Write a PREreview

Microscopic analysis of the latent space: heuristics for interpretability, authenticity, and bias detection in VAE representations

by Eduardo Pires Hermanson

Posted: August 13, 2025
Server: Zenodo
DOI: 10.5281/zenodo.16827724

A proposal modular heuristic framework (SBS, ABI, CLS) for microscopic analysis of latent spaces in generative models (VAEs / CVAEs). The framework combines ICA-based Uniqueness, entropic Originality and a simulated Stability heuristic to produce interpretable, multi-dimensional scores that characterise representations in the latent manifold. We validate the approach in a controlled synthetic environment and present a case study on a 10k subset of CelebA using a CVAE, showing applications for bias detection, identity-consistency analysis and discovery of high-information outliers. Code, cleaned notebook and selected outputs are provided.

You can write a PREreview of Microscopic analysis of the latent space: heuristics for interpretability, authenticity, and bias detection in VAE representations. A PREreview is a review of a preprint and can vary from a few sentences to a lengthy report, similar to a journal-organized peer-review report.

Before you start

We will ask you to log in with your ORCID iD. If you don’t have an iD, you can create one.