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

Instrumented Process Control Valve Package

Calculates source-bound process control valve metrics from a deterministic SSC-10 task-owned source pack. The template combines valve Cv, valve authority, 4-20 mA scaling, fail-close timing, basin HRT, and an overall synthetic pass score.

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

Standards

4-20 mA loop scalingP&ID review workflowcontrol valve sizing workflow

Tags

control-valvecvdeterministichrtinstrumentationloopmechanicalwastewater

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

13 inputs

Always given

Included directly in every task prompt.

13
Show 13 inputs

  • Design flow

    design_flow_l_s

    PID-10-VALVE-04 design flow

    38 L/s

  • Specific gravity

    specific_gravity

    VALVE-10-DATA-04 fluid specific gravity

    1.02

  • Upstream pressure

    upstream_pressure_kpa

    PID-10-VALVE-04 upstream pressure

    420 kPa

  • Downstream pressure

    downstream_pressure_kpa

    PID-10-VALVE-04 downstream pressure

    255 kPa

  • Selected valve cv

    selected_valve_cv

    VALVE-10-DATA-04 selected valve Cv

    145

  • Total control zone drop

    total_control_zone_drop_kpa

    CONTROL-10-NARR-04 total control-zone pressure drop

    240 kPa

  • Process lrv

    process_lrv

    RANGE-10-PV-04 lower range value

    0

  • Process urv

    process_urv

    RANGE-10-PV-04 upper range value

    60

  • Setpoint value

    setpoint_value

    LOOP-10-SCHED-04 process setpoint

    42

  • Measured signal

    measured_signal_ma

    LOOP-10-SCHED-04 measured command signal

    15.2 mA

  • Required fail close

    required_fail_close_s

    CONTROL-10-NARR-04 required fail-close time

    18 s

  • Actual fail close

    actual_fail_close_s

    VALVE-10-DATA-04 actual fail-close time

    13 s

  • Basin volume

    basin_volume_m3

    PID-10-VALVE-04 controlled basin volume

    750 m3

Scored outputs

8 outputs

Required cv

required_cv

Required valve Cv

Scores if within ±3% of the reference value.

Cv margin

cv_margin

Selected Cv minus required Cv

Scores if within ±3% of the reference value.

Valve authority ratio

valve_authority_ratio

Valve pressure drop divided by total control-zone drop

Scores if within ±3% of the reference value.

Command signal ma

command_signal_ma

Setpoint converted to 4-20 mA command

Scores if within ±3% of the reference value.

Signal error ma

signal_error_ma

Difference between measured and calculated command signal

Scores if within ±3% of the reference value.

Fail close margin s

fail_close_margin_s

Required fail-close time minus actual fail-close time

Scores if within ±3% of the reference value.

Basin hrt hr

basin_hrt_hr

Hydraulic retention time through controlled basin

Scores if within ±3% of the reference value.

Overall pass score

overall_pass_score

1.0 when Cv, signal, fail-close, and HRT 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-10 process control valve package
medium:
All source-pack values given for the SSC-10 process control valve package
hard:
All source-pack values given for the SSC-10 process control valve package

