Hidden

Secondary Ion Mass Spectrometry (SIMS) Imaging — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

No data downloadable. Algorithm runs server-side on hidden measurements.

Package algorithm as Docker container / Python script. Submit via link.

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter	Spec Range	Unit
mass_calibration_drift	-0.7 – 2.3	ppm
matrix_effect_(sputter_yield)	-7.0 – 23.0	-
crater_edge_effect	-1.4 – 4.6	-
charging_(insulating_samples)	-28.0 – 92.0	V

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	U-Net-Spectra + gradient	0.572	22.22	0.699	0.85	✓ Certified	Spectral U-Net variant
2	PnP-DnCNN + gradient	0.571	22.71	0.72	0.78	✓ Certified	Zhang et al., 2017
3	PINN-Spectra + gradient	0.566	22.15	0.696	0.83	✓ Certified	Physics-informed neural network
4	DiffusionSpectra + gradient	0.560	22.45	0.709	0.76	✓ Certified	Zhang et al., 2024
5	CDAE + gradient	0.549	21.9	0.686	0.78	✓ Certified	Zhang et al., Sensors 2024
6	Cascade-UNet + gradient	0.535	21.52	0.669	0.76	✓ Certified	Physics-informed UNet, 2025
7	SG-ALS + gradient	0.534	21.33	0.661	0.78	✓ Certified	Savitzky-Golay + ALS baseline
8	Baseline Correction + gradient	0.526	20.37	0.616	0.88	✓ Certified	Polynomial fitting baseline
9	ScoreSpectra + gradient	0.525	20.41	0.618	0.87	✓ Certified	Wei et al., 2025
10	SVD + gradient	0.492	19.59	0.579	0.82	✓ Certified	Singular Value Decomposition
11	SpectraFormer + gradient	0.478	19.54	0.576	0.76	✓ Certified	Spectroscopy transformer, 2024

Scenes: 5

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%