基于补丁的空间作者归属在人类-机器人协作绘画中
Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings
AI总结：
本文提出了一种基于补丁的空间作者归属方法，用于人类-机器人协作绘画，通过实验验证在数据稀缺情况下有效区分混合作者身份。
摘要：
随着代理AI在创造性生产中的参与度日益增加，记录作者身份对于艺术家、收藏家和法律情境变得至关重要。我们提出了一种基于补丁的框架，用于在人类-机器人协作绘画实践中进行空间作者归属，通过一个对人类艺术家和一个机器人系统在15幅抽象绘画中的法医案例研究来演示。使用商用平板扫描仪和留一绘画法交叉验证，该方法在补丁层面达到88.8%的准确率（通过多数投票在绘画层面达到86.7%），优于基于纹理和预训练特征的基线（68.0%-84.7%）。对于协作作品，其中真实情况本质上是模糊的，我们使用条件香农熵来量化风格重叠；手动标注的混合区域表现出比纯绘画高64%的不确定性（p=0.003），表明模型检测的是混合作者身份而非分类失败。训练好的模型专门针对这对人类-机器人系统，但为数据稀缺的人类-人工智能创造性工作流程提供了方法论基础，未来有潜力将作者归属扩展到任何人类-机器人协作绘画。
英文摘要：
As agentic AI becomes increasingly involved in creative production, documenting authorship has become critical for artists, collectors, and legal contexts. We present a patch-based framework for spatial authorship attribution within human-robot collaborative painting practice, demonstrated through a forensic case study of one human artist and one robotic system across 15 abstract paintings. Using commodity flatbed scanners and leave-one-painting-out cross-validation, the approach achieves 88.8% patch-level accuracy (86.7% painting-level via majority vote), outperforming texture-based and pretrained-feature baselines (68.0%-84.7%). For collaborative artworks, where ground truth is inherently ambiguous, we use conditional Shannon entropy to quantify stylistic overlap; manually annotated hybrid regions exhibit 64% higher uncertainty than pure paintings (p=0.003), suggesting the model detects mixed authorship rather than classification failure. The trained model is specific to this human-robot pair but provides a methodological grounding for sample-efficient attribution in data-scarce human-AI creative workflows that, in the future, has the potential to extend authorship attribution to any human-robot collaborative painting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
