Paper Citation Record · LEDGER

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

As of 8 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2607.22798.

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

pith.paper-citation-record.v1
2607.22798 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T05:06:47.520046Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

17 of 17 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1da55cf4-60d8-4eab-90a8-f3a010397709 · outbound

This paper cites Let’s think in two steps: Mitigating agreement bias in MLLMs with self-grounded verification.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Let’s think in two steps: Mitigating agreement bias in MLLMs with self-grounded verification

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.472442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5765e9a-e319-40a5-a089-7607a6bcb9d6 · outbound

This paper cites ComputerRL: Scaling end-to-end online reinforcement learning for computer use agents.arXiv preprint arXiv:2508.14040,.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents ComputerRL: Scaling end-to-end online reinforcement learning for computer use agents.arXiv preprint arXiv:2508.14040,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.485026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41fc920-f4e3-4c7c-9ec5-5c4bcfc611e0 · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Self-Refine: Iterative Refinement with Self-Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.487678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01dd1e66-0ff5-4f3b-bbdc-70d349390e20 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.494392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c888b112-510b-46c5-9c74-174e0c8bc2ba · outbound

This paper cites CoAct-1: Computer-using multi-agent system with coding actions.arXiv preprint arXiv:2508.03923,.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents CoAct-1: Computer-using multi-agent system with coding actions.arXiv preprint arXiv:2508.03923,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.497322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d79a931c-651a-4194-b648-6afa17d10fc9 · outbound

This paper cites Executable Code Actions Elicit Better LLM Agents.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Executable Code Actions Elicit Better LLM Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.499969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd7680c-d1df-45a9-b270-354c9f359874 · outbound

This paper cites OpenComputer: Verifiable Software Worlds for Computer-Use Agents.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents OpenComputer: Verifiable Software Worlds for Computer-Use Agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.503100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42e5d86a-ecea-4b51-8e88-209b45cab508 · outbound

This paper cites Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.506046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54bcb467-5f8b-4bee-8936-51e2332a4f7a · outbound

This paper cites MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.508954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7936554d-365a-4803-b7f9-0fd598422158 · outbound

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

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.511752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb56d48-2f68-4e86-b587-1122096316b3 · outbound

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

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.514595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd933ea-5853-4989-b6fa-7868d4ec9af6 · outbound

This paper cites GTA1: GUI Test-time Scaling Agent.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents GTA1: GUI Test-time Scaling Agent

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.517167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c96a851-70eb-4a7c-85ba-db5f902a0082 · outbound

This paper cites UFO2: The Desktop AgentOS.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents UFO2: The Desktop AgentOS

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.520046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b5fdf7-9fb7-485b-809e-6b9a6b76577b · outbound

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

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.491105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95bb43f8-bdae-42ff-af28-022b11e60ba6 · outbound

This paper cites Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.479150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f0b283-3b2c-4d37-8922-5c1dac8ee71c · outbound

This paper cites Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.475945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72c1c95-3088-4c15-9009-f379500b6b5e · outbound

This paper cites Mobile- World: Benchmarking autonomous mobile agents in agent-user interactive and mcp-augmented environments.arXiv preprint arXiv:2512.19432,.

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Mobile- World: Benchmarking autonomous mobile agents in agent-user interactive and mcp-augmented environments.arXiv preprint arXiv:2512.19432,

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T05:06:47.482334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.