ArtMine: Discovering and Formalizing Artistic Processes

2026-07-09

AI Summary

This work addresses the prevailing limitation in current AI systems, which predominantly focus on generating final artworks while neglecting the modeling of artistic creation processes—processes often preserved only as fragmented historical records and thus resistant to computational formalization. To bridge this gap, the authors propose ArtMine, a novel framework that, for the first time, integrates heterogeneous historical evidence through Peircean abductive reasoning and compositional graph modeling to construct structured, interpretable, and auditable representations of creative workflows. By coupling this representation with self-reflective optimization and generative prompt engineering, the framework transforms these reconstructions into an optimizable generative mechanism. In open-domain experiments spanning multiple artists and styles, ArtMine successfully produces coherent and traceable creative processes, thereby advancing a new paradigm of process-centered human-AI collaborative creation.

Abstract

Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model distributions over finished artifacts rather than the creative processes underlying their creation. In practice, artistic workflows are only partially documented through fragmented sources such as archival records, preparatory studies, correspondence, etc., making process-level understanding difficult to formalize computationally. In this work, we introduce ArtMine, a framework for discovering and formalizing artistic processes from heterogeneous historical evidence. Our approach synthesizes heterogeneous artwork evidence into a structured repository, from which a Peircean abductive agent infers evidence-grounded production steps. These steps are converted into a compositional graph and rendering prompt, then optimized through self-reflection over deviations between the generated and reference artworks. We provide a preliminary proof-of-concept case study using open-domain historical sources across multiple artists and artistic movements, demonstrating that fragmented documentary evidence can support coherent, interpretable, and auditable representations of artistic workflows. By modeling creative processes rather than only final artifacts, our work moves toward process-centred human-AI co-creativity systems that can support artistic interpretation, creative education, reflective collaboration, and computational studies of cultural production.

Problem

• artistic processes
• creative workflows
• historical evidence
• process formalization
• computational art understanding

Innovation

• artistic process modeling
• abductive reasoning
• heterogeneous evidence integration
• self-reflective optimization
• process-centered AI