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

Culvert Driveway Access Safety Continuity Package

Calculates task-owned synthetic SSC-01 driveway grade, culvert capacity, freeboard, roadway spread, and sight-distance metrics for one road access case.

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

Standards

AASHTO Green BookFHWA HEC-22culvert design workflow

Tags

accesscivilculvertdeterministicdrivewayroadsight-distance

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

23 inputs

Always given

Included directly in every task prompt.

23
Show 23 inputs

  • Driveway low level

    driveway_low_level_m

    ACCESS-SSC01-006 driveway low point level

    42.2 m

  • Driveway high level

    driveway_high_level_m

    ACCESS-SSC01-006 driveway tie-in high point level

    42.8 m

  • Driveway length

    driveway_length_m

    ACCESS-SSC01-006 driveway grade length

    18 m

  • Allowable driveway grade pct

    allowable_driveway_grade_pct

    MEMO-SSC01-006 allowable driveway grade

    8 %

  • Culvert diameter

    culvert_diameter_m

    CULV-SSC01-006 culvert diameter

    0.75 m

  • Culvert mannings n

    culvert_mannings_n

    CULV-SSC01-006 culvert Manning roughness

    0.013

  • Culvert slope pct

    culvert_slope_pct

    CULV-SSC01-006 culvert slope

    1 %

  • Design flow

    design_flow_m3_s

    CULV-SSC01-006 design flow

    0.82 m3/s

  • Tailwater level

    tailwater_level_m

    TAIL-SSC01-006 tailwater level

    41.95 m

  • Headwater base depth

    headwater_base_depth_m

    TAIL-SSC01-006 base headwater depth allowance

    0.42 m

  • Headwater loss factor

    headwater_loss_factor_m

    TAIL-SSC01-006 ratio-squared headwater loss factor

    0.25 m

  • Road edge level

    road_edge_level_m

    ACCESS-SSC01-006 road edge level to remain clear

    42.65 m

  • Minimum freeboard

    minimum_freeboard_m

    MEMO-SSC01-006 minimum freeboard

    0.1 m

  • Gutter flow

    gutter_flow_m3_s

    ACCESS-SSC01-006 gutter flow across driveway path

    0.12 m3/s

  • Cross slope pct

    cross_slope_pct

    ACCESS-SSC01-006 cross slope

    2 %

  • Longitudinal slope pct

    longitudinal_slope_pct

    ACCESS-SSC01-006 longitudinal slope

    1.2 %

  • Gutter mannings n

    gutter_mannings_n

    ACCESS-SSC01-006 gutter Manning roughness

    0.016

  • Allowable spread

    allowable_spread_m

    MEMO-SSC01-006 allowable spread across driveway path

    4 m

  • Access speed kmh

    access_speed_kmh

    SIGHT-SSC01-006 access sight-distance speed

    40 km/h

  • Sight reaction time

    sight_reaction_time_s

    SIGHT-SSC01-006 sight-distance reaction time

    2.5 s

  • Braking friction coefficient

    braking_friction_coefficient

    SIGHT-SSC01-006 braking friction coefficient

    0.35

  • Access grade pct

    access_grade_pct

    SIGHT-SSC01-006 signed access grade

    4 %

  • Available sight distance

    available_sight_distance_m

    SIGHT-SSC01-006 available sight distance

    120 m

Scored outputs

12 outputs

Driveway grade

driveway_grade_percent

Computed driveway grade

Scores if within ±3% of the reference value.

Driveway grade margin

driveway_grade_margin_percent

Allowable grade minus computed grade

Scores if within ±3% of the reference value.

Culvert capacity

culvert_capacity_m3_s

Full-pipe culvert capacity

Scores if within ±3% of the reference value.

Culvert capacity margin

culvert_capacity_margin_m3_s

Culvert capacity minus design flow

Scores if within ±3% of the reference value.

Headwater level

headwater_level_m

Synthetic headwater level

Scores if within ±3% of the reference value.

