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

Temporary Fuel Chemical Bund Fire Interface Package

Calculates source-bound temporary bund volume, fire HRR, visibility margin, NAC load, alarm battery, drain isolation, and spill response metrics from a deterministic SSC-16 task-owned source pack.

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

Standards

alarm load workflowfire interface workflowhazardous storage workflow

Tags

alarmbundconstructiondeterministicfiremechanicalsite-safety

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

20 inputs

Always given

Included directly in every task prompt.

20
Show 20 inputs

  • Largest container

    largest_container_l

    INV-16-FUEL-06 largest temporary storage container

    2500 L

  • Rainfall allowance

    rainfall_allowance_l

    BUND-16-DETAIL-06 rainfall allowance

    600 L

  • Provided bund volume

    provided_bund_volume_l

    BUND-16-DETAIL-06 provided bund volume

    3600 L

  • Fire growth alpha

    fire_growth_alpha_kw_s2

    FIRE-16-NOTE-06 t-squared fire growth alpha

    0.0469 kW/s2

  • Design fire time

    design_fire_time_s

    FIRE-16-NOTE-06 design fire time

    240 s

  • Provided visibility

    provided_visibility_m

    FIRE-16-NOTE-06 provided site visibility

    14 m

  • Required visibility

    required_visibility_m

    FIRE-16-NOTE-06 required visibility

    10 m

  • Horn

    horn_count

    ALARM-16-LOAD-06 horn count

    6 count

  • Horn current

    horn_current_a

    ALARM-16-LOAD-06 horn current

    0.075 A

  • Strobe

    strobe_count

    ALARM-16-LOAD-06 strobe count

    4 count

  • Strobe current

    strobe_current_a

    ALARM-16-LOAD-06 strobe current

    0.11 A

  • Panel current

    panel_current_a

    ALARM-16-LOAD-06 panel current

    0.2 A

  • Nac supply capacity

    nac_supply_capacity_a

    ALARM-16-LOAD-06 NAC supply capacity

    2 A

  • Alarm load

    alarm_load_w

    ALARM-16-LOAD-06 alarm standby load

    95 W

  • Alarm runtime

    alarm_runtime_h

    ALARM-16-LOAD-06 alarm runtime

    24 h

  • Alarm battery capacity

    alarm_battery_capacity_kwh

    ALARM-16-LOAD-06 alarm battery capacity

    3 kWh

  • Isolated drain

    isolated_drain_count

    BUND-16-DETAIL-06 isolated drain count

    3 count

  • Total drain

    total_drain_count

    BUND-16-DETAIL-06 total drain count

    3 count

  • Allowed spill response

    allowed_spill_response_min

    STORE-16-LAYOUT-06 allowed spill response time

    30 min

  • Planned spill response

    planned_spill_response_min

    STORE-16-LAYOUT-06 planned spill response time

    18 min

Scored outputs

11 outputs

Required bund volume l

required_bund_volume_l

Required temporary bund volume

Scores if within ±3% of the reference value.

Bund volume margin l

bund_volume_margin_l

Provided bund volume minus required bund volume

Scores if within ±3% of the reference value.

Fire hrr

fire_hrr_kw

T-squared design fire heat release rate

Scores if within ±3% of the reference value.

Visibility margin

visibility_margin_m

Provided visibility minus required visibility

Scores if within ±3% of the reference value.

Nac current

nac_current_a

Total notification appliance circuit current

Scores if within ±0.3% of the reference value.

Nac headroom

nac_headroom_a

NAC supply capacity minus current

Scores if within ±0.3% of the reference value.

Alarm battery required kwh

alarm_battery_required_kwh

Alarm battery energy required

Scores if within ±3% of the reference value.

Alarm battery margin kwh

alarm_battery_margin_kwh

Alarm battery capacity minus required battery energy

Scores if within ±3% of the reference value.

Drain isolation fraction

drain_isolation_fraction

Fraction of drains isolated for temporary storage

Scores if within ±0.1% of the reference value.

Spill response margin min

spill_response_margin_min

Allowed spill response time minus planned response time

Scores if within ±3% of the reference value.

Overall pass score

overall_pass_score

1.0 when bund, visibility, alarm, drain, and response checks pass

Scores if within ±0.1% 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 given for the SSC-16 temporary bund fire interface package
medium:
All source-pack values given for the SSC-16 temporary bund fire interface package
hard:
All source-pack values given for the SSC-16 temporary bund fire interface package

