从论文中重构代码：重新实现人机交互（HCI）人工制品
Revibing Code from Papers: Reimplementing HCI Artifacts
AI总结：
本研究利用智能体AI技术直接从HCI研究论文重构交互式软件，提出重构性指标，经UIST论文验证可生成强基线代码，有望改变HCI研究人工制品的生产评估方式。
AI中文摘要：
大多数技术人机交互（HCI）研究项目的软件人工制品不可用，无法获取这些人工制品限制了学术知识生产，难以扩展或复用研究人工制品、在后续工作评估中使用强基线、开展复制或可复现性研究。本研究展示了新型智能体AI技术重构交互式软件的潜力：直接从研究论文重新实现系统。为衡量该方法的成功性，提出了重构性（revibeability）指标。通过重构近期UIST会议的研究论文并访谈原作者，展示了重构系统的可行性及局限性，结果令人鼓舞，多数情况下能生成适用于强基线使用的代码，这可能代表技术HCI社区生产、使用和评估研究人工制品方式的根本性转变。
英文摘要：
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.