Freeboard

freeboard_m

Road edge level minus headwater level

Scores if within ±3% of the reference value.

Freeboard margin

freeboard_margin_m

Freeboard minus minimum freeboard

Scores if within ±3% of the reference value.

Roadway spread

roadway_spread_m

Triangular-gutter spread across the access path

Scores if within ±3% of the reference value.

Spread margin

spread_margin_m

Allowable spread minus computed spread

Scores if within ±3% of the reference value.

Sight distance required

sight_distance_required_m

Grade-adjusted sight distance required

Scores if within ±3% of the reference value.

Sight distance margin

sight_distance_margin_m

Available sight distance minus required sight distance

Scores if within ±3% of the reference value.

Overall pass score

overall_pass_score

1.0 when access grade, culvert, freeboard, spread, and sight-distance checks pass

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 source-pack values visible
medium:
Same deterministic source-pack values with package-level aggregation
hard:
Same deterministic source-pack values with cross-discipline handoff checks

Task bundle

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

/workspace

  • instruction.md
  • culvert-driveway-access-safety-continuity-package_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 road drainage and access-safety engineer checking a task-owned synthetic SSC-01 culvert, driveway access, and safety continuity package.2 3Use only the task-owned synthetic source pack values below for numeric grading. Road access, culvert, freeboard, and sight-distance workflows shape the context only; they are not extra data sources for this instance.4 5## Scene6 7- Product: `SSC-01-LH-06`8- Driveway access profile: `ACCESS-SSC01-006`9- Culvert schedule: `CULV-SSC01-006`10- Tailwater table: `TAIL-SSC01-006`11- Sight-distance basis: `SIGHT-SSC01-006`12- Access safety memo: `MEMO-SSC01-006`13 14## Source Values15 16- Driveway low/high levels and length: {{ driveway_low_level_m }} m, {{ driveway_high_level_m }} m, {{ driveway_length_m }} m17- Allowable driveway grade: {{ allowable_driveway_grade_pct }} %18- Culvert diameter, Manning n, slope, and design flow: {{ culvert_diameter_m }} m, {{ culvert_mannings_n }}, {{ culvert_slope_pct }} %, {{ design_flow_m3_s }} m3/s19- Tailwater level, base headwater depth, headwater loss factor: {{ tailwater_level_m }} m, {{ headwater_base_depth_m }} m, {{ headwater_loss_factor_m }} m20- Road edge level and minimum freeboard: {{ road_edge_level_m }} m, {{ minimum_freeboard_m }} m21- Gutter flow, cross slope, longitudinal slope, gutter Manning n, allowable spread: {{ gutter_flow_m3_s }} m3/s, {{ cross_slope_pct }} %, {{ longitudinal_slope_pct }} %, {{ gutter_mannings_n }}, {{ allowable_spread_m }} m22- Access speed, reaction time, braking friction, grade, and available sight distance: {{ access_speed_kmh }} km/h, {{ sight_reaction_time_s }} s, {{ braking_friction_coefficient }}, {{ access_grade_pct }} %, {{ available_sight_distance_m }} m23 24## Required Calculations25 26- Driveway grade is the level difference divided by driveway length.27- Culvert full-flow capacity uses Manning's equation for a circular full pipe.28- Headwater level is tailwater plus base depth plus a ratio-squared loss allowance.29- Freeboard is road edge level minus headwater level.30- Roadway spread uses the triangular-gutter relation with SI coefficient `0.376`.31- Sight distance uses reaction distance plus grade-adjusted braking distance.32- Overall pass score is `1.0` only when grade, culvert, freeboard, spread, and sight-distance margins pass.33 34Write a compact memo to `/workspace/output.md`. Include a source-boundary statement that this is a task-owned synthetic source pack. Preserve the source IDs above and state that the baseline source pack passes the current synthetic checks.35 36Do not claim authority approval, accepted project evidence, software export validity, full standards compliance, executable source-pack hardening, generated benchmark readiness, or benchmark readiness.37 38Include a fenced JSON block with exactly these numeric keys:39 40```json41{42 "driveway_grade_percent": <numeric_value>,43 "driveway_grade_margin_percent": <numeric_value>,44 "culvert_capacity_m3_s": <numeric_value>,45 "culvert_capacity_margin_m3_s": <numeric_value>,46 "headwater_level_m": <numeric_value>,47 "freeboard_m": <numeric_value>,48 "freeboard_margin_m": <numeric_value>,49 "roadway_spread_m": <numeric_value>,50 "spread_margin_m": <numeric_value>,51 "sight_distance_required_m": <numeric_value>,52 "sight_distance_margin_m": <numeric_value>,53 "overall_pass_score": <numeric_value>54}55```56

