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

Excavation Dewatering Temporary Power Package

Calculates source-bound excavation and dewatering metrics from a deterministic SSC-07 task-owned source pack. The template combines exit-gradient safety, rapid-drawdown screening, pump power, temporary generator capacity, battery runtime, and uplift pressure checks.

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

Standards

exit gradient screeningpump power calculationrapid drawdown slope screening

Tags

deterministicdewateringexcavationgroundtemporary-poweruplift

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

16 inputs

Always given

Included directly in every task prompt.

16
Show 16 inputs

  • Water head above base

    water_head_above_base_m

    GW-07-DEWATER-01 water head above excavation base

    3.2 m

  • Seepage path

    seepage_path_m

    EXC-07-SECTION-01 seepage path length

    14 m

  • Critical gradient

    critical_gradient

    GW-07-DEWATER-01 critical exit gradient

    0.9

  • Slope angle deg

    slope_angle_deg

    EXC-07-SECTION-01 temporary slope angle

    26 degrees

  • Friction angle deg

    friction_angle_deg

    EXC-07-SECTION-01 drained friction angle

    34 degrees

  • Pore pressure ratio

    pore_pressure_ratio

    GW-07-DEWATER-01 rapid-drawdown pore pressure ratio

    0.18

  • Pump flow

    pump_flow_m3_s

    PUMP-07-TEMP-01 pump flow per pump

    0.024 m3/s

  • Pump head

    pump_head_m

    PUMP-07-TEMP-01 dewatering pump head

    12 m

  • Pump efficiency

    pump_efficiency

    PUMP-07-TEMP-01 pump efficiency

    0.62

  • Pump

    pump_count

    PUMP-07-TEMP-01 operating pump count

    2 count

  • Controls load

    controls_load_kw

    PWR-07-TEMP-01 controls and monitoring load

    1.5 kW

  • Generator capacity

    generator_capacity_kw

    PWR-07-TEMP-01 temporary generator capacity

    18 kW

  • Battery capacity

    battery_capacity_kwh

    PWR-07-TEMP-01 backup battery capacity

    25 kWh

  • Autonomy load

    autonomy_load_kw

    PWR-07-TEMP-01 critical autonomy load

    3 kW

  • Required runtime

    required_runtime_h

    MEMO-07-TEMP-01 required monitoring runtime

    6 h

  • Slab resisting pressure

    slab_resisting_pressure_kpa

    EXC-07-SECTION-01 slab resisting pressure

    42 kPa

Scored outputs

11 outputs

Exit gradient

exit_gradient

Water head above base divided by seepage path

Scores if within ±3% of the reference value.

Exit gradient fs

exit_gradient_fs

Critical gradient divided by exit gradient

Scores if within ±3% of the reference value.

Rapid drawdown fs

rapid_drawdown_fs

Rapid-drawdown slope factor of safety

Scores if within ±3% of the reference value.

Pump power

pump_power_kw

Per-pump hydraulic input power

Scores if within ±3% of the reference value.

Temporary power

temporary_power_kw

Pump power for all pumps plus controls load

Scores if within ±3% of the reference value.

Generator margin

generator_margin_kw

Generator capacity minus temporary power

Scores if within ±3% of the reference value.

Battery runtime h

battery_runtime_h

Battery runtime at autonomy load

Scores if within ±3% of the reference value.

Battery runtime margin h

battery_runtime_margin_h

Battery runtime minus required runtime

Scores if within ±3% of the reference value.

Uplift pressure

uplift_pressure_kpa

Water unit weight times water head above base

Scores if within ±3% of the reference value.

Uplift margin

uplift_margin_kpa

Slab resisting pressure minus uplift pressure

Scores if within ±3% of the reference value.

Overall pass score

overall_pass_score

1.0 when seepage, slope, power, runtime, and uplift checks pass

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.

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 given for the SSC-07 excavation dewatering package
medium:
All source-pack values given for the SSC-07 excavation dewatering package
hard:
All source-pack values given for the SSC-07 excavation dewatering package

