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

Spl Log Sum

Calculates combined sound pressure level from three independent source levels using logarithmic addition. The template converts each dB value to linear acoustic energy, sums the terms, and converts back to dB for deterministic acoustic fundamentals checks.

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

Standards

Acoustic Fundamentals

Tags

acousticsdeterministiclogarithmic-summechanicalspl

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

3 inputs

Always given

Included directly in every task prompt.

3

  • Source 1 spl

    source_1_spl_db

    Sound pressure level from source 1

    20 – 130 dB

  • Source 2 spl

    source_2_spl_db

    Sound pressure level from source 2

    20 – 130 dB

  • Source 3 spl

    source_3_spl_db

    Sound pressure level from source 3

    20 – 130 dB

Scored outputs

3 outputs

Total linear energy

total_linear_energy

Sum of linear acoustic energy terms

Scores if within ±3% of the reference value.

Combined spl db

combined_spl_db

Combined sound pressure level

Scores if within ±3% of the reference value.

Dominant source spl db

dominant_source_spl_db

Highest individual source level

Scores if within ±1% 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 plant room sources
medium:
All parameters given across plant and industrial noise sources
hard:
All parameters given for higher-level industrial noise sources

Task bundle

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

/workspace

  • instruction.md
  • spl-log-sum_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 building services acoustics.2 3## Problem4 5Calculate the combined sound pressure level from three independent sound sources using logarithmic addition.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Source 1 SPL | {{ source_1_spl_db }} | dB |12| Source 2 SPL | {{ source_2_spl_db }} | dB |13| Source 3 SPL | {{ source_3_spl_db }} | dB |14 15{% if archetype_description is defined %}16### Acoustic Context17 18{{ archetype_description }}19{% endif %}20 21{% if tool_available %}22## Available Tool23 24An SPL logarithmic summation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:25 26```bash27python3 /workspace/{{ meta.name }}_calc.py --help28```29 30You may use this tool to verify your calculations or compute values directly.31{% endif %}32 33## Required34 35Calculate the following:36 371. Sum of linear acoustic energy terms382. Combined sound pressure level (dB)393. Dominant individual source level (dB)40 41## Constraints42 43- No internet access is available. Work from engineering knowledge and the provided tool.44- Convert each source level to a linear energy term using 10^(L/10).45- Sum the three linear energy terms.46- Convert back to dB using L_total = 10 log10(sum of linear terms).47- Identify the dominant source as the highest individual SPL.48 49## Output Format50 51Show 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:52 53```json54{55 "total_linear_energy": <numeric_value>,56 "combined_spl_db": <numeric_value>,57 "dominant_source_spl_db": <numeric_value>58}59```60 61Write your complete solution to `/workspace/output.md`.62

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.

Plant room sources

plant_room_sources

Three mechanical plant sources in a plant room

hospital-plant-roomcommercial-rooftop-plant
Parameter ranges
source_1_spl_db
65 – 95
source_2_spl_db
60 – 90
source_3_spl_db
55 – 85

Industrial noise sources

industrial_noise_sources

Three industrial process noise sources

water-treatment-plantindustrial-process-building
Parameter ranges
source_1_spl_db
75 – 110
source_2_spl_db
70 – 105
source_3_spl_db
65 – 100

Example task

water-treatment-plant-industrial-noise-sources-preview — hard difficulty, all inputs given.

Three industrial process noise sources. water-treatment-plant. Required outputs: total_linear_energy, combined_spl_db, dominant_source_spl_db

The model sees

Scenario context and visible inputs.

source_1_spl_db
75 to 110 dB
source_2_spl_db
70 to 105 dB
source_3_spl_db
65 to 100 dB

Executable tool: spl-log-sum_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.

{
  "total_linear_energy": <number>,
  "combined_spl_db": <number>,
  "dominant_source_spl_db": <number>
}
  • total_linear_energy · scored within ±3%
  • combined_spl_db · scored within ±3%
  • dominant_source_spl_db · scored within ±1%