Vertov Research

Research

Preprints, the data behind them and the code that produced the numbers. Each study states who funded it and where the company has an interest in the result.

Studies

How GUI Agents Receive Instructions: An Exploratory Mapping of 85 Benchmark Families

Task Specification, Video Demonstrations and Evaluation Methods

Ankur Shrestha, Vertov, United States. 14 November 2026.

How benchmarks for GUI and computer-use agents give the agent its task, and where video and recorded demonstrations fit. Coded with AI assistance; no independent human recoding was performed.

85
benchmark families read in full (147 components)
80 of 81
video-targeted components give the goal as text (64 of 66 in the random comparison group)
9 of 81
video-targeted components include a video or demonstration in the instruction (1 of 66 in the comparison group)

Preprint, released with its data under CC BY 4.0.

Read the study

Screen Recordings, Screencasts and Video in Software Engineering

An Evidence Map of Bug Reporting, Documentation, Training and Collaboration

Ankur Shrestha, Vertov, United States. 14 November 2026.

How research on screen recordings, screencasts and video divides across bug reporting, documentation, training and collaboration, and where the evidence is thin. Coded with AI assistance and reviewed by the author.

198
studies included, from 1382 unique records
19
compare a recording with text, or with text and screenshots
8 of 19
of those favor the recording; 8 are mixed, 1 found no difference, and 2 favor the alternative

Preprint, released with its data under CC BY 4.0.

Read the study

Commands and recent recordings
Actions
Go to
↑ ↓ Select↵ OpenEsc Close