Training–serving skew
A semantic or computational mismatch between features seen during training and inference.
Aliases: train-serve-skewLessons
Formal explanations, examples, simulations, and checkpoints.
Data contracts, ownership, and lineage
Use data contracts, ownership, and lineage to move the data & features production brief toward a defensible release.
Data & feature foundationsPoint-in-time-correct features
Use point-in-time-correct features to move the data & features production brief toward a defensible release.
Data & feature foundationsFeature transformations that survive production
Use feature transformations that survive production to move the data & features production brief toward a defensible release.
Data & feature foundationsBatch, stream, and training-serving parity
Use batch, stream, and training-serving parity to move the data & features production brief toward a defensible release.
Data & feature foundationsLabels, snapshots, and backfills
Use labels, snapshots, and backfills to move the data & features production brief toward a defensible release.
Courses & assignments
Dependency-authoritative learning units.
Casebook
Reported facts and course reconstructions.