AI 中文总结
RaivenTracks是Raiven可视化管道的工作流感知扩展，通过两级状态管理架构实现可分支的版本树与细粒度撤销/重做，试点研究显示其支持可视化工作流的分支与恢复，为AI驱动科学工作流的溯源监督提供了新方向。
AI 中文摘要
随着AI智能体越来越多地参与科学工作流，科学家们正从直接创作转向监督、检查和引导。由大语言模型（LLM）驱动的可视化系统是实现这种角色转换的有前景的接口，但它们大多是无状态的，迫使用户在多次优化中重建上下文，且几乎不支持回顾先前的决策或探索替代方案。我们提出了RaivenTracks，它是Raiven DSL介导的可视化管道的工作流感知扩展，将经过验证的可视化规范视为持久、可分支的检查点。由于每个检查点都是可验证的Raiven DSL规范而非对话记录，恢复节点会重新编译已知工件，而非重新解释先前上下文。RaivenTracks提供了一个两级状态管理架构，将持久、可分支的版本树与运行时可视化设置的细粒度撤销/重做栈配对，适用于信息可视化（InfoVis）和科学可视化（SciVis）后端。我们与三位可视化研究人员开展的初步试点研究显示出早期潜力：所有参与者均采用版本树进行分支和恢复，同时揭示了树导航、节点标记和可扩展性方面的设计方向，这些方向将为计划开展的、与无版本历史的Raiven进行的受控比较提供参考。我们将可分支的对话式可视化历史视为为未来“科学家在回路中”监督AI驱动的科学工作流提供溯源支持的一步。
英文摘要
As AI agents increasingly participate in scientific workflows, scientists are shifting from direct authorship toward oversight, inspection, and steering. LLM-driven visualization systems are a promising interface for this hand-off, yet they remain largely stateless, forcing users to reconstruct context across refinements and offering little support for revisiting prior decisions or exploring alternatives. We present RaivenTracks, a workflow-aware extension of the Raiven DSL-mediated visualization pipeline that treats validated visualization specifications as persistent, branchable checkpoints. Because each checkpoint is a verifiable RaivenDSL specification rather than a dialogue transcript, restoring a node recompiles a known artifact rather than re-interpreting prior context. RaivenTracks contributes a two-level state management architecture that pairs a persistent, branchable version tree with a fine-grained undo/redo stack over runtime visualization settings, across both InfoVis and SciVis backends. A formative pilot study with three visualization researchers shows early promise, with all participants adopting the version tree for branching and recovery, and surfaces design directions for tree navigation, node labeling, and scalability that inform a planned controlled comparison against Raiven without version history. We frame branchable conversational visualization history as a step toward provenance support for future scientist-in-the-loop oversight of AI-driven scientific workflows.
Comments*Ella Hugie and Alexandra Irger are co-first authors
