For BOSC 2026, organizers tested bosc-pre-review, an agentic skill that collected evidence against six abstract-review criteria, including project openness, valid open-source licensing, and runnability. Runabilly built and tested projects inside disposable Docker containers. The system supplied evidence and preliminary conclusions, while human reviewers retained all acceptance decisions. Most responding reviewers found the pre-review useful, but preferred checking its conclusions against their own assessment rather than accepting them unquestioningly. The paper is an experience report, so it primarily documents workflow and reviewer perceptions rather than a controlled evaluation of accuracy or efficiency.
No heat snapshots are available in the last 24 hours.