Task bundle

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

/workspace

  • instruction.md
  • excavation-dewatering-temporary-power-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 checking a task-owned synthetic SSC-07 excavation/dewatering and temporary power safety package for `SSC-07-LH-04`.2 3Use only the task-owned synthetic source pack values shown below for numeric grading.4 5## Source Pack6 7- Excavation section: `EXC-07-SECTION-01`8- Groundwater record: `GW-07-DEWATER-01`9- Temporary pump schedule: `PUMP-07-TEMP-01`10- Temporary power layout: `PWR-07-TEMP-01`11- Temporary works memo: `MEMO-07-TEMP-01`12 13## Source Values14 15| Item | Value |16|---|---:|17| Water head above base | {{ water_head_above_base_m }} m |18| Seepage path | {{ seepage_path_m }} m |19| Critical gradient | {{ critical_gradient }} |20| Excavation slope angle | {{ slope_angle_deg }} degrees |21| Soil friction angle | {{ friction_angle_deg }} degrees |22| Pore pressure ratio | {{ pore_pressure_ratio }} |23| Pump flow | {{ pump_flow_m3_s }} m3/s |24| Pump head | {{ pump_head_m }} m |25| Pump efficiency | {{ pump_efficiency }} |26| Pump count | {{ pump_count }} |27| Controls load | {{ controls_load_kw }} kW |28| Generator capacity | {{ generator_capacity_kw }} kW |29| Battery capacity | {{ battery_capacity_kwh }} kWh |30| Autonomy load | {{ autonomy_load_kw }} kW |31| Required runtime | {{ required_runtime_h }} h |32| Slab resisting pressure | {{ slab_resisting_pressure_kpa }} kPa |33 34Compute exit-gradient safety, rapid-drawdown slope safety, pump power, temporary power, generator margin, battery runtime, uplift pressure, and uplift margin.35 36Write a compact source-bound temporary works memo to `/workspace/output.md`. Preserve the source IDs above. Include a source-boundary statement that this is a task-owned synthetic source pack.37 38Do not claim authority approval, accepted project evidence, executable real source-pack parsing, full standards compliance, generated benchmark readiness, or benchmark readiness.39 40Include a fenced JSON block with exactly these numeric keys:41 42```json43{44 "exit_gradient": <numeric_value>,45 "exit_gradient_fs": <numeric_value>,46 "rapid_drawdown_fs": <numeric_value>,47 "pump_power_kw": <numeric_value>,48 "temporary_power_kw": <numeric_value>,49 "generator_margin_kw": <numeric_value>,50 "battery_runtime_h": <numeric_value>,51 "battery_runtime_margin_h": <numeric_value>,52 "uplift_pressure_kpa": <numeric_value>,53 "uplift_margin_kpa": <numeric_value>,54 "overall_pass_score": <numeric_value>55}56```57

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.

Ssc07 excavation dewatering case

ssc07_excavation_dewatering_case

Ground investigation package for one excavation, dewatering, and temporary power check

excavation-dewateringtemporary-power-handoff
Parameter ranges
water_head_above_base_m
3.2
seepage_path_m
14
critical_gradient
0.9
slope_angle_deg
26
friction_angle_deg
34
pore_pressure_ratio
0.18
pump_flow_m3_s
0.024
pump_head_m
12
pump_efficiency
0.62
pump_count
2
controls_load_kw
1.5
generator_capacity_kw
18
battery_capacity_kwh
25
autonomy_load_kw
3
required_runtime_h
6
slab_resisting_pressure_kpa
42

Example task

excavation-dewatering-ssc07-excavation-dewatering-case-preview — hard difficulty, all inputs given.

Ground investigation package for one excavation, dewatering, and temporary power check. excavation-dewatering. Required outputs: exit_gradient, exit_gradient_fs, rapid_drawdown_fs, pump_power_kw, temporary_power_kw, generator_margin_kw

The model sees

Scenario context and visible inputs.

water_head_above_base_m
3.2 to 3.2 m
seepage_path_m
14 to 14 m
critical_gradient
0.9 to 0.9
slope_angle_deg
26 to 26 degrees
friction_angle_deg
34 to 34 degrees
pore_pressure_ratio
0.18 to 0.18
pump_flow_m3_s
0.024 to 0.024 m3/s
pump_head_m
12 to 12 m
pump_efficiency
0.62 to 0.62
pump_count
2 to 2 count
controls_load_kw
1.5 to 1.5 kW
generator_capacity_kw
18 to 18 kW
battery_capacity_kwh
25 to 25 kWh
autonomy_load_kw
3 to 3 kW
required_runtime_h
6 to 6 h
slab_resisting_pressure_kpa
42 to 42 kPa

Executable tool: excavation-dewatering-temporary-power-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.

{
  "exit_gradient": <number>,
  "exit_gradient_fs": <number>,
  "rapid_drawdown_fs": <number>,
  "pump_power_kw": <number>,
  "temporary_power_kw": <number>,
  "generator_margin_kw": <number>,
  "battery_runtime_h": <number>,
  "battery_runtime_margin_h": <number>,
  "uplift_pressure_kpa": <number>,
  "uplift_margin_kpa": <number>,
  "overall_pass_score": <number>
}
  • exit_gradient · scored within ±3%
  • exit_gradient_fs · scored within ±3%
  • rapid_drawdown_fs · scored within ±3%
  • pump_power_kw · scored within ±3%
  • temporary_power_kw · scored within ±3%
  • generator_margin_kw · scored within ±3%
  • battery_runtime_h · scored within ±3%
  • battery_runtime_margin_h · scored within ±3%
  • uplift_pressure_kpa · scored within ±3%
  • uplift_margin_kpa · scored within ±3%
  • overall_pass_score · scored within ±3%