ionis-validate
Validation suite for the IONIS V22-gamma + PhysicsOverrideLayer HF propagation model. Run 29 physics tests (18 KI7MT operator-grounded + 11 band x time discrimination), predict SNR for any HF path, or batch-test your own paths — all from the command line or a browser UI, on any platform.
IONIS (Ionospheric Neural Inference System) predicts HF radio signal strength from WSPR, RBN, and contest data. The V22-gamma model was trained on 38.7 million propagation observations spanning 2008-2026, with a deterministic PhysicsOverrideLayer for high-band night closure.
Install
pip install ionis-validate
Requires Python 3.10+ and PyTorch 2.0+. Works on Windows, macOS, and Linux.
Quick Start
# Show model and system info
ionis-validate info
# Run the full 29-test validation suite
ionis-validate test
# Predict SNR for a single path
ionis-validate predict \
--tx-grid FN20 --rx-grid IO91 --band 20m \
--sfi 150 --kp 2 --hour 14 --month 6 --day-of-year 172
# Acid test: 10m EU path at night (override should fire)
ionis-validate predict \
--tx-grid DN46 --rx-grid JN48 --band 10m \
--sfi 150 --kp 2 --hour 2 --month 2 --day-of-year 45
Browser UI
A point-and-click dashboard wrapping every command.
pip install "ionis-validate[ui]"
ionis-validate ui
Opens a browser tab at http://localhost:8765 with tabs for Predict,
Custom, Report, and Info.
Batch Predictions
Define a set of paths in a JSON file and run them all at once:
# Run the bundled example (2 easy, 2 medium, 2 hard)
ionis-validate custom --example
# Run your own paths
ionis-validate custom my_paths.json
See the Custom Path Tests
documentation for the JSON format. V22 adds day_of_year and an OVR
(override) column to the output.
Beta Testing
Generate a structured report for filing as a GitHub Issue:
ionis-validate report
Privacy
IONIS processes only grid-pair geometry, band, time, and solar indices. No callsigns, names, or personal data are used by the model or stored by this tool.
Full privacy policy: https://ionis-ai.com/about/data-privacy/
License
GPL-3.0-or-later. See LICENSE.
Links
- Documentation: https://ionis-ai.com/testing/
- Source: https://github.com/IONIS-AI/ionis-validate
- Issues: https://github.com/IONIS-AI/ionis-validate/issues
- IONIS Project: https://ionis-ai.com/
Metadata
Release files for ionis-validate 4.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ionis_validate-4.0.3.tar.gz | 817.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ionis_validate-4.0.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.6 MB
Release files / ionis_validate-4.0.3.tar.gz
| Download URL | ionis_validate-4.0.3.tar.gz |
|---|---|
| Size | 817.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
aa6da3bb12e6184fd38bb30c423f88d805662f2edc8ecbce8ddaf638608358e6
|
|
BLAKE2b-256 checksum How to use checksums |
a7742b909850ecbd415511d432bd5a578ad3b0ef67afd0ff5fc4f8b8a8de0b2d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 26, 2026.
Transparency logRelease files / ionis_validate-4.0.3-py3-none-any.whl
| Download URL | ionis_validate-4.0.3-py3-none-any.whl |
|---|---|
| Size | 822.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fb9e8ca1d976905891c2d1acf65337de0daff682d80695e1a0806e3fbf7cbc28
|
|
BLAKE2b-256 checksum How to use checksums |
bd0fae4e4d97de15be80618f88e3262c1f3e8470d1069ae3d4c9762708d6622a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 26, 2026.
Transparency log