Entropy Calculation with Numerical Stability and Streaming

Problem Overview

Given a vector of logits (raw unnormalized scores), implement Shannon entropy of the corresponding softmax distribution. The entropy is H = -Σ p_i · log(p_i) where p_i = softmax(z_i). The round has four graded parts, each building on the previous one: Part 1 — Basic entropy Implement a straightforward entropy…

• 5 candidate-reported follow-ups — the exact probes interviewers asked, with the trigger for each
• The rest of the problem statement — full requirements, constraints, and edge cases
• Approach and trade-offs — what passing candidates did, and the mistakes that sink people