Saved in:
Bibliographic Details
Main Authors: Chen, Eric, Alves-Oliveira, Patricia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.17030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918344876097536
author Chen, Eric
Alves-Oliveira, Patricia
author_facet Chen, Eric
Alves-Oliveira, Patricia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17030
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings
Chen, Eric
Alves-Oliveira, Patricia
Computer Vision and Pattern Recognition
Robotics
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.
title Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2602.17030