LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …

groundwith-tool

Spt Corrections

Applies standard corrections to raw SPT blow counts following the Liao and Whitman (1986) procedure per ASTM D1586 practice. Applies energy (CE), borehole diameter (CB), sampler (CS), and rod length (CR) corrections to obtain N60, then normalizes to a reference overburden pressure of 100 kPa using CN = sqrt(Pa/sigma'v) to produce the corrected (N1)60 value for liquefaction and strength correlations.

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

Standards

ASTM D1586 Liao and Whitman (1986)

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

01
Template
The reusable contract shown on this page.
02
Scenario
An archetype and site context are sampled.
03
Difficulty tier
Inputs may be hidden at harder tiers.
04
Task prompt
The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

6 inputs

Always given

Included directly in every task prompt.

Raw n value
raw_n_value
Raw field-measured SPT blow count
5 – 60
Effective overburden
effective_overburden_kpa
Effective overburden stress at test depth
10 – 400 kPa
Rod length
rod_length_m
Total rod length from surface to sampler
3 – 30 m

Hidden at higher difficulty

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

Hammer type
hammer_type
SPT hammer type
Hidden at hard difficulty.
autosafetydonut
Borehole diameter
borehole_diameter_mm
Borehole diameter
Hidden at hard difficulty.
65115150200
Sampler type
sampler_type
Sampler liner configuration
Hidden at hard difficulty.
with_linerwithout_liner

Scored outputs

7 outputs

Ce

Energy correction factor CE

Scores if within ±1% of the reference value.

Cb

Borehole diameter correction factor CB

Scores if within ±1% of the reference value.

Cs

Sampler correction factor CS

Scores if within ±1% of the reference value.

Cr

Rod length correction factor CR

Scores if within ±1% of the reference value.

N60

n60

Energy-corrected N-value N60

Scores if within ±3% of the reference value.

Cn

Overburden correction factor CN

Scores if within ±3% of the reference value.

N1 60

n1_60

Normalised corrected N-value (N1)60

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

Standard auto hammer, standard borehole, all params given

Hammer type restricted to: auto

Borehole diameter restricted to: 115

Sampler type restricted to: with_liner

medium

All inputs given

Any equipment combination, all params given

hard

Some inputs hidden

Equipment parameters hidden, agent infers from context

Hidden inputs

Hammer typehammer_type
Sampler typesampler_type
Borehole diameterborehole_diameter_mm

Prompt replacement text

The SPT was conducted using standard Australian practice equipment.

Task bundle

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

/workspace

instruction.md
spt-corrections_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 geotechnical engineer specializing in site investigation.2 3## Problem4 5Apply standard corrections to a raw SPT N-value to obtain the energy-corrected N60 and the overburden-normalised (N1)60 values, using the Liao & Whitman (1986) procedure.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Raw SPT blow count (N) | {{ raw_n_value }} | blows/300mm |12| Effective overburden stress (σ'v) | {{ effective_overburden_kpa }} | kPa |13{% if hammer_type is defined %}14| Hammer type | {{ hammer_type }} | - |15{% endif %}16{% if borehole_diameter_mm is defined %}17| Borehole diameter | {{ borehole_diameter_mm }} | mm |18{% endif %}19{% if sampler_type is defined %}20| Sampler type | {{ sampler_type }} | - |21{% endif %}22| Rod length | {{ rod_length_m }} | m |23{% if archetype_description is defined %}24 25### Test Conditions26 27{{ archetype_description }}28{% endif %}29 30{% if tool_available %}31## Available Tool32 33An SPT correction calculation tool is available at `/workspace/spt_corrections_calc.py`. Run it with:34 35```bash36python3 /workspace/spt_corrections_calc.py --help37```38 39You may use this tool to verify your calculations or compute values directly.40{% endif %}41 42## Required43 44Calculate the following correction factors and corrected values:45 461. Energy correction factor CE472. Borehole diameter correction factor CB483. Sampler correction factor CS494. Rod length correction factor CR505. Energy-corrected N-value: N60 = N × CE × CB × CS × CR516. Overburden correction factor: CN = min(sqrt(Pa/σ'v), 2.0) where Pa = 100 kPa527. Normalised corrected value: (N1)60 = CN × N6053 54## Applicable Standards55 56- Liao, S.S.C. and Whitman, R.V. (1986) — Overburden correction factors for SPT in sand57- ASTM D1586 — Standard Test Method for Standard Penetration Test58 59## Constraints60 61- No internet access is available. Work from engineering knowledge and the provided tool.62- Use the following correction factor tables:63  - CE: auto=1.33, safety=0.96, donut=0.7964  - CB: 65mm=1.00, 115mm=1.00, 150mm=1.05, 200mm=1.1565  - CS: with liner=1.00, without liner=1.2066  - CR: 3-4m=0.75, 4-6m=0.85, 6-10m=0.95, >10m=1.0067- Cap CN at 2.0 maximum68 69## Output Format70 71Show your step-by-step working in Markdown. At the end of your solution, include a JSON block with your final answers in exactly this format:72 73```json74{75  "ce": <numeric_value>,76  "cb": <numeric_value>,77  "cs": <numeric_value>,78  "cr": <numeric_value>,79  "n60": <numeric_value>,80  "cn": <numeric_value>,81  "n1_60": <numeric_value>82}83```84 85Write your complete solution to `/workspace/output.md`.86

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.

Shallow loose

shallow_loose

Shallow test in loose material

brisbane-alluvialdarwin-estuarine

Parameter ranges

raw_n_value: 5 – 15
effective_overburden_kpa: 20 – 80
rod_length_m: 3 – 6

Medium depth

medium_depth

Typical mid-depth test

sydney-hawkesburymelbourne-basalthunter-valley-alluvial

Parameter ranges

raw_n_value: 15 – 30
effective_overburden_kpa: 80 – 200
rod_length_m: 6 – 15

Deep dense

deep_dense

Deep test in dense stratum

perth-coastaladelaide-stiffcairns-coral

Parameter ranges

raw_n_value: 30 – 50
effective_overburden_kpa: 200 – 400
rod_length_m: 15 – 30

Example task

brisbane-alluvial-shallow-loose-preview — hard difficulty, some inputs hidden.

Shallow test in loose material. brisbane-alluvial. Required outputs: ce, cb, cs, cr, n60, cn

The model sees

Scenario context and visible inputs.

raw_n_value: 5 to 15
effective_overburden_kpa: 20 to 80 kPa
rod_length_m: 3 to 6 m

Executable tool: spt-corrections_calc.py

The model must infer

Inputs withheld at this difficulty.

Hammer type
hammer_type
Sampler type
sampler_type
Borehole diameter
borehole_diameter_mm

Stand-in text in the prompt

The SPT was conducted using standard Australian practice equipment.

The model must produce

The scored JSON answer schema.

{
  "ce": <number>,
  "cb": <number>,
  "cs": <number>,
  "cr": <number>,
  "n60": <number>,
  "cn": <number>,
  "n1_60": <number>
}

ce · scored within ±1%
cb · scored within ±1%
cs · scored within ±1%
cr · scored within ±1%
n60 · scored within ±3%
cn · scored within ±3%
n1_60 · scored within ±3%

Spt Corrections

How this task is generated

Template

Scenario

Difficulty tier

Task prompt

Parameters

Inputs

Scored outputs

Ce

Cb

Cs

Cr

N60

Cn

N1 60

Difficulty

easy

medium

hard

Task bundle

Scenario archetypes

Shallow loose

Medium depth

Deep dense

Example task

The model sees

The model must infer

The model must produce