Output Artifacts¶
The standard artifact-writing path produces a small set of files that capture the model surface, projected compounds, and run metadata.
CSV files¶
train_coords.csvembedded training coordinates and labels
test_coords.csvprojected test coordinates and scores
predictions_test.csvsame tabular test prediction payload used for downstream inspection
Array artifact¶
surface_grid.npzgrid_xgrid_yposterior_zpos_density_z
JSON metadata¶
params.jsonrun configuration
metrics.jsonevaluation summary and metric metadata
Python return value¶
When you use the library API rather than only the CLI, the workflow
returns typed public dataclasses from psma.results.