LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …

civilwith-tool

Vertical Curve Design

Computes the minimum vertical curve radius and length required at railway grade transition points using R_v = V^2 / (12.96 * a_v) and L_v = (A/100) * R_v. Ensures vertical acceleration remains within passenger comfort and rolling stock safety limits per ARTC ETS-05-00 and AREMA Chapter 5.

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

Standards

AREMA MRE Chapter 5 ARTC ETS-05-00

How this task is generated

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

01
Template
The reusable contract shown on this page.
02
Scenario
An archetype and site context are sampled.
03
Difficulty tier
Inputs may be hidden at harder tiers.
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.

Initial grade pct
initial_grade_pct
Initial longitudinal grade g1 (positive = uphill)
-5 – 5 %
Final grade pct
final_grade_pct
Final longitudinal grade g2 (positive = uphill)
-5 – 5 %
Design speed
design_speed_km_h
Design operating speed V
20 – 300 km/h

Derived from scenario

Sampled from the scenario and inferable from its description.

Max vertical acceleration
max_vertical_acceleration_m_s2
Maximum acceptable vertical acceleration a_v for passenger comfort
Derived from the archetype scenario. Hidden at hard difficulty.
0.01 – 0.1 m/s²

Scored outputs

3 outputs

Algebraic grade difference pct

algebraic_grade_difference_pct

Algebraic grade difference A = |g1 - g2| (%)

Scores if within ±1% of the reference value.

Min vertical curve radius

min_vertical_curve_radius_m

Minimum vertical curve radius R_v (m)

Scores if within ±3% of the reference value.

Min vertical curve length

min_vertical_curve_length_m

Minimum vertical curve length L_v (m)

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.

easy

All inputs given

All parameters given, moderate gradients on mainline or freight corridors

medium

All inputs given

All parameters given, any corridor type including steep metro grades

hard

Some inputs hidden

Vertical acceleration hidden — agent must infer from corridor type and passenger comfort requirements

Hidden inputs

Max vertical acceleration m s2max_vertical_acceleration_m_s2

Prompt replacement text

The track is a {{ archetype.description }} ({{ archetype.site_context }})

Task bundle

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

/workspace

instruction.md
vertical-curve-design_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 civil engineer specializing in railway track geometry and vertical alignment design.2 3## Problem4 5Determine the algebraic grade difference, minimum vertical curve radius, and minimum vertical curve length for a railway grade transition.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Initial grade (g1) | {{ initial_grade_pct }} | % |12| Final grade (g2) | {{ final_grade_pct }} | % |13| Design speed (V) | {{ design_speed_km_h }} | km/h |14{% if max_vertical_acceleration_m_s2 is defined %}15| Max vertical acceleration (a_v) | {{ max_vertical_acceleration_m_s2 }} | m/s² |16{% endif %}17{% if archetype_description is defined %}18 19### Site Conditions20 21{{ archetype_description }}22{% endif %}23 24{% if tool_available %}25## Available Tool26 27A vertical curve design tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:28 29```bash30python3 /workspace/{{ meta.name }}_calc.py --help31```32 33You may use this tool to verify your calculations or compute values directly.34{% endif %}35 36## Required37 38Calculate the following:39 401. Algebraic grade difference A (%)412. Minimum vertical curve radius R_v (m)423. Minimum vertical curve length L_v (m)43 44## Applicable Standards45 46- ARTC Engineering Track Standard ETS-05-00 (Track Geometry)47- AREMA Manual for Railway Engineering, Chapter 5 (Track)48 49## Constraints50 51- No internet access is available. Work from engineering knowledge and the provided tool.52- Use the following formulae for vertical curve design:53  - Algebraic grade difference: A = |g1 - g2| where g1 and g2 are grades in percent (positive = uphill)54  - Minimum vertical curve radius: R_v = V² / (3.6² × a_v) where V is design speed in km/h and a_v is acceptable vertical acceleration in m/s²55  - Minimum vertical curve length: L_v = (A / 100) × R_v where A is in percent and R_v is in metres56{% if max_vertical_acceleration_m_s2 is not defined %}57- The acceptable vertical acceleration depends on the type of rail service and passenger comfort requirements58{% endif %}59 60## Output Format61 62Show 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:63 64```json65{66  "algebraic_grade_difference_pct": <numeric_value>,67  "min_vertical_curve_radius_m": <numeric_value>,68  "min_vertical_curve_length_m": <numeric_value>69}70```71 72Write your complete solution to `/workspace/output.md`.73

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.

Mainline passenger

mainline_passenger

Mainline passenger rail corridor with moderate speeds and comfort requirements

artc-north-south-corridorsydney-central-westmelbourne-geelong-mainline

Parameter ranges

initial_grade_pct: -2 – 2
final_grade_pct: -2 – 2
design_speed_km_h: 100 – 160
max_vertical_acceleration_m_s2: 0.03 – 0.05

Heavy haul freight

heavy_haul_freight

Heavy haul freight corridor with low speeds and relaxed comfort limits

artc-hunter-valley-coalpilbara-iron-ore-waqld-north-coast-freight

Parameter ranges

initial_grade_pct: -1.5 – 1.5
final_grade_pct: -1.5 – 1.5
design_speed_km_h: 60 – 100
max_vertical_acceleration_m_s2: 0.05 – 0.07

Urban metro

urban_metro

Urban metro or commuter rail with tight gradients and frequent grade transitions

sydney-metro-northwestmelbourne-metro-tunnelbrisbane-cross-river-rail

Parameter ranges

initial_grade_pct: -3.5 – 3.5
final_grade_pct: -3.5 – 3.5
design_speed_km_h: 40 – 80
max_vertical_acceleration_m_s2: 0.03 – 0.05

Branch line

branch_line

Regional branch line with moderate gradients and mixed traffic

nsw-north-coast-linevic-geelong-warrnamboolqld-western-line

Parameter ranges

initial_grade_pct: -2.5 – 2.5
final_grade_pct: -2.5 – 2.5
design_speed_km_h: 20 – 80
max_vertical_acceleration_m_s2: 0.04 – 0.07

Example task

artc-north-south-corridor-mainline-passenger-preview — hard difficulty, some inputs hidden.

Mainline passenger rail corridor with moderate speeds and comfort requirements. artc-north-south-corridor. Required outputs: algebraic_grade_difference_pct, min_vertical_curve_radius_m, min_vertical_curve_length_m

The model sees

Scenario context and visible inputs.

initial_grade_pct: -2 to 2 %
final_grade_pct: -2 to 2 %
design_speed_km_h: 100 to 160 km/h

Executable tool: vertical-curve-design_calc.py

The model must infer

Inputs withheld at this difficulty.

Max vertical acceleration m s2
max_vertical_acceleration_m_s2

Stand-in text in the prompt

The track is a {{ archetype.description }} ({{ archetype.site_context }})

The model must produce

The scored JSON answer schema.

{
  "algebraic_grade_difference_pct": <number>,
  "min_vertical_curve_radius_m": <number>,
  "min_vertical_curve_length_m": <number>
}

algebraic_grade_difference_pct · scored within ±1%
min_vertical_curve_radius_m · scored within ±3%
min_vertical_curve_length_m · scored within ±3%

Vertical Curve Design

How this task is generated

Template

Scenario

Difficulty tier

Task prompt

Parameters

Inputs

Scored outputs

Algebraic grade difference pct

Min vertical curve radius

Min vertical curve length

Difficulty

easy

medium

hard

Task bundle

Scenario archetypes

Mainline passenger

Heavy haul freight

Urban metro

Branch line

Example task

The model sees

The model must infer

The model must produce