FastParam Resource Hub

Welcome to the FastParam Resource Hub. Here you’ll find EPTA data, source code, and publications produced by the project..

At a glance: browse the index on the left or scroll down to render any section.

Source Code

Heads up: Following, you can visit the EPTA site where you can download the relevant data and source code, all the things for running your own experiments. They are under CC BY 4.0 and MIT Licence respectively.

FastParam Core Repository

  • Languages: Python (PyTorch), JAX (planned)
  • Licence: MIT (TBC)
  • Visibility: Private (opening soon)

View on GitHub Download ZIP

Publications

This section lists journal & conference submissions, technical diagrams/notes.

Journal & Conference Submissions

  • Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis I: Methodology and implementation
    • Status: In review
    • Type: Journal article

    Abstract Preprint

    Show short note
    Scope: NF-based hierarchical Bayesian inference for PTA analysis; improved statistical robustness & computational efficiency.
  • Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis II: Noise and SGWB inference through parameter decorrelation
    • Status: In review
    • Type: Journal article

    Abstract Preprint

    Show short note
    Scope: Application to pulsar noise modeling and SGWB detection using decorrelated hierarchical parameters.
  • On Bayesian inference in pulsar timing arrays: identifiability and choice of the priors
    • Status: In review
    • Type: Journal article

    Abstract (Coming soon) · Preprint (Coming soon)

    Show short note
    Bayesian inference in pulsar timing arrays - choice of the priors

Diagrams & Technical Notes

  • DL network architecture: I-NESSAI

    Blocks and data flow of the DL model.

    DL network architecture: I-NESSAI

    Visual summaries of the images. Click an image to download the full-resolution version.

  • Training workflow

    Preprocessing, training, and evaluation steps.

    Training workflow

    Visual summaries of the images. Click an image to download the full-resolution version.

Licence & Citation

To support ethical reuse and proper attribution, FastParam provides default licensing and citation templates for datasets and software. Important: if a dataset or repository includes its own LICENSE, citation.txt, or DOI, that local file overrides the defaults below. Always prefer the per-item files when present.

If you adapt the datasets or code, indicate changes and, where practical, link back to this hub so others can find the original materials.

Software — Licence & how to cite

Licence (intended): MIT Licence (to be confirmed in the repository). A copy of the licence will be included as LICENSE in the repo. About MIT.

Recommended software citation (plain text)

FastParam Project (2025). FastParam Core (v0.1) — Generative models and characterisation tools.
Source code. URL: https://fastparam.koexai.com/resources/  Licence: MIT.

Software BibTeX (template)

@software{fastparam_core_v0_1_2025,
      author  = {Koexai Srl},
      title   = {FastParam Source Code},
      year    = {2025},
      version = {1.0},
      url     = {https://fastparam.koexai.com/resources/},
      license = {MIT},
      note    = {Replace with repository URL and tag when public}
    }