Task bundle

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

/workspace

  • instruction.md
  • instrumented-process-control-valve-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 wastewater process engineer checking a task-owned synthetic SSC-10 instrumented process control and valve package.2 3Use only the task-owned synthetic source pack values shown below for numeric grading. P&ID review, control valve sizing, loop scaling, and control narrative workflows shape the context only; this instance does not parse a real P&ID, vendor export, or authority-approved design.4 5## Scene6 7- Product: `SSC-10-LH-04`8- P&ID: `PID-10-VALVE-04`9- Loop schedule: `LOOP-10-SCHED-04`10- Valve data sheet: `VALVE-10-DATA-04`11- Process range table: `RANGE-10-PV-04`12- Control narrative: `CONTROL-10-NARR-04`13- Instrumentation memo: `MEMO-10-INST-04`14 15## Source Values16 17| Item | Value |18| --- | --- |19| Design flow | {{ design_flow_l_s }} L/s |20| Specific gravity | {{ specific_gravity }} |21| Upstream pressure | {{ upstream_pressure_kpa }} kPa |22| Downstream pressure | {{ downstream_pressure_kpa }} kPa |23| Selected valve Cv | {{ selected_valve_cv }} |24| Total control-zone drop | {{ total_control_zone_drop_kpa }} kPa |25| Process LRV | {{ process_lrv }} |26| Process URV | {{ process_urv }} |27| Setpoint | {{ setpoint_value }} |28| Measured signal | {{ measured_signal_ma }} mA |29| Required fail-close time | {{ required_fail_close_s }} s |30| Actual fail-close time | {{ actual_fail_close_s }} s |31| Basin volume | {{ basin_volume_m3 }} m3 |32 33## Calculation Rules34 35- Required Cv equals `flow_gpm / sqrt(delta_psi / specific_gravity)`, where `flow_gpm = design_flow_l_s x 15.8503`.36- Valve authority equals valve pressure drop divided by total control-zone pressure drop.37- Command signal equals `4 + 16 x (setpoint - LRV) / (URV - LRV)`.38- Signal error equals the absolute difference between measured and calculated command signal.39- Fail-close margin equals required fail-close time minus actual fail-close time.40- Basin HRT equals basin volume divided by design flow, converted to hours.41- Overall pass score is `1.0` only when Cv margin, authority, signal error, fail-close margin, and HRT checks pass.42 43## Output Format44 45Write 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 whether the baseline source pack passes the current docs-only checks.46 47Do not claim authority approval, accepted project evidence, software export validity, full standards compliance, executable real source-pack parsing, generated modelling evidence, generated benchmark readiness, or benchmark readiness.48 49Include a fenced JSON block with exactly these numeric keys:50 51```json52{53 "required_cv": <numeric_value>,54 "cv_margin": <numeric_value>,55 "valve_authority_ratio": <numeric_value>,56 "command_signal_ma": <numeric_value>,57 "signal_error_ma": <numeric_value>,58 "fail_close_margin_s": <numeric_value>,59 "basin_hrt_hr": <numeric_value>,60 "overall_pass_score": <numeric_value>61}62```63

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.

Ssc10 process control valve case

ssc10_process_control_valve_case

Instrumented process control and valve source pack

process-control-valvevalve-loop-scaling-check
Parameter ranges
params
{'design_flow_l_s': {'min': 38.0, 'max': 38.0}, 'specific_gravity': {'min': 1.02, 'max': 1.02}, 'upstream_pressure_kpa': {'min': 420.0, 'max': 420.0}, 'downstream_pressure_kpa': {'min': 255.0, 'max': 255.0}, 'selected_valve_cv': {'min': 145.0, 'max': 145.0}, 'total_control_zone_drop_kpa': {'min': 240.0, 'max': 240.0}, 'process_lrv': {'min': 0.0, 'max': 0.0}, 'process_urv': {'min': 60.0, 'max': 60.0}, 'setpoint_value': {'min': 42.0, 'max': 42.0}, 'measured_signal_ma': {'min': 15.2, 'max': 15.2}, 'required_fail_close_s': {'min': 18.0, 'max': 18.0}, 'actual_fail_close_s': {'min': 13.0, 'max': 13.0}, 'basin_volume_m3': {'min': 750.0, 'max': 750.0}}

Example task

process-control-valve-ssc10-process-control-valve-case-preview — hard difficulty, all inputs given.

Instrumented process control and valve source pack. process-control-valve. Required outputs: required_cv, cv_margin, valve_authority_ratio, command_signal_ma, signal_error_ma, fail_close_margin_s

The model sees

Scenario context and visible inputs.

design_flow_l_s
38 to 38 L/s
specific_gravity
1.02 to 1.02
upstream_pressure_kpa
420 to 420 kPa
downstream_pressure_kpa
255 to 255 kPa
selected_valve_cv
145 to 145
total_control_zone_drop_kpa
240 to 240 kPa
process_lrv
0 to 0
process_urv
60 to 60
setpoint_value
42 to 42
measured_signal_ma
15.2 to 15.2 mA
required_fail_close_s
18 to 18 s
actual_fail_close_s
13 to 13 s
basin_volume_m3
750 to 750 m3

Executable tool: instrumented-process-control-valve-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_cv": <number>,
  "cv_margin": <number>,
  "valve_authority_ratio": <number>,
  "command_signal_ma": <number>,
  "signal_error_ma": <number>,
  "fail_close_margin_s": <number>,
  "basin_hrt_hr": <number>,
  "overall_pass_score": <number>
}
  • required_cv · scored within ±3%
  • cv_margin · scored within ±3%
  • valve_authority_ratio · scored within ±3%
  • command_signal_ma · scored within ±3%
  • signal_error_ma · scored within ±3%
  • fail_close_margin_s · scored within ±3%
  • basin_hrt_hr · scored within ±3%
  • overall_pass_score · scored within ±0.1%