A few vectors for a mixed folder: a pre-registered measurement of pooled directory embeddings
A folder's metadata holds a few kilobytes, and the cheapest vector to store there is the mean of its files' embeddings. Where a folder mixes images and texts, the mean loses its minority modality, and a few representatives per modality recover it.
- Status
- Preprint, not peer reviewed
- Published
- on Zenodo, version 1
- Code and data
- github.com/ali-basheer/dirvec-study
- Licence
- Paper CC BY 4.0, code MIT
Cite as
Basheer, A. (2026). A few vectors for a mixed folder: a pre-registered measurement of pooled directory embeddings (Version 1) [Preprint]. Zenodo. https://doi.org/10.5281/zenodo.23178122
@misc{basheer2026fewvectors,
author = {Basheer, Ali},
title = {A few vectors for a mixed folder: a pre-registered measurement of pooled directory embeddings},
year = {2026},
month = oct,
date = {2026-10-06},
publisher = {Zenodo},
version = {1},
doi = {10.5281/zenodo.23178122},
url = {https://doi.org/10.5281/zenodo.23178122},
note = {Preprint, not peer reviewed. Code and data: https://github.com/ali-basheer/dirvec-study}
}