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

Visibility Criterion

Calculates smoke visibility from extinction coefficient and an explicit visibility constant, then compares the result with a minimum visibility criterion. The template reports visibility, margin, utilisation, and a numeric criterion flag.

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

Standards

ISO 13571SFPE Handbook

Tags

deterministicfire-safetymechanicaltenabilityvisibility

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

  • Extinction coefficient m inv

    extinction_coefficient_m_inv

    Smoke extinction coefficient

    0.001 – 10 1/m

  • Visibility constant

    visibility_constant

    Visibility constant for the target sign or object contrast

    1 – 20

  • Minimum visibility

    minimum_visibility_m

    Minimum acceptable visibility

    0.1 – 100 m

Scored outputs

4 outputs

Visibility

visibility_m

Calculated visibility

Scores if within ±3% of the reference value.

Visibility margin

visibility_margin_m

Visibility margin above minimum criterion

Scores if within ±3% of the reference value.

Visibility utilisation ratio

visibility_utilisation_ratio

Minimum visibility divided by calculated visibility

Scores if within ±3% of the reference value.

Criterion satisfied

criterion_satisfied

Numeric flag where 1 means visibility meets the criterion

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 an egress route
medium:
All parameters given across tenability settings
hard:
All parameters given for large volume spaces

Task bundle

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

/workspace

  • instruction.md
  • visibility-criterion_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 fire safety engineer specializing in smoke tenability checks.2 3## Problem4 5Calculate smoke visibility from extinction coefficient and compare it with an explicit minimum visibility criterion.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Extinction coefficient | {{ extinction_coefficient_m_inv }} | 1/m |12| Visibility constant | {{ visibility_constant }} | - |13| Minimum visibility | {{ minimum_visibility_m }} | m |14 15{% if archetype_description is defined %}16### Tenability Context17 18{{ archetype_description }}19{% endif %}20 21{% if tool_available %}22## Available Tool23 24A visibility criterion calculation 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. Visibility in metres382. Visibility margin above the minimum criterion393. Visibility utilisation ratio404. Numeric pass flag, where 1 means the criterion is satisfied41 42## Constraints43 44- No internet access is available. Work from engineering knowledge and the provided tool.45- Use visibility = visibility constant / extinction coefficient.46- Use only the explicit minimum visibility criterion provided.47 48## Output Format49 50Show 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:51 52```json53{54 "visibility_m": <numeric_value>,55 "visibility_margin_m": <numeric_value>,56 "visibility_utilisation_ratio": <numeric_value>,57 "criterion_satisfied": <numeric_value>58}59```60 61Write your complete solution to `/workspace/output.md`.62 63

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.

Egress route

egress_route

Egress route smoke visibility check

egress-routesmoke-control-zone
Parameter ranges
extinction_coefficient_m_inv
0.05 – 2
visibility_constant
3 – 10
minimum_visibility_m
5 – 15

Large volume space

large_volume_space

Large volume space smoke visibility check

atriumstation-concourse
Parameter ranges
extinction_coefficient_m_inv
0.02 – 1
visibility_constant
3 – 10
minimum_visibility_m
10 – 30

Example task

atrium-large-volume-space-preview — hard difficulty, all inputs given.

Large volume space smoke visibility check. atrium. Required outputs: visibility_m, visibility_margin_m, visibility_utilisation_ratio, criterion_satisfied

The model sees

Scenario context and visible inputs.

extinction_coefficient_m_inv
0.02 to 1 1/m
visibility_constant
3 to 10 -
minimum_visibility_m
10 to 30 m

Executable tool: visibility-criterion_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.

{
  "visibility_m": <number>,
  "visibility_margin_m": <number>,
  "visibility_utilisation_ratio": <number>,
  "criterion_satisfied": <number>
}
  • visibility_m · scored within ±3%
  • visibility_margin_m · scored within ±3%
  • visibility_utilisation_ratio · scored within ±3%
  • criterion_satisfied · scored within ±1%