Hidden
Radio Interferometry (VLBI) — Hidden Tier
(3 scenes)Fully blind server-side evaluation — no data download.
What you get
No data downloadable. Algorithm runs server-side on hidden measurements.
How to use
Package algorithm as Docker container / Python script. Submit via link.
What to submit
Containerized algorithm accepting y + H, outputting x_hat + corrected spec.
Parameter Specifications
🔒
True spec hidden — blind evaluation, only ranges available.
| Parameter | Spec Range | Unit |
|---|---|---|
| baseline_error | -0.0014 – 0.0046 | m |
| phase_calibration | -1.4 – 4.6 | deg |
| amplitude_calibration | 0.986 – 1.046 | - |
| clock_offset | -0.14 – 0.46 | ns |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | R2D2 + gradient | 0.528 | 20.51 | 0.623 | 0.87 | ✓ Certified | Aghabiglou et al., ApJS 2024 |
| 2 | AIRI + gradient | 0.483 | 19.42 | 0.571 | 0.8 | ✓ Certified | Terris et al., MNRAS 2022 |
| 3 | PRIMO + gradient | 0.436 | 17.45 | 0.473 | 0.86 | ✓ Certified | Medeiros et al., ApJL 2023 |
| 4 | CLEAN + gradient | 0.420 | 17.12 | 0.456 | 0.83 | ✓ Certified | Hogbom, A&AS 1974 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%