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

4 20Ma Scaling

Calculates the current signal for a process variable over a configured lower and upper range. The deterministic linear scaling reports percentage of span, 4-20 mA current, and reconstructed process value from the current signal for instrumentation checks.

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

Standards

IEC 60381ISA-5.1

Tags

4-20madeterministicelectricalinstrumentationsignal-scaling

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.

2

  • Process value

    process_value

    Process variable value

    0 – 1000

  • Lower range value

    lower_range_value

    Lower range value

    -1000 – 500

Hidden at higher difficulty

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

1

  • Upper range value

    upper_range_value

    Upper range value

    Hidden at hard difficulty.

    1 – 2000

Scored outputs

3 outputs

Span pct

span_pct

Percentage of configured span

Scores if within ±3% of the reference value.

Current signal ma

current_signal_ma

Current signal

Scores if within ±3% of the reference value.

Reconstructed process value

reconstructed_process_value

Process variable reconstructed from current

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

Percent range scaling

medium

All inputs given

Engineering range scaling

hard

Some inputs hidden

Upper range value hidden in context

Hidden inputs

  • Upper range valueupper_range_value

Prompt replacement text

Use the configured upper range implied by {{ archetype.description }}.

Upper range value restricted to: 1000

Task bundle

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

/workspace

  • instruction.md
  • 4-20ma-scaling_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 instrumentation engineer checking a 4-20 mA signal scaling calculation.2 3## Problem4 5Calculate the span percentage, current signal, and reconstructed process variable.6 7## Given8 9| Parameter | Value |10|-----------|-------|11| Process value | {{ process_value }} |12| Lower range value | {{ lower_range_value }} |13{% if upper_range_value is defined %}14| Upper range value | {{ upper_range_value }} |15{% endif %}16 17{% if tool_available %}18## Available Tool19 20A 4-20 mA scaling tool is available at `/workspace/4-20ma-scaling_calc.py`.21{% endif %}22 23## Constraints24 25- Use `span_pct = (process_value - LRV) / (URV - LRV) x 100`.26- Use `current_mA = 4 + 16 x span_fraction`.27- Reconstruct the process value from the current using the inverse relation.28 29## Output Format30 31Include a JSON block with exactly these keys:32 33```json34{35 "span_pct": <numeric_value>,36 "current_signal_ma": <numeric_value>,37 "reconstructed_process_value": <numeric_value>38}39```40 41Write your complete solution to `/workspace/output.md`.42

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.

Level transmitter

level_transmitter

Tank level transmitter scaled in percent

pump-stationwater-treatment
Parameter ranges
process_value
10 – 90
lower_range_value
0
upper_range_value
100

Pressure transmitter

pressure_transmitter

Pressure transmitter scaled over a positive engineering range

process-skidgas-metering
Parameter ranges
process_value
100 – 900
lower_range_value
0
upper_range_value
1000

Example task

process-skid-pressure-transmitter-preview — hard difficulty, some inputs hidden.

Pressure transmitter scaled over a positive engineering range. process-skid. Required outputs: span_pct, current_signal_ma, reconstructed_process_value

The model sees

Scenario context and visible inputs.

process_value
100 to 900
lower_range_value
0 to 0

Executable tool: 4-20ma-scaling_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Upper range value

    upper_range_value

Stand-in text in the prompt

Use the configured upper range implied by {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "span_pct": <number>,
  "current_signal_ma": <number>,
  "reconstructed_process_value": <number>
}
  • span_pct · scored within ±3%
  • current_signal_ma · scored within ±3%
  • reconstructed_process_value · scored within ±3%