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.

Ssc01 culvert driveway access

ssc01_culvert_driveway_access

SSC-01 task-owned synthetic culvert driveway access safety package

culvert-driveway-access-safety-continuity
Parameter ranges

Example task

culvert-driveway-access-safety-continuity-ssc01-culvert-driveway-access-preview — hard difficulty, all inputs given.

SSC-01 task-owned synthetic culvert driveway access safety package. culvert-driveway-access-safety-continuity. Required outputs: driveway_grade_percent, driveway_grade_margin_percent, culvert_capacity_m3_s, culvert_capacity_margin_m3_s, headwater_level_m, freeboard_m

The model sees

Scenario context and visible inputs.

driveway_low_level_m
42.2 to 42.2 m
driveway_high_level_m
42.8 to 42.8 m
driveway_length_m
18 to 18 m
allowable_driveway_grade_pct
8 to 8 %
culvert_diameter_m
0.75 to 0.75 m
culvert_mannings_n
0.013 to 0.013
culvert_slope_pct
1 to 1 %
design_flow_m3_s
0.82 to 0.82 m3/s
tailwater_level_m
41.95 to 41.95 m
headwater_base_depth_m
0.42 to 0.42 m
headwater_loss_factor_m
0.25 to 0.25 m
road_edge_level_m
42.65 to 42.65 m
minimum_freeboard_m
0.1 to 0.1 m
gutter_flow_m3_s
0.12 to 0.12 m3/s
cross_slope_pct
2 to 2 %
longitudinal_slope_pct
1.2 to 1.2 %
gutter_mannings_n
0.016 to 0.016
allowable_spread_m
4 to 4 m
access_speed_kmh
40 to 40 km/h
sight_reaction_time_s
2.5 to 2.5 s
braking_friction_coefficient
0.35 to 0.35
access_grade_pct
4 to 4 %
available_sight_distance_m
120 to 120 m

Executable tool: culvert-driveway-access-safety-continuity-package_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.

{
  "driveway_grade_percent": <number>,
  "driveway_grade_margin_percent": <number>,
  "culvert_capacity_m3_s": <number>,
  "culvert_capacity_margin_m3_s": <number>,
  "headwater_level_m": <number>,
  "freeboard_m": <number>,
  "freeboard_margin_m": <number>,
  "roadway_spread_m": <number>,
  "spread_margin_m": <number>,
  "sight_distance_required_m": <number>,
  "sight_distance_margin_m": <number>,
  "overall_pass_score": <number>
}
  • driveway_grade_percent · scored within ±3%
  • driveway_grade_margin_percent · scored within ±3%
  • culvert_capacity_m3_s · scored within ±3%
  • culvert_capacity_margin_m3_s · scored within ±3%
  • headwater_level_m · scored within ±3%
  • freeboard_m · scored within ±3%
  • freeboard_margin_m · scored within ±3%
  • roadway_spread_m · scored within ±3%
  • spread_margin_m · scored within ±3%
  • sight_distance_required_m · scored within ±3%
  • sight_distance_margin_m · scored within ±3%
  • overall_pass_score · scored within ±1%