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

Rule Length

Calculates the Rule length L used throughout the IACS Harmonised Common Structural Rules for Bulk Carriers and Oil Tankers (CSR-H). L is the distance, in m, measured on the waterline at the scantling draught T_SC from the forward side of the stem to the centre of the rudder stock, and is clamped to lie between 96% and 97% of the extreme length on the waterline at T_SC. Ships without a rudder stock (e.g. fitted with azimuth thrusters) take L equal to 97% of the extreme length. This is the first principal-particulars quantity computed for any CSR-H scantling assessment.

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

Standards

IACS CSR-H (Common Structural Rules) 01 JUL 2025, Pt 1 Ch 1 Sec 4

Tags

csr-hdeterministiciacsmaritimeprincipal-particularsrule-length

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.

1

  • Extreme length on waterline at TSC

    extreme_length_on_waterline_at_TSC_m

    Extreme length on the waterline at the scantling draught T_SC

    90 – 450 m

Hidden at higher difficulty

Visible in easier tasks and withheld in one or more harder tiers.

1

  • Has rudder stock

    has_rudder_stock

    Whether the ship has a rudder stock (false for ships fitted with azimuth thrusters and similar)

    Hidden at hard difficulty.

    truefalse

Optional

Used only when the sampled task needs this part of the contract.

1

  • Stem to rudder stock distance

    stem_to_rudder_stock_distance_m

    Distance measured on the waterline at T_SC from the forward side of the stem to the centre of the rudder stock

    Optional input. Hidden at hard difficulty.

    85 – 440 m

Scored outputs

1 output

Rule length L

rule_length_L_m

Rule length L (m)

Scores if within ±0.5% 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

Rudder stock ship with measured distance between the 96%/97% bounds

Has rudder stock restricted to: true

Clamp regime restricted to: within_bounds

medium

All inputs given

Rudder stock ship where the measured distance falls outside the 96%/97% band, so the clamp bites

Has rudder stock restricted to: true

Clamp regime restricted to: lower_bound_bites, upper_bound_bites

hard

Some inputs hidden

has_rudder_stock hidden; agent must infer the azimuth-thruster case from the vessel description

Hidden inputs

  • Has rudder stockhas_rudder_stock
  • Stem to rudder stock distancestem_to_rudder_stock_distance_m

Prompt replacement text

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

Has rudder stock restricted to: false

Clamp regime restricted to: no_rudder_stock

Task bundle

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

/workspace

  • instruction.md
  • rule-length_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 naval architect specializing in classification society rule compliance.2 3## Problem4 5Calculate the IACS Rule length L for a ship under the Harmonised Common Structural Rules (CSR-H).6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Extreme length on the waterline at T_SC | {{ extreme_length_on_waterline_at_TSC_m }} | m |12{% if has_rudder_stock is defined %}13| Has rudder stock | {{ has_rudder_stock }} | - |14{% endif %}15{% if stem_to_rudder_stock_distance_m is defined %}16| Distance from stem to rudder stock centre, on the waterline at T_SC | {{ stem_to_rudder_stock_distance_m }} | m |17{% endif %}18{% if archetype_description is defined %}19 20### Vessel Context21 22{{ archetype_description }}23{% endif %}24 25{% if tool_available %}26## Available Tool27 28A Rule length calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:29 30```bash31python3 /workspace/{{ meta.name }}_calc.py --help32```33 34You may use this tool to verify your calculations or compute values directly.35{% endif %}36 37## Required38 39Calculate the following:40 411. Rule length L (m)42 43## Applicable Standards44 45- IACS Harmonised Common Structural Rules (CSR-H), edition 01 JUL 2025, Pt 1 Ch 1 Sec 4 §3.1.146 47## Constraints48 49- No internet access is available. Work from engineering knowledge and the provided tool.50- Quote from Pt 1 Ch 1 Sec 4 §3.1.1: "The Rule length L is the distance, in m, measured on the waterline at the scantling draught T_SC from the forward side of the stem to the centre of the rudder stock. L is to be not less than 96% and need not exceed 97% of the extreme length on the waterline at the scantling draught T_SC. In ships without rudder stock (e.g. ships fitted with azimuth thrusters), the Rule length L is to be taken equal to 97% of the extreme length on the waterline at the scantling draught T_SC. In ships with unusual stem or stern arrangements, the Rule length is considered on a case-by-case basis."51- If the ship has a rudder stock, clamp the measured stem-to-rudder-stock distance to the range [0.96 x extreme length, 0.97 x extreme length].52- If the ship has no rudder stock (e.g. azimuth thrusters), L = 0.97 x extreme length on the waterline at T_SC.53- Ships with unusual stem or stern arrangements are out of scope for this calculation — assume conventional arrangements unless stated otherwise.54 55## Output Format56 57Show your step-by-step working in Markdown, including formulas and intermediate calculations. At the end of your solution, include a JSON block with your final answer in exactly this format:58 59```json60{61 "rule_length_L_m": <numeric_value>62}63```64 65Write your complete solution to `/workspace/output.md`.66

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.

Conventional within bounds

conventional_within_bounds

Conventional single-screw ship with a rudder stock; measured distance falls inside the 96%/97% band

bulk-carrier-panamaxproduct-tanker-mrgeneral-cargo-handysize
Parameter ranges
extreme_length_on_waterline_at_TSC_m
200 – 200.5
stem_to_rudder_stock_distance_m
192.6 – 193.8

Conventional lower bites

conventional_lower_bites

Conventional single-screw ship with a rudder stock; measured distance is short, so the 96% lower bound bites

bulk-carrier-panamaxproduct-tanker-mrgeneral-cargo-handysize
Parameter ranges
extreme_length_on_waterline_at_TSC_m
150 – 300
stem_to_rudder_stock_distance_m
80 – 140

Conventional upper bites

conventional_upper_bites

Conventional single-screw ship with a rudder stock; measured distance is long, so the 97% upper bound bites

bulk-carrier-panamaxproduct-tanker-mrgeneral-cargo-handysize
Parameter ranges
extreme_length_on_waterline_at_TSC_m
220 – 224
stem_to_rudder_stock_distance_m
217.5 – 220

Azimuth thruster ship

azimuth_thruster_ship

Ship fitted with azimuth thrusters and no rudder stock

shuttle-tanker-dpoffshore-support-vesselharbour-tug-azimuth
Parameter ranges
extreme_length_on_waterline_at_TSC_m
100 – 250

Example task

shuttle-tanker-dp-azimuth-thruster-ship-preview — hard difficulty, some inputs hidden.

Ship fitted with azimuth thrusters and no rudder stock. shuttle-tanker-dp. Required outputs: rule_length_L_m

The model sees

Scenario context and visible inputs.

extreme_length_on_waterline_at_TSC_m
100 to 250 m

Executable tool: rule-length_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Has rudder stock

    has_rudder_stock

  • Stem to rudder stock distance

    stem_to_rudder_stock_distance_m

Stand-in text in the prompt

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

The model must produce

The scored JSON answer schema.

{
  "rule_length_L_m": <number>
}
  • rule_length_L_m · scored within ±0.5%