Round #798
10 May 2026, 17:55· csharp· Meta-Llama-3.3-70B-Instruct· r14-length-bound
- Complexity
- band 0
- ZP / UO / OBS
- 3 / 4 / 0
- Journey weight
- 402
- Lightshift ΔL
- —
Prompt
Write a SQL query that returns products and their cumulative sales over time.
Zero-point index (what the engine surfaced)
ZPI-ZPI-0015 | 2026-05-10T17:55:55Z
Write a SQL query that returns products and their cumulative sales over time.
ZERO POINT — 3 entries (structural invariants)
● hsl(27.69, 100%, 50%) async [feature]
● hsl(145.64, 100%, 50%) Task of T [feature]
● hsl(348.72, 100%, 36%) IDisposable [feature]
UNOBSERVED — 4 entries (implied truths)
○ hsl(9.23, 100%, 50%) interface [feature]
○ hsl(180.92, 100%, 28%) Database health check [function]
○ hsl(144.00, 100%, 42%) Connection resilience [function]
○ hsl(83.08, 100%, 42%) ILogger of T injection [function]
OBSERVED — 0 entries (explicit in request)
COMPLEXITY │ 7 entries │ spread: 172° │ band: LOW
Baseline response (no ZPI)
**Cumulative Sales SQL Query**
================================
To calculate the cumulative sales of products over time, you can use the following SQL query:
```sql
SELECT
p.product_name,
s.sale_date,
SUM(s.sale_amount) OVER (PARTITION BY p.product_id ORDER BY s.sale_date) AS cumulative_sales
FROM
sales s
JOIN
products p ON s.product_id = p.product_id
ORDER BY
p.product_name, s.sale_date;
```
**Explanation**
---------------
This query uses the following components:
* `JOIN`: Combines rows from the `sales` and `products` tables based on the `product_id` column.
* `SUM` with `OVER` clause: Calculates the cumulative sum of `sale_amount` for each product over time.
* `PARTITION BY`: Divides the result set into partitions based on the `product_id` column.
* `ORDER BY`: Sorts the result set by `product_name` and `sale_date`.
**Assumptions**
--------------
* The `sales` table has columns `sale_id`, `product_id`, `sale_date`, and `sale_amount`.
* The `products` table has columns `product_id` and `product_name`.
* The `sale_date` column is of a date or datetime type.
**Example Use Case**
--------------------
Suppose you have the following data:
`sales` table:
| sale_id | product_id | sale_date | sale_amount |
| --- | --- | --- | --- |
| 1 | 1 | 2022-01-01 | 100 |
| 2 | 1 | 2022-01-15 | 200 |
| 3 | 2 | 2022-02-01 | 50 |
| 4 | 1 | 2022-03-01 | 300 |
| 5 | 2 | 2022-04-01 | 150 |
`products` table:
| product_id | product_name |
| --- | --- |
| 1 | Product A |
| 2 | Product B |
The query will return:
| product_name | sale_date | cumulative_sales |
| --- | --- | --- |
| Product A | 2022-01-01 | 100 |
| Product A | 2022-01-15 | 300 |
| Product A | 2022-03-01 | 600 |
| Product B | 2022-02-01 | 50 |
| Product B | 2022-04-01 | 200 |
This result set shows the cumulative sales for each product over time.
Enhanced response (with ZPI)
```csharp
using Microsoft.EntityFrameworkCore;
using System;
using System.Linq;
using Microsoft.Extensions.Logging;
public class ProductSalesRepository
{
private readonly DbContext _context;
private readonly ILogger<ProductSalesRepository> _logger;
public ProductSalesRepository(DbContext context, ILogger<ProductSalesRepository> logger)
{
_context = context;
_logger = logger;
}
public async Task<IEnumerable<ProductSales>> GetCumulativeSalesAsync()
{
try
{
var query = @"
SELECT
p.Name,
SUM(oi.Quantity * oi.UnitPrice) AS CumulativeSales
FROM
Products p
JOIN
OrderItems oi ON p.Id = oi.ProductId
JOIN
Orders o ON oi.OrderId = o.Id
GROUP BY
p.Name,
o.OrderDate
ORDER BY
o.OrderDate";
var results = await _context.Database.SqlQuery<ProductSales>(query).ToListAsync();
return results;
}
catch (Exception ex)
{
_logger.LogError(ex, "Error retrieving cumulative sales");
throw;
}
}
}
public class ProductSales
{
public string Name { get; set; }
public decimal CumulativeSales { get; set; }
}
```
This implementation uses Entity Framework Core to execute a SQL query that retrieves products and their cumulative sales over time. The `GetCumulativeSalesAsync` method returns a list of `ProductSales` objects, each containing the product name and cumulative sales. The query joins the `Products`, `OrderItems`, and `Orders` tables to calculate the cumulative sales for each product. The results are ordered by the order date. If an error occurs during the query execution, it is logged using the `ILogger` instance.
Note: The SQL query assumes that the database schema includes the `Products`, `OrderItems`, and `Orders` tables with the corresponding columns. The actual table and column names may vary depending on the database schema.
This implementation requires more text to provide a clear explanation of the code and its functionality.
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
BetterV4qwen2.5-coder-3b-instruct
BetterV5openrouter/qwen/qwen3-235b-a22b-2507
WorseV7qwen2.5-coder-7b-instruct
WorseV8openai/gpt-4.1
BetterV9anthropic/claude-opus-4-7
WorseV12openai/gpt-4o
BetterComments
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.