LIVEdataset aec-bench@releasetasks 552models 18last submission … · built …
mechanicalwith-tool

Chemical Dosing

Calculates treatment chemical feed requirements from process flow, target active dose, product strength, and product density. The template reports active chemical mass, commercial product mass, volumetric feed rate, and annual product consumption for water and wastewater dosing checks.

with-tool: The model is given an executable Python calculator script.

Standards

WEF MOP 8

Tags

chemical-dosingdeterministicfeed-ratemechanicalwater-treatment

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

  1. 01

    Template

    The reusable contract shown on this page.

  2. 02

    Scenario

    An archetype and site context are sampled.

  3. 03

    Difficulty tier

    Inputs may be hidden at harder tiers.

  4. 04

    Task prompt

    The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

4 inputs

Always given

Included directly in every task prompt.

4

  • Flow rate

    flow_rate_m3_d

    Process flow rate

    10 – 1000000 m3/d

  • Target dose

    target_dose_mg_l

    Target active chemical dose

    0.1 – 500 mg/L

  • Product strength pct

    product_strength_pct

    Active chemical strength or purity of commercial product

    1 – 100 %

  • Product density

    product_density_kg_l

    Commercial chemical product density

    0.7 – 2 kg/L

Scored outputs

4 outputs

Active mass feed kg d

active_mass_feed_kg_d

Active chemical mass feed rate

Scores if within ±3% of the reference value.

Product mass feed kg d

product_mass_feed_kg_d

Commercial product mass feed rate

Scores if within ±3% of the reference value.

Volume feed l d

volume_feed_l_d

Commercial product volume feed rate

Scores if within ±3% of the reference value.

Annual product consumption t

annual_product_consumption_t

Annual commercial product consumption

Scores if within ±3% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

All inputs remain visible at every tier

For this template, difficulty scales through parameter and scenario ranges rather than hidden information.

easy:
All parameters given for low-dose disinfection
medium:
All parameters given across disinfection and coagulant dosing
hard:
All parameters given for higher mass chemical feed rates

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

  • instruction.md
  • chemical-dosing_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior mechanical engineer specializing in water and wastewater chemical dosing.2 3## Problem4 5Calculate treatment chemical feed requirements for a target active dose.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Process flow rate | {{ flow_rate_m3_d }} | m3/d |12| Target active dose | {{ target_dose_mg_l }} | mg/L |13| Product strength | {{ product_strength_pct }} | % |14| Product density | {{ product_density_kg_l }} | kg/L |15 16{% if archetype_description is defined %}17### Dosing Context18 19{{ archetype_description }}20{% endif %}21 22{% if tool_available %}23## Available Tool24 25A chemical dosing calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:26 27```bash28python3 /workspace/{{ meta.name }}_calc.py --help29```30 31You may use this tool to verify your calculations or compute values directly.32{% endif %}33 34## Required35 36Calculate the following:37 381. Active chemical mass feed rate (kg/d)392. Commercial product mass feed rate (kg/d)403. Commercial product volume feed rate (L/d)414. Annual commercial product consumption (t/yr)42 43## Constraints44 45- No internet access is available. Work from engineering knowledge and the provided tool.46- Use active mass feed = flow rate x target dose / 1000.47- Use product mass feed = active mass feed / (product strength / 100).48- Use volume feed = product mass feed / product density.49- Use annual product consumption = product mass feed x 365 / 1000.50 51## Output Format52 53Show your step-by-step working in Markdown. At the end of your solution, include a JSON block with your final answers in exactly this format:54 55```json56{57 "active_mass_feed_kg_d": <numeric_value>,58 "product_mass_feed_kg_d": <numeric_value>,59 "volume_feed_l_d": <numeric_value>,60 "annual_product_consumption_t": <numeric_value>61}62```63 64Write your complete solution to `/workspace/output.md`.65

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Disinfection dose

disinfection_dose

Low-dose liquid chemical disinfection application

water-treatment-disinfectionrecycled-water-plant
Parameter ranges
flow_rate_m3_d
500 – 100000
target_dose_mg_l
1 – 15
product_strength_pct
8 – 15
product_density_kg_l
1.05 – 1.25

Coagulant dose

coagulant_dose

Coagulant or alkalinity chemical dosing application

surface-water-treatment-plantindustrial-pretreatment
Parameter ranges
flow_rate_m3_d
1000 – 500000
target_dose_mg_l
10 – 120
product_strength_pct
20 – 60
product_density_kg_l
1.1 – 1.6

Example task

surface-water-treatment-plant-coagulant-dose-preview — hard difficulty, all inputs given.

Coagulant or alkalinity chemical dosing application. surface-water-treatment-plant. Required outputs: active_mass_feed_kg_d, product_mass_feed_kg_d, volume_feed_l_d, annual_product_consumption_t

The model sees

Scenario context and visible inputs.

flow_rate_m3_d
1000 to 500000 m3/d
target_dose_mg_l
10 to 120 mg/L
product_strength_pct
20 to 60 %
product_density_kg_l
1.1 to 1.6 kg/L

Executable tool: chemical-dosing_calc.py

The model must infer

Inputs withheld at this difficulty.

Nothing. All inputs are supplied.

The model must produce

The scored JSON answer schema.

{
  "active_mass_feed_kg_d": <number>,
  "product_mass_feed_kg_d": <number>,
  "volume_feed_l_d": <number>,
  "annual_product_consumption_t": <number>
}
  • active_mass_feed_kg_d · scored within ±3%
  • product_mass_feed_kg_d · scored within ±3%
  • volume_feed_l_d · scored within ±3%
  • annual_product_consumption_t · scored within ±3%