Line speed m s
line_speed_m_s
Line speed converted to m/s
Scores if within ±1% of the reference value.
LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …
electricalwith-tool
Signal Sighting Distance
Calculates the minimum signal sighting distance required for a train driver to perceive, react, and brake to a stop. The reduced kinematic method combines reaction distance with braking distance adjusted for track gradient.
with-tool: The model is given an executable Python calculator script.
Standards
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.
Maximum line speed kmh
maximum_line_speed_kmh
Maximum line speed
5 – 250 km/hService braking rate
service_braking_rate_m_s2
Service braking rate
0.2 – 2 m/s2Driver reaction time
driver_reaction_time_s
Driver perception-reaction time
0 – 10 s
Hidden at higher difficulty
Visible in easier tasks and withheld in one or more harder tiers.
Track gradient pct
track_gradient_pct
Track gradient, positive for upgrade and negative for downgrade
Hidden at hard difficulty.
-5 – 5 %
Scored outputs
5 outputs
Reaction distance
reaction_distance_m
Distance travelled during driver reaction
Scores if within ±3% of the reference value.
Grade adjusted braking rate m s2
grade_adjusted_braking_rate_m_s2
Braking rate adjusted for track gradient
Scores if within ±3% of the reference value.
Braking distance
braking_distance_m
Kinematic braking distance
Scores if within ±3% of the reference value.
Required sighting distance
required_sighting_distance_m
Total required signal sighting distance
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
Metro signal with all inputs visible
medium
All inputs given
Metro or mainline signal
hard
Some inputs hidden
Track gradient hidden in alignment context
Hidden inputs
- Track gradient pcttrack_gradient_pct
Prompt replacement text
Use the track gradient implied by {{ archetype.description }}.
Track gradient pct restricted to: -1
Task bundle
The exact instruction and parameter contract used to generate this task, pinned to the published library source.
/workspace
- instruction.md
- signal-sighting-distance_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 rail signalling engineer calculating required signal sighting distance.2 3## Given4 5| Parameter | Value | Unit |6|-----------|-------|------|7| Maximum line speed | {{ maximum_line_speed_kmh }} | km/h |8| Service braking rate | {{ service_braking_rate_m_s2 }} | m/s2 |9| Driver reaction time | {{ driver_reaction_time_s }} | s |10{% if track_gradient_pct is defined %}11| Track gradient | {{ track_gradient_pct }} | % |12{% endif %}13 14## Constraints15 16- Convert line speed from km/h to m/s.17- Reaction distance equals speed times reaction time.18- Adjust braking rate using `a_adjusted = a + 9.81 x grade_decimal`.19- Positive grade is upgrade and negative grade is downgrade.20- Braking distance equals `v^2 / (2 a_adjusted)`.21- Required sighting distance equals reaction distance plus braking distance.22 23## Output Format24 25Include a JSON block with exactly these keys:26 27```json28{29 "line_speed_m_s": <numeric_value>,30 "reaction_distance_m": <numeric_value>,31 "grade_adjusted_braking_rate_m_s2": <numeric_value>,32 "braking_distance_m": <numeric_value>,33 "required_sighting_distance_m": <numeric_value>34}35```36 37Write your complete solution to `/workspace/output.md`.38 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.
Metro signal
metro_signal
Metro or suburban signal sighting check
metro-linesuburban-corridor
Parameter ranges
- maximum_line_speed_kmh
- 30 – 90
- service_braking_rate_m_s2
- 0.7 – 1.2
- driver_reaction_time_s
- 1.5 – 3
- track_gradient_pct
- -2 – 2
Mainline signal
mainline_signal
Mainline signal sighting check
regional-mainlinefreight-corridor
Parameter ranges
- maximum_line_speed_kmh
- 80 – 160
- service_braking_rate_m_s2
- 0.4 – 1
- driver_reaction_time_s
- 2 – 5
- track_gradient_pct
- -3 – 3
Example task
regional-mainline-mainline-signal-preview — hard difficulty, some inputs hidden.
Mainline signal sighting check. regional-mainline. Required outputs: line_speed_m_s, reaction_distance_m, grade_adjusted_braking_rate_m_s2, braking_distance_m, required_sighting_distance_m
The model sees
Scenario context and visible inputs.
- maximum_line_speed_kmh
- 80 to 160 km/h
- service_braking_rate_m_s2
- 0.4 to 1 m/s2
- driver_reaction_time_s
- 2 to 5 s
Executable tool: signal-sighting-distance_calc.py
The model must infer
Inputs withheld at this difficulty.
Track gradient pct
track_gradient_pct
Stand-in text in the prompt
Use the track gradient implied by {{ archetype.description }}.
The model must produce
The scored JSON answer schema.
{
"line_speed_m_s": <number>,
"reaction_distance_m": <number>,
"grade_adjusted_braking_rate_m_s2": <number>,
"braking_distance_m": <number>,
"required_sighting_distance_m": <number>
}- line_speed_m_s · scored within ±1%
- reaction_distance_m · scored within ±3%
- grade_adjusted_braking_rate_m_s2 · scored within ±3%
- braking_distance_m · scored within ±3%
- required_sighting_distance_m · scored within ±3%