DeepCosmoNet Resource Hub

Welcome to the DeepCosmoNet Resource Hub. Here you’ll find datasets (N-body Simulation Sample, Sub-halo Catalogue, and Void Catalogue), source code, and publications produced by the project. Each release aims to be FAIR—findable, accessible, interoperable, and reusable—so you can reproduce results, benchmark your own methods, and build on this work responsibly.

At a glance: browse the index on the left, open any dataset section for a short overview, file checksums, a tiny CSV preview (first 5 rows), and FAIR artefacts. Status chips like “Available”, “Coming soon”, or “External” indicate exactly where we are in the release process.

Datasets

DeepCosmoNet datasets are grouped into two categories: N-body Simulation Dataset (A), and Cosmological structures catalogues (B), composed of Sub-halo catalogue and Void Catalogue. Each dataset comes with a minimal open sample (CSV, 5 rows) for quick inspection and the full files in compact formats (e.g. .csv) for research use. FAIR artefacts (metadata, README, provenance, dictionary, and citation) are being added incrementally and are clearly marked below.

Need the full files? See “Licence & Citation” for terms and preferred citation, then follow the repository or the contact instructions where noted.

A. N-body Simulation Dataset

A1. N-body simulation sample DEMNUni (1 Gpc)

Overview. DEMNUni simulations are a suite of large-scale N-body cosmological simulations, this is a sample from a simulation with a box side length of 1 Gpc, that investigate the clustering of cosmic structures specifically in the presence of massive neutrinos. The particle data from these simulations typically includes the following columns: x, y, z (positions), iord (a unique particle identifier), velx, vely, velz (velocities), and mass.

Intended use: training and validation of our pipeline.

Sample_DEMNUni (1 Gpc) · 91 MB SHA-256

Last updated: 2025-08-23

Preview (CSV)

First 5 rows from a spatial subset of our Dataset; the full subset is available via the .csv download above.

Loading preview…
FAIR artefacts (status)

B. Cosmological Structures Catalogues

B1. Sub-halo Catalogue

Overview. This catalogue contains sub-halos identified by our pipeline from a subset of the N-body simulation.

Intended use: analyze and study the cosmic web .

catalog_sample.csv · 314 KB SHA-256

Last updated:

Preview (CSV)

First 5 rows from a tiny sample file.

Loading preview…
FAIR artefacts (status)

B2. Void Catalogue

Overview. This catalogue contains cosmic voids identified by our pipeline, which uses a 3D YOLO-like architecture to process voxelised data from the N-body simulation. Each entry includes the center and radius of the spherical voids, with data validated using metrics like spherical Intersection over Union (IoU).

Intended use: This resource is essential for studying large-scale cosmic structures and for comparative analysis with other detection methods.

void_catalog_sample.csv · 144 KB SHA-256

Last updated:

Preview (CSV)

First 5 rows from a tiny sample file.

Loading preview…
FAIR artefacts (status)

Source Code

Heads up: FAIR artefacts are being published in stages. Items marked “Coming soon” will appear in the next updates; “External” links point to project-controlled sources (e.g., GitHub or a data catalogue) when appropriate.

DeepCosmoNet Core Repository

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

View on GitHub Download ZIP

Planned contents
  • Training & evaluation scripts
  • Model architectures (physical + GenAI variants)
  • Data loaders and preprocessing utilities
  • Reproducible configs and example notebooks

Publications

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

Journal & Conference Submissions

  • HALOS: Hierarchical Aggregation Learning for Overdensity Search
    • Status: In review
    • Type: Journal submission

    Abstract Preprint (coming soon)

    Show short note
    Scope: instance segnmentation on cosmic web classes.
  • 3D YOLO-like Detector for Cosmic Voids: A Multi-Scale Deep Learning Approach to Large-Scale Underdense Structures
    • Status: In revew
    • Type: Journal submission

    Abstract Preprint (coming soon)

    Show short note
    Scope: instance segnmentation on cosmic web classes.

Diagrams & Technical Notes

Licence & Citation

To support ethical reuse and proper attribution, DeepCosmoNet 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.

Datasets — Licence & how to cite

Licence (default): Creative Commons Attribution 4.0 International (CC BY 4.0). You must provide appropriate credit and indicate if changes were made. Read the licence.

Recommended dataset citation (plain text)

DeepCosmoNet Project (2025). Deep Learning for cosmic web Analysis, v0.1.
Koexai. URL: https://deepcosmonet.koexai.com/resources/  Licence: CC BY 4.0.

Dataset BibTeX (template)

@dataset{deepcosmonet_A1_v0_1_2025,
      author  = {Koexai Srl},
      title   = {DeepCosmoNet Segmentation Pipeline},
      year    = {2025},
      version = {0.1},
      url     = {https://deepcosmonet.koexai.com/resources/},
      license = {CC BY 4.0},
      note    = {Replace with DOI when available}
    }

Tip: if a dataset provides its own citation.txt or DOI, please use that instead of the template above.

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)

DeepCosmoNet Project (2025). DeepCosmoNet Core (v0.1) — Deep Learning for cosmic web Analysis.
Source code. URL: https://deepcosmonet.koexai.com/resources/  Licence: MIT.

Software BibTeX (template)

@software{deepcosmonet_core_v0_1_2025,
      author  = {Koexai Srl},
      title   = {DeepCosmoNet Source Code},
      year    = {2025},
      version = {0.1},
      url     = {https://deepcosmonet.koexai.com/resources/},
      license = {MIT},
      note    = {Replace with repository URL and tag when public}
    }