Round #1041

19 May 2026, 10:32· math· Meta-Llama-3.3-70B-Instruct· r13-clean-hints
Complexity
band 0
ZP / UO / OBS
3 / 0 / 0
Journey weight
255
Lightshift ΔL

Prompt

A factory produces widgets and 2% are defective. If you sample 50 widgets, what is the probability that exactly 1 is defective?

Zero-point index (what the engine surfaced)

ZPI-ZPI-0038 | 2026-05-19T10:32:41Z A factory produces widgets and 2% are defective. If you sample 50 widgets, what is the probability that exactly 1 is defective? ZERO POINT — 3 entries (structural invariants) ● hsl(47.02, 100%, 15%) factor theorem [contract] ● hsl(103.84, 100%, 15%) common factor extraction [contract] ● hsl(307.92, 100%, 15%) difference of squares a²-b²=(a-b)(a+b) [contract] UNOBSERVED — 0 entries (implied truths) OBSERVED — 0 entries (explicit in request) COMPLEXITY │ 3 entries │ spread: 0° │ band: LOW

Baseline response (no ZPI)

```csharp using System; class Program { static void Main() { // define the probability of a widget being defective double p = 0.02; // define the number of widgets sampled int n = 50; // define the number of defective widgets we are interested in int k = 1; // calculate the probability using the binomial distribution double probability = BinomialProbability(n, k, p); Console.WriteLine("The probability that exactly 1 widget is defective: " + probability); } static double BinomialProbability(int n, int k, double p) { return Combination(n, k) * Math.Pow(p, k) * Math.Pow(1 - p, n - k); } static double Combination(int n, int k) { double result = 1; for (int i = 1; i <= k; i++) { result = result * (n - i + 1) / i; } return result; } } ```

Enhanced response (with ZPI)

```csharp using System; public class Program { public static void Main() { double probability = CalculateProbability(50, 0.02, 1); Console.WriteLine($"The probability that exactly 1 widget is defective is {probability:F4}"); } public static double CalculateProbability(int n, double p, int k) { // Calculate the probability using the binomial distribution formula double probability = BinomialCoefficient(n, k) * Math.Pow(p, k) * Math.Pow(1 - p, n - k); return probability; } public static double BinomialCoefficient(int n, int k) { // Calculate the binomial coefficient using the formula n! / (k! * (n-k)!) double result = 1; for (int i = 1; i <= k; i++) { result = result * (n - i + 1) / i; } return result; } } ``` This C# program calculates the probability of exactly 1 defective widget in a sample of 50, given a 2% defect rate. The `CalculateProbability` function uses the binomial distribution formula, which is `P(X = k) = (nCk) * (p^k) * ((1-p)^(n-k))`, where `n` is the sample size, `k` is the number of defective widgets, `p` is the probability of a widget being defective, and `nCk` is the binomial coefficient. The `BinomialCoefficient` function calculates the binomial coefficient using the formula `n! / (k! * (n-k)!)`. The result is then printed to the console.

Grader chain

Each grader reads the same baseline + enhanced pair and casts an independent verdict. Disagreement is the framework's own signal — not noise to be averaged away.

V1samba/Meta-Llama-3.3-70B-Instruct
Same
V4qwen2.5-coder-3b-instruct
Better
V5cerebras/qwen-3-235b-a22b-instruct-2507
Better
V7qwen2.5-coder-7b-instruct
Same
V8openai/gpt-4.1
Same
V9anthropic/claude-opus-4-7
Same
V12openai/gpt-4o
Better

Comments

Our grader said what it said. What do you say? Comment as a guest below.

No comments yet. Be the first to say what you make of this round.

← back to all rounds