BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart

In one sentence

A computational atlas that represents 81 bioartworks along 13 interpretive axes and clusters the field by conceptual similarity rather than medium or chronology.

Abstract

Bioart brings living material into artistic practice, where a single work can be at once an aesthetic object, a scientific instrument, and an ethical provocation. Traditional categories sort such works along one axis at a time, which flattens the very hybridity that defines the field and leaves curators no way to compare works across many dimensions together. I introduce BioArtlas, a computational atlas that represents each bioartwork along many curated dimensions at once and organizes the field by conceptual similarity rather than by medium or chronology. My method embeds the keywords of all 81 works on each of thirteen interpretive axes, groups related concepts into a shared codebook that tames inconsistent terminology, and then searches systematically for a clustering that is both statistically clean and interpretable. Among the methods that place every work on the map, agglomerative clustering separates the field far more cleanly than the usual k-means baseline (silhouette 0.664 versus 0.483), whereas density-based methods reach higher scores only by discarding most of the corpus as noise. By separating rigorous analysis from public storytelling, BioArtlas turns the tangled complexity of bioart into a navigable landscape, openly available as an interactive interface (https://www.bioartlas.com) and dataset (https://github.com/joonhyungbae/BioArtlas).

Source: arXiv:2511.19162

Key facts

• 81 bioartworks × 13 interpretive axes; shared concept codebook
• Agglomerative clustering silhouette 0.664 vs. k-means 0.483 (among methods that keep every work)
• Open interactive interface (bioartlas.com) and dataset (GitHub)
• NeurIPS 2025 Creative AI Track

When this paper is relevant

• You classify or curate bioart / art–science works
• You map an art collection with multi-dimensional embeddings and clustering (digital art history, cultural analytics)
• You need to reconcile inconsistent keyword vocabularies with a shared codebook
• You balance statistical cluster quality against interpretability
• You want an example separating rigorous analysis from a public-facing storytelling interface

Cite

Joonhyung Bae (2025). BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart. Proc. 39th Annual Conference on Neural Information Processing Systems Creative AI Track, San Diego, CA, USA, Dec. 2-7, 2025. https://arxiv.org/abs/2511.19162

@inproceedings{Bae2025bioartlas,
  title = {BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart},
  author = {Joonhyung Bae},
  booktitle = {Proc. 39th Annual Conference on Neural Information Processing Systems Creative AI Track, San Diego, CA, USA, Dec. 2-7, 2025},
  year = {2025},
  eprint = {2511.19162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.19162}
}

Machine-readable copy: /papers/bioartlas-2025.md