Problem
Research questions and friction points this paper is trying to address.
Conversational Visualization
Provenance
Stateless Systems
Scientific Workflows
Branching History
RaivenTracks: Branching Provenance for Conversational Visualization Workflows
🤖 AI Summary
This study addresses the limitations of statelessness, poor traceability, and lack of branching exploration in LLM-driven visualization systems by proposing RaivenTracks. This method introduces a novel branchable session history based on DSL specifications and constructs a dual-layer state management architecture. By treating validated visualization specifications as branchable checkpoints, the framework enables state recovery from conversational records to verifiable artifacts with fine-grained version control. A pilot study demonstrates that users can effectively leverage the version tree for workflow branching and state restoration. These findings validate the framework’s effectiveness in supporting traceable conversational visualization exploration and clarify directions for future design research.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Branching Provenance
Conversational Visualization
State Management Architecture
DSL-mediated Pipeline
Scientist-in-the-loop
🔎 Similar Papers
No similar papers found.
