286176Z

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 83fef97e-38e4-45a3-a718-b77cfe61aae1 · outbound

This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.226681Z

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 05e64b20-9112-4211-ba79-c3969358df7b · outbound

This paper cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.229587Z

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 ba7302b0-2dc4-424b-ac3c-a2f8d2a60c89 · outbound

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

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Mobile-Agent-v3: Fundamental Agents for GUI Automation

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.210011Z

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 ded88bb3-7268-4256-8d73-42b080b7c787 · outbound

This paper cites VideoGameBench: Can Vision-Language Models complete popular video games?.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use VideoGameBench: Can Vision-Language Models complete popular video games?

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.222716Z

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 5edf0bcf-564c-4d65-9551-ccf929071349 · outbound

This paper cites A Simple LLM Framework for Long-Range Video Question-Answering.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use A Simple LLM Framework for Long-Range Video Question-Answering

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.233670Z

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 b51c57cc-4ce4-4c25-8ab1-c7db330ae8de · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:04:21.287941Z

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 c9dbe76f-b26c-4668-9b61-2ec3dea2696c · outbound

This paper cites Apollo: An Exploration of Video Understanding in Large Multimodal Models.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use Apollo: An Exploration of Video Understanding in Large Multimodal Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:04:21.211164Z

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 366e1f75-191d-4ccc-9b0d-7996eabf5c92 · outbound

This paper cites What is the new launch date?.

Agent-Computer Observation Interfaces Enable Dynamic Computer Use What is the new launch date?

Reference 27

Resolution: malformed identifier; no resolver link, observed 2026-06-30T06:59:20.295818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bfa30dfe-3e2a-4591-810e-d581c8ffeed7 · inbound

Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees cites this paper.

Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees Agent-Computer Observation Interfaces Enable Dynamic Computer Use

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T08:40:18.802325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.