Particle Calorimetry

Particle Calorimetry

Join the Competition Contribute to Benchmark

Standard reconstruction benchmark — forward model perfectly known, no calibration needed. Score = 0.5 × clip((PSNR−15)/30, 0, 1) + 0.5 × SSIM

# Method Score PSNR (dB) SSIM Source
🥇 CaloDiffusion 0.725 31.5 0.900 ✓ Certified Mikuni & Nachman, PRD 2023
🥈 GravNet 0.672 29.5 0.860 ✓ Certified Qasim et al., EPJC 2019
🥉 GARFIELD++ 0.535 25.5 0.720 ✓ Certified Veenhof, NIM 1998
4 PandoraPFA 0.407 22.0 0.580 ✓ Certified Thomson, JINST 2009

Dataset: PWM Benchmark (4 algorithms)

Blind Reconstruction Challenge — forward model has unknown mismatch, must calibrate from data. Score = 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

# Method Overall Score Public
PSNR / SSIM
 Dev
PSNR / SSIM
 Hidden
PSNR / SSIM
 Trust Source
🥇 CaloDiffusion + gradient 0.645
0.732
29.33 dB / 0.906
0.617
23.58 dB / 0.753
0.587
23.09 dB / 0.735
✓ Certified Mikuni & Nachman, PRD 2023
🥈 GARFIELD++ + gradient 0.587
0.639
24.21 dB / 0.776
0.596
23.15 dB / 0.737
0.526
20.45 dB / 0.620
✓ Certified Veenhof, Nucl. Instr. Meth. 1998
🥉 GravNet + gradient 0.553
0.697
27.37 dB / 0.867
0.518
20.5 dB / 0.622
0.443
18.22 dB / 0.511
✓ Certified Qasim et al., Eur. Phys. J. C 2019
4 PandoraPFA + gradient 0.468
0.545
20.67 dB / 0.630
0.458
18.07 dB / 0.503
0.402
16.44 dB / 0.423
✓ Certified Thomson, JINST 2009

Complete score requires all 3 tiers (Public + Dev + Hidden).

Join the competition →
Scoring: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖) PSNR 40% · SSIM 40% · Consistency 20%
Public 5 scenes

Full-access development tier with all data visible.

What you get & how to use

What you get: Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

How to use: Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

What to submit: Reconstructed signals (x_hat) and corrected spec as HDF5.

Public Leaderboard
# Method Score PSNR SSIM
1 CaloDiffusion + gradient 0.732 29.33 0.906
2 GravNet + gradient 0.697 27.37 0.867
3 GARFIELD++ + gradient 0.639 24.21 0.776
4 PandoraPFA + gradient 0.545 20.67 0.63
Spec Ranges (4 parameters)
Parameter Min Max Unit
energy_scale_factor 0.994 1.012 -
position_resolution -1.0 2.0 mm
sampling_fraction 0.096 0.108 -
pile_up_fraction -0.01 0.02 -
View Details →
Dev 5 scenes

Blind evaluation tier — no ground truth available.

What you get & how to use

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.

Dev Leaderboard
# Method Score PSNR SSIM
1 CaloDiffusion + gradient 0.617 23.58 0.753
2 GARFIELD++ + gradient 0.596 23.15 0.737
3 GravNet + gradient 0.518 20.5 0.622
4 PandoraPFA + gradient 0.458 18.07 0.503
Spec Ranges (4 parameters)
Parameter Min Max Unit
energy_scale_factor 0.9928 1.0108 -
position_resolution -1.2 1.8 mm
sampling_fraction 0.0952 0.1072 -
pile_up_fraction -0.012 0.018 -
Submit Reconstruction View Details →
Hidden 5 scenes

Fully blind server-side evaluation — no data download.

What you get & how to use

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.

Hidden Leaderboard
# Method Score PSNR SSIM
1 CaloDiffusion + gradient 0.587 23.09 0.735
2 GARFIELD++ + gradient 0.526 20.45 0.62
3 GravNet + gradient 0.443 18.22 0.511
4 PandoraPFA + gradient 0.402 16.44 0.423
Spec Ranges (4 parameters)
Parameter Min Max Unit
energy_scale_factor 0.9958 1.0138 -
position_resolution -0.7 2.3 mm
sampling_fraction 0.0972 0.1092 -
pile_up_fraction -0.007 0.023 -
Submit Algorithm View Details →

Blind Reconstruction Challenge

Challenge

Given measurements with unknown mismatch and spec ranges (not exact params), reconstruct the original signal. A method must be evaluated on all three tiers for a complete score. Scored on a composite metric: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖).

Input

Measurements y, ideal forward model H, spec ranges

Output

Reconstructed signal x̂

Spec DAG — Forward Model Pipeline

R → Σ → D

R Rotation
Σ Summation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
e_s energy_scale_factor Energy scale factor (-) 1.0 1.006
p_r position_resolution Position resolution (mm) 0.0 1.0
s_f sampling_fraction Sampling fraction (-) 0.1 0.104
p_f pile_up_fraction Pile-up fraction (-) 0.0 0.01

Credits System

40%
Platform Profit Pool
Revenue allocated to benchmark rewards
30%
Winner Share
Top algorithm receives from pool
$100
Min Withdrawal
Minimum payout threshold
Spec Primitives Reference (11 primitives)
P Propagation

Free-space or medium propagation kernel (Fresnel, Rayleigh-Sommerfeld).

M Mask / Modulation

Spatial or spatio-temporal amplitude modulation (coded aperture, SLM pattern).

Π Projection

Geometric projection operator (Radon transform, fan-beam, cone-beam).

F Fourier Sampling

Sampling in the Fourier / k-space domain (MRI, ptychography).

C Convolution

Shift-invariant convolution with a point-spread function (PSF).

Σ Summation / Integration

Summation along a physical dimension (spectral, temporal, angular).

D Detector

Sensor readout with gain g and noise model η (Gaussian, Poisson, mixed).

S Structured Illumination

Patterned illumination (block, Hadamard, random) applied to the scene.

W Wavelength Dispersion

Spectral dispersion element (prism, grating) with shift α and aperture a.

R Rotation / Motion

Sample or gantry rotation (CT, electron tomography).

Λ Wavelength Selection

Spectral filter or monochromator selecting a wavelength band.