Dev
Atom Probe Tomography (APT) — 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 |
|---|---|---|
| flight_path_error | -0.12 – 0.18 | mm |
| voltage_calibration | 0.9952 – 1.0072 | - |
| detection_efficiency | 0.576 – 0.636 | - |
| tip_radius_error | -1.2 – 1.8 | nm |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | EquivAPT + gradient | 0.766 | 31.76 | 0.94 | 0.86 | ✓ Certified | Adapted from equivariant vision transformer for atomic imaging, 2025 |
| 2 | DiffusionAPT + gradient | 0.716 | 29.31 | 0.906 | 0.8 | ✓ Certified | Inspired by Chung et al., ICLR 2023 (score-based MRI) |
| 3 | APT-Former + gradient | 0.707 | 28.25 | 0.886 | 0.85 | ✓ Certified | Moody et al., Microsc. Microanal. 30(2):341, 2024 |
| 4 | TrajectoryPINN + gradient | 0.624 | 24.67 | 0.792 | 0.8 | ✓ Certified | De Geuser & Gault, Annu. Rev. Mater. Res. 52:1, 2022 |
| 5 | LISTA-APT + gradient | 0.590 | 22.91 | 0.728 | 0.85 | ✓ Certified | Gregor & LeCun, ICML 2010; adapted for APT 2020 |
| 6 | ResNet-ArtefactCorr + gradient | 0.543 | 20.87 | 0.64 | 0.89 | ✓ Certified | Wei et al., Ultramicroscopy 206:112817, 2019 |
| 7 | Tikhonov-Trajectory + gradient | 0.539 | 21.31 | 0.66 | 0.81 | ✓ Certified | Geiser et al., Microsc. Microanal. 13(6):437, 2007 |
| 8 | PnP-BM3D (APT) + gradient | 0.494 | 19.15 | 0.557 | 0.9 | ✓ Certified | Danielyan et al., IEEE TIP 21(9):3884, 2012 |
| 9 | Bas-Protocol + gradient | 0.453 | 18.29 | 0.514 | 0.82 | ✓ Certified | Bas et al., Appl. Surf. Sci. 87-88:298, 1995 |
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%