Revibing Code from Papers: Reimplementing HCI Artifacts

2026-08-01

AI Summary

This work addresses the pervasive absence of software artifacts in HCI research, which severely hinders reproducibility, baseline comparisons, and reuse of published results. To tackle this challenge, we propose the first agent-based AI approach capable of automatically reconstructing interactive software systems directly from HCI papers. We introduce “revibeability”—a novel metric for evaluating the fidelity and usability of reconstructed implementations. Our method integrates code generation, UI parsing, and validation through author interviews, successfully reproducing multiple systems originally presented at UIST. The resulting open-source implementations are high-quality, reusable, and establish strong baselines for future research. This advancement not only enhances the reproducibility of HCI studies but also catalyzes a paradigm shift toward more transparent and replicable scholarship in the field.

Abstract

Software artifacts for most technical HCI research projects are unavailable. The lack of access to these imposes limits on academic knowledge production. It is difficult to: extend or reuse research artifacts; use strong baselines in evaluating follow-up work; and perform replication or reproducibility research. In this work, we demonstrate the potential of new agentic AI technologies to revibe interactive software: reimplement systems directly from research papers. To measure the success of the approach, we describe a revibeability metric. By revibing recent research papers from UIST, and interviewing their original authors, we demonstrate the plausibility (and limitations) of revibed system. The results are encouraging. In many cases producing code suitable for strong baseline use. We argue that this may represent a fundamental shift in how we produce, use, and evaluate research artifacts in the technical HCI community.

Problem

• HCI
• software artifacts
• reproducibility
• reimplementation
• research replication

Innovation

• agentic AI
• software reviving
• research reproducibility
• HCI artifacts
• revibeability