Artifact–Transform Workflow Language (ATWL)

Visual analytics (VA) workflows are inherently complex, involving data transformation, feature engineering, visual representation, and human interpretation. While these processes are central to research and practice, they are typically described in unstructured prose, hindering systematic comparison, reuse of proven analytical strategies, and training of novice practitioners. We present Artifact--Transform Workflow Language (ATWL), a domain-agnostic, declarative language designed to formally represent VA workflows by capturing their structure and underlying analytical intent. ATWL is built upon a modular ontology of eight artifact types (entities, features, arrangements, visualisations, patterns, models, knowledge, and specifications) and transforms characterised by standardised intents (e.g., define-unit, characterise, contextualise, abstract). To demonstrate that the formalisation effort can be moderate and may not impede adoption, we show that workflows can be extracted from research papers through supervised interaction with LLM agents, reducing the human role to review and refinement. Using this process, we constructed a library of seventeen ATWL workflows extracted from published VA papers. Cross-workflow analysis within this library reveals structural regularities---a recurrent meta-structure, recurring structural motifs, reusable methodological building blocks, diverse iterative strategies, and cross-domain equivalences---that remain invisible when comparing the original prose descriptions. This analysis illustrates the analytical affordances of formal representation. We further evaluate practical utility through a controlled experiment in which the same LLM addressed two analytical problems with the library supplied either as the original research papers or as ATWL representations. Both forms enabled useful recommendations, but the formal representation systematically added explicit iteration structure, typed data flow, fragment-level adaptation provenance, and compactness that supports scaling beyond what prose libraries can fit in an LLM's context. By providing a common vocabulary for analytical structure and intent, ATWL enables a transition from narrative descriptions to formally represented, comparable, and reusable analytical knowledge.