Cite torchtsetlin¶
If you use torchtsetlin in your work, please cite the technical report below, together with
the Tsetlin machine papers whose algorithms you rely on. Each concept page names the paper
behind every option.
-
Technical report (5 pages): the document to cite
torchtsetlin: Fast, Interpretable Tsetlin Machines for the PyTorch Ecosystem. Software version 0.6.1.
-
White paper (long form)
The full design, the batched feedback algorithm, benchmarks, the literature catalog and limitations.
BibTeX¶
@techreport{thambawita2026torchtsetlin,
author = {Thambawita, Vajira},
title = {torchtsetlin: Fast, Interpretable Tsetlin Machines for the PyTorch Ecosystem},
institution = {Simula Metropolitan Center for Digital Engineering},
type = {Technical report},
year = {2026},
note = {Software version 0.6.1},
url = {https://github.com/vlbthambawita/torchtsetlin}
}
Plain text¶
V. Thambawita. torchtsetlin: Fast, Interpretable Tsetlin Machines for the PyTorch Ecosystem. Technical report, Simula Metropolitan Center for Digital Engineering, 2026. Software version 0.6.1. https://github.com/vlbthambawita/torchtsetlin
The repository's CITATION.cff carries the same entry, which is what GitHub's
Cite this repository button shows.
Building the PDFs¶
Both documents are LaTeX sources in whitepaper/, sharing one theme, the figures and data
files: make builds the white paper (main.pdf), and make summary builds the report
(summary.pdf). Their benchmark charts read the repository's benchmark records. Their
literature counts and charts come from the literature database, via
python whitepaper/data/regen_literature.py. The documentation build copies both committed
PDFs into the site.