🔬 Deborah.jl

Deborah.jl is a machine-learning–assisted analysis framework for bias-corrected cumulant estimation and multi-ensemble reweighting workflows in lattice QCD.
It provides an end-to-end pipeline spanning supervised-learning–based trace estimation, higher-order cumulant analysis, κ-reweighting, and reproducible research workflows within a unified Julia ecosystem.

Compatibility: Julia 1.12+
➡️ Quick start: explore reproducible example pipelines in sample/.

💻 Installation

import Pkg
Pkg.add("Deborah")

📚 Documentation

The full API reference and user documentation for Deborah.jl is automatically generated using Documenter.jl and hosted online:

👉 https://saintbenjamin.github.io/Deborah.jl/stable/

The stable documentation corresponds to tagged releases (e.g. v1.0.0), while development versions may appear under dev/.

🧩 Package Ecosystem

• Deborah.jl: Deborah.jl is an Estimation tool for Bias-cOrrected Regression Analysis with Heuristics.
• Esther.jl: Esther.jl is a Summary Tool for Higher-order cumulants through Estimation via Regression.
• Miriam.jl: MultI-Ensemble Reweighting & Interpolation Analysis with Miriam.jl
• Sarah.jl: Shared Abstractions and Reusable Auxiliary Hub
• Rebekah.jl: Reporting, Evaluation, and Benchmarking via Explainable Knowledge Aggregation Hub
• Elijah.jl: Expert for Logical Inference and Judgment-based Assistance in Human decisions
• Rahab.jl: Reconnaissance & Analysis for Heuristics Across data Bundles

🧑‍🔬 Citation

If you found this library to be useful in academic work, then please cite:

@misc{Choi:2026zen,
    author       = {Benjamin J. Choi},
    title        = {\href{https://doi.org/10.5281/zenodo.18755146}{saintbenjamin/Deborah.jl: Deborah.jl}},
    month        = feb,
    year         = 2026,
    note         = {If you use this software, please cite it as below.},
    publisher    = {Zenodo},
    version      = {v1.0.3},
    doi          = {10.5281/zenodo.18755146}
}

License

MIT License — see LICENSE for details.