Dev
Secondary Ion Mass Spectrometry (SIMS) Imaging — Dev Tier
(5 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| mass_calibration_drift | -1.2 – 1.8 | ppm |
| matrix_effect_(sputter_yield) | -12.0 – 18.0 | - |
| crater_edge_effect | -2.4 – 3.6 | - |
| charging_(insulating_samples) | -48.0 – 72.0 | V |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | U-Net-Spectra + gradient | 0.649 | 25.01 | 0.803 | 0.89 | ✓ Certified | Spectral U-Net variant |
| 2 | PINN-Spectra + gradient | 0.643 | 25.44 | 0.816 | 0.81 | ✓ Certified | Physics-informed neural network |
| 3 | PnP-DnCNN + gradient | 0.634 | 24.78 | 0.795 | 0.84 | ✓ Certified | Zhang et al., 2017 |
| 4 | CDAE + gradient | 0.614 | 23.94 | 0.766 | 0.84 | ✓ Certified | Zhang et al., Sensors 2024 |
| 5 | DiffusionSpectra + gradient | 0.611 | 23.5 | 0.75 | 0.88 | ✓ Certified | Zhang et al., 2024 |
| 6 | ScoreSpectra + gradient | 0.605 | 23.89 | 0.765 | 0.8 | ✓ Certified | Wei et al., 2025 |
| 7 | Cascade-UNet + gradient | 0.599 | 23.17 | 0.738 | 0.86 | ✓ Certified | Physics-informed UNet, 2025 |
| 8 | SpectraFormer + gradient | 0.574 | 22.16 | 0.697 | 0.87 | ✓ Certified | Spectroscopy transformer, 2024 |
| 9 | Baseline Correction + gradient | 0.547 | 21.67 | 0.676 | 0.8 | ✓ Certified | Polynomial fitting baseline |
| 10 | SG-ALS + gradient | 0.544 | 21.15 | 0.652 | 0.86 | ✓ Certified | Savitzky-Golay + ALS baseline |
| 11 | SVD + gradient | 0.502 | 20.24 | 0.61 | 0.78 | ✓ Certified | Singular Value Decomposition |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%