Milestone A

Each milestone is scored out of twenty under the peer-review protocol: five criteria, 0 to 4 each. Score 0 for missing evidence, 1 to 2 for an incomplete artifact, 3 for a sound artifact with limited measurement, and 4 for reproducible evidence with the measurement, its noise and its limitations stated. 14 of 20 passes. A high score never overrides a failed mastery gate.

Five four-point criteria:

• A deployed service a stranger runs in three commands, with tests that exercise a failure path.
• A profiling before/after with numbers, and one assistant-written bug you caught and explained.
• A tabular project with a baseline, cross-validated comparison and a metric chosen for a stated reason.
• Error analysis of the 30 worst cases, categorised, with one fix measured.
• A leakage note per feature and a drawing of gradient descent that a reviewer accepts.

Challenge: your model is 94% accurate and your reviewer says "so what?". Answer with the baseline, the metric that matches the decision, and the biggest failure category.

Submission checklist

For each milestone include: commit identifier; environment and setup; exact commands; the measurement, its denominator and its noise; what you expected before running; what you observed; limitations; next steps. Anything not run (a GPU run you could not afford, users you could not recruit) must say "not done", not be implied. Grade reasoning and reproducibility, not screenshots.

Use the instructor keys for module reasoning and the capstone for the final practical assessment.