Smart Pixel Dataset: Simulated Silicon Pixel Clusters from CMS Run 2 Particle Tracks

A simulated dataset of silicon pixel clusters produced by charged pions, where particle kinematics are taken from fitted tracks in CMS Run 2 data. The dataset includes truth properties for each particle and 3D charge deposition clusters across time slices. It was created by M. Swartz of Johns Hopkins University.

Use Cases

• Training models for particle impact point prediction based on (x-entry, y-entry) and (x-midplane, y-midplane) coordinates.
• Developing algorithms for track direction inference using the (n_x, n_y, n_z) vector components.
• Simulating detector response for charged particles in a 3.8T magnetic field using the cotAlpha and cotBeta incidence angles.
• Analyzing charge deposition patterns by reshaping the recon files into (8,13,21) 3D clusters representing time, y, and x dimensions.

Strengths

• Includes detailed truth labels such as particle transverse momentum (pt), entry points, and direction vectors.
• Simulates a specific detector geometry: a 21x13 pixel array with 50x12.5 micron pitch, situated 30mm from the origin.
• Models physical effects including a 3.8T magnetic field and time-sliced charge deposition with 200 ps windows.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Johns Hopkins University

Collection Method

Simulation using a time-sliced version of PixelAV, with particle kinematics from fitted tracks in CMS Run 2 data.