Task bundle

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

/workspace

  • instruction.md
  • temporary-fuel-chemical-bund-fire-interface-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 construction site safety engineer checking a task-owned synthetic SSC-16 package for temporary fuel/chemical storage bunding, drainage isolation, fire mode, alarm load, and spill response.2 3Use only the task-owned synthetic source pack values shown below for numeric grading. External hazardous-material storage, fire interface, alarm load, and construction inspection workflows shape the context only; they are not extra data sources for this instance.4 5## Source Objects6 7- Product: `SSC-16-LH-06`8- Storage layout: `STORE-16-LAYOUT-06`9- Fuel/chemical inventory: `INV-16-FUEL-06`10- Bund detail: `BUND-16-DETAIL-06`11- Fire/hazard note: `FIRE-16-NOTE-06`12- Monitoring/alarm load schedule: `ALARM-16-LOAD-06`13- Site safety memo: `MEMO-16-SAFETY-06`14 15## Source Values16 17| Item | Value |18|------|-------|19| Largest container | {{ largest_container_l }} L |20| Rainfall allowance | {{ rainfall_allowance_l }} L |21| Provided bund volume | {{ provided_bund_volume_l }} L |22| Fire growth alpha | {{ fire_growth_alpha_kw_s2 }} kW/s2 |23| Design fire time | {{ design_fire_time_s }} s |24| Provided visibility | {{ provided_visibility_m }} m |25| Required visibility | {{ required_visibility_m }} m |26| Horn count | {{ horn_count }} |27| Horn current | {{ horn_current_a }} A |28| Strobe count | {{ strobe_count }} |29| Strobe current | {{ strobe_current_a }} A |30| Panel current | {{ panel_current_a }} A |31| NAC supply capacity | {{ nac_supply_capacity_a }} A |32| Alarm load | {{ alarm_load_w }} W |33| Alarm runtime | {{ alarm_runtime_h }} h |34| Alarm battery capacity | {{ alarm_battery_capacity_kwh }} kWh |35| Isolated drains | {{ isolated_drain_count }} |36| Total drains | {{ total_drain_count }} |37| Allowed spill response time | {{ allowed_spill_response_min }} min |38| Planned spill response time | {{ planned_spill_response_min }} min |39 40## Required Checks41 42- Required bund volume equals largest container plus rainfall allowance for this source pack.43- Fire HRR equals alpha times design fire time squared.44- NAC current is the sum of horns, strobes, and panel current.45- Alarm battery energy covers the alarm load over the required runtime.46- Drain isolation fraction confirms every listed drain is isolated.47 48## Output Format49 50Write a compact memo to `/workspace/output.md`. Include a source-boundary statement that this is a task-owned synthetic source pack, preserve the source object IDs above, and state whether the baseline checks pass.51 52Do not claim authority approval, accepted project evidence, software export validity, full standards compliance, executable source-pack hardening, generated benchmark readiness, or benchmark readiness.53 54Include a fenced JSON block with exactly these numeric keys:55 56```json57{58 "required_bund_volume_l": <numeric_value>,59 "bund_volume_margin_l": <numeric_value>,60 "fire_hrr_kw": <numeric_value>,61 "visibility_margin_m": <numeric_value>,62 "nac_current_a": <numeric_value>,63 "nac_headroom_a": <numeric_value>,64 "alarm_battery_required_kwh": <numeric_value>,65 "alarm_battery_margin_kwh": <numeric_value>,66 "drain_isolation_fraction": <numeric_value>,67 "spill_response_margin_min": <numeric_value>,68 "overall_pass_score": <numeric_value>69}70```71

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.

Ssc16 bund fire case

ssc16_bund_fire_case

Temporary fuel chemical bund and fire interface case

Parameter ranges
largest_container_l
2500
rainfall_allowance_l
600
provided_bund_volume_l
3600
fire_growth_alpha_kw_s2
0.0469
design_fire_time_s
240
provided_visibility_m
14
required_visibility_m
10
horn_count
6
horn_current_a
0.075
strobe_count
4
strobe_current_a
0.11
panel_current_a
0.2
nac_supply_capacity_a
2
alarm_load_w
95
alarm_runtime_h
24
alarm_battery_capacity_kwh
3
isolated_drain_count
3
total_drain_count
3
allowed_spill_response_min
30
planned_spill_response_min
18

Example task

ssc16-bund-fire-case-preview — hard difficulty, all inputs given.

Temporary fuel chemical bund and fire interface case. Required outputs: required_bund_volume_l, bund_volume_margin_l, fire_hrr_kw, visibility_margin_m, nac_current_a, nac_headroom_a

The model sees

Scenario context and visible inputs.

largest_container_l
2500 to 2500 L
rainfall_allowance_l
600 to 600 L
provided_bund_volume_l
3600 to 3600 L
fire_growth_alpha_kw_s2
0.0469 to 0.0469 kW/s2
design_fire_time_s
240 to 240 s
provided_visibility_m
14 to 14 m
required_visibility_m
10 to 10 m
horn_count
6 to 6 count
horn_current_a
0.075 to 0.075 A
strobe_count
4 to 4 count
strobe_current_a
0.11 to 0.11 A
panel_current_a
0.2 to 0.2 A
nac_supply_capacity_a
2 to 2 A
alarm_load_w
95 to 95 W
alarm_runtime_h
24 to 24 h
alarm_battery_capacity_kwh
3 to 3 kWh
isolated_drain_count
3 to 3 count
total_drain_count
3 to 3 count
allowed_spill_response_min
30 to 30 min
planned_spill_response_min
18 to 18 min

Executable tool: temporary-fuel-chemical-bund-fire-interface-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.

{
  "required_bund_volume_l": <number>,
  "bund_volume_margin_l": <number>,
  "fire_hrr_kw": <number>,
  "visibility_margin_m": <number>,
  "nac_current_a": <number>,
  "nac_headroom_a": <number>,
  "alarm_battery_required_kwh": <number>,
  "alarm_battery_margin_kwh": <number>,
  "drain_isolation_fraction": <number>,
  "spill_response_margin_min": <number>,
  "overall_pass_score": <number>
}
  • required_bund_volume_l · scored within ±3%
  • bund_volume_margin_l · scored within ±3%
  • fire_hrr_kw · scored within ±3%
  • visibility_margin_m · scored within ±3%
  • nac_current_a · scored within ±0.3%
  • nac_headroom_a · scored within ±0.3%
  • alarm_battery_required_kwh · scored within ±3%
  • alarm_battery_margin_kwh · scored within ±3%
  • drain_isolation_fraction · scored within ±0.1%
  • spill_response_margin_min · scored within ±3%
  • overall_pass_score · scored within ±0.1%