发表机构
School of International Public Affairs, Columbia University; Department of Computer Science, Columbia University; Department of Statistics, Columbia University（哥伦比亚大学国际公共事务学院; 哥伦比亚大学计算机科学系; 哥伦比亚大学统计系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ForkSCOPE提出人机协作框架，从分析代码语料库自下而上归纳结构，无需预设分类法，通过交互式查看器突出分叉并生成决策图，以扩展分析评估并避免处理瓶颈。
AI 中文摘要
即使在数据集和研究问题固定的情况下，数据分析也涉及许多合理的决策。理解这些选择如何影响结果在科学上很重要，但仍然具有挑战性。众包和智能体AI可以生成数百个端到端的分析，但仅靠扩大生成规模会造成处理瓶颈和分析的“黑洞”。常见的解决方法是施加一个共享的固定决策分类法，这可能会限制洞察力并低估不确定性。我们提出了ForkSCOPE，一个人机协作框架，它从端到端分析的代码语料库中自下而上地归纳结构，无需在生成之前或之后固定分类法，因此花园的组织和评估可以随语料库扩展。ForkSCOPE通过人机协作流程和证据关联的交互式查看器（用于引导和验证）呈现已绘制的分叉路径花园：它突出显示有机识别的分叉和结构，并生成与现有多重宇宙工具兼容的派生分类法和决策图。
英文摘要
Even with a fixed dataset and research question, data analysis involves many defensible decisions. Understanding how these choices influence the results is scientifically important but remains challenging. Crowdsourcing and agentic AI can generate hundreds of end-to-end analyses, but scaling generation alone can create a processing bottleneck and an analytic ``black hole.'' A common workaround is to impose a shared fixed decision taxonomy, which can limit insight and understate uncertainty. We present ForkSCOPE, a human-AI collaboration framework that induces structure bottom-up from the code corpus of end-to-end analyses, without a taxonomy fixed before or after generation, so the organization and evaluation of the garden can scale with the corpus. ForkSCOPE surfaces the charted garden of forking paths through a human-AI collaboration pipeline and an evidence-linked interactive viewer for steering and verification: it spotlights organically identified forks and structures and produces a derived taxonomy and decision map compatible with existing multiverse tools.
