ESPAI Resource Hub

Welcome to the ESPAI Resource Hub. Here you’ll find datasets (Anomaly Detection System, real observations, and GenAI simulations), 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

ESPAI datasets are grouped into three categories: Physical Simulations (A), Real Supernova Observations (B), and GenAI Simulator (C). Each dataset comes with a minimal open sample (CSV, 5 rows) for quick inspection and the full files in compact formats (e.g. .parquet) 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. Physical Simulations

A1. Physical models (4-parameters)

Overview. Semi-analytic explosions with four core parameters controlling energy, radius, ejecta mass, and radioactive contribution. The release includes time-dependent observables plus generation metadata.

Intended use: parameter-recovery benchmarks, uncertainty calibration, and sanity checks against semi-analytic expectations.

light_curves.parquet · 3.7 MB SHA-256
params.parquet · 4.1 KB SHA-256

Last updated: 2025-08-23

Preview (CSV)

First 5 rows from a tiny sample file for curves; the full dataset is available via the csv download above.

Loading preview…

First 5 rows from a tiny sample file for parameters; the full dataset is available via the csv download above.

Loading preview…
FAIR artefacts (status)

We’re progressively adding the artefacts below; items marked “Coming soon” will appear in the next releases.

A2. Physical models (7-parameters)

Overview. An expanded physical grid with seven parameters to capture a broader range of progenitor and CSM scenarios. Useful for ablation studies and robustness tests when moving from compact to richer physical descriptions.

Intended use: stress-testing model generalisation and examining parameter identifiability under increased realism.

light_curves.parquet · 21.6 MB SHA-256
params.parquet · 6.1 KB SHA-256

Last updated:

Preview (CSV)

First 5 rows from a tiny sample file for curves; the full dataset is available via the .parquet download above.

Loading preview…

First 5 rows from a tiny sample file for parameters; the full dataset is available via the .parquet download above.

Loading preview…
FAIR artefacts (status)

We’re progressively adding the artefacts below; items marked “Coming soon” will appear in the next releases.

B. Real Supernova Observations

B1. Real observations

Overview. Curated multi-band observations with cadence, passbands, uncertainty model, and basic quality flags. Where possible, records are mapped to standard naming and include minimal provenance notes.

Intended use: evaluating methods trained on synthetic data, domain shift studies, and end-to-end validation on real light curves.

74_SNE_bolometric_real.parquet · 248.1 KB SHA-256

Last updated:

Preview (CSV)

First 5 rows from a tiny sample file.

Loading preview…
FAIR artefacts (status)

We’re progressively adding the artefacts below; items marked “Coming soon” will appear in the next releases.

C. GenAI Simulator

C1. Synthetic GenAI data

Overview. Synthetic light curves produced by the ESPAI GenAI model to augment coverage where observations are sparse. Paired .parquet files provide light time series; releases will ship with transparent generation settings.

Intended use: data augmentation, controlled experiments on cadence/noise, and benchmarking generalisation.

generated_supernovae.parquet · 45.9 MB SHA-256

Last updated:

Preview (CSV)

First 5 rows from a tiny sample file.

Loading preview…
FAIR artefacts (status)

We’re progressively adding the artefacts below; items marked “Coming soon” will appear in the next releases.

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.

ESPAI 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 findings for the community.

Journal & Conference Submissions

  • Paper #1 (title TBC)
    • Status: In preparation
    • Type: Journal article

    Abstract Preprint (coming soon)

    Show short note
    Scope: early results on physical-model light curves; baselines & GenAI augmentation plan.
  • Paper #2 (title TBC)
    • Status: Planned submission
    • Type: Conference paper

    Outline

Diagrams & Technical Notes

Findings

Licence & Citation

To support ethical reuse and proper attribution, ESPAI 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)

ESPAI Project (2025). ESPAI Light Curves — Physical models (4-parameters), v0.1.
Koexai. URL: https://ESPAI.koexai.com/resources/  Licence: CC BY 4.0.

Dataset BibTeX (template)

@dataset{ESPAI_A1_v0_1_2025,
      author  = {ESPAI Project},
      title   = {ESPAI Light Curves — Physical models (4-parameters)},
      year    = {2025},
      version = {0.1},
      url     = {https://ESPAI.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)

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

Software BibTeX (template)

@software{ESPAI_core_v0_1_2025,
      author  = {ESPAI Project},
      title   = {ESPAI Core},
      year    = {2025},
      version = {0.1},
      url     = {https://ESPAI.koexai.com/resources/},
      license = {MIT},
      note    = {Replace with repository URL and tag when public}
    }