Improvement ratio
improvement_ratio
Post-improvement N1,60 divided by pre-improvement N1,60
Scores if within ±3% of the reference value.
Calculates source-bound ground improvement recheck metrics from a deterministic SSC-07 task-owned source pack. The template combines pre/post SPT improvement, bearing capacity, immediate settlement, consolidation settlement, certificate match, and overall acceptance checks.
with-tool: The model is given an executable Python calculator script.
One template produces many comparable benchmark tasks while keeping the scoring contract fixed.
01
The reusable contract shown on this page.
02
An archetype and site context are sampled.
03
Inputs may be hidden at harder tiers.
04
The model responds with the declared outputs.
Inputs the model receives, and the outputs it is scored on.
12 inputs
Included directly in every task prompt.
Pre improvement n1 60
pre_improvement_n1_60
SPT-07-POST-01 baseline corrected N1,60
Post improvement n1 60
post_improvement_n1_60
SPT-07-POST-01 post-improvement corrected N1,60
Target n1 60
target_n1_60
GI-07-CERT-01 required post-improvement N1,60
Applied bearing pressure
applied_bearing_pressure_kpa
FDN-07-RECHECK-01 applied service bearing pressure
Bearing factor per blow
bearing_factor_per_blow_kpa
SETTLE-07-RECHECK-01 source-owned bearing factor per corrected SPT blow
Footing width
footing_width_m
FDN-07-RECHECK-01 footing width
Elastic modulus
elastic_modulus_kpa
SETTLE-07-RECHECK-01 post-improvement elastic modulus
Poisson ratio
poisson_ratio
SETTLE-07-RECHECK-01 Poisson ratio
Primary settlement
primary_settlement_mm
SETTLE-07-RECHECK-01 primary settlement component
Allowable settlement
allowable_settlement_mm
MEMO-07-FOUND-01 allowable total settlement
Required certificate items
required_certificate_items
GI-07-CERT-01 required certificate fields
Matching certificate items
matching_certificate_items
GI-07-CERT-01 matched certificate fields
11 outputs
improvement_ratio
Post-improvement N1,60 divided by pre-improvement N1,60
Scores if within ±3% of the reference value.
post_improvement_n_margin
Post-improvement N1,60 minus target N1,60
Scores if within ±3% of the reference value.
allowable_bearing_capacity_kpa
Source-owned bearing factor times post-improvement N1,60
Scores if within ±3% of the reference value.
bearing_utilization
Applied bearing pressure divided by allowable bearing capacity
Scores if within ±3% of the reference value.
bearing_margin_kpa
Allowable bearing capacity minus applied bearing pressure
Scores if within ±3% of the reference value.
immediate_settlement_mm
Elastic immediate settlement estimate
Scores if within ±3% of the reference value.
primary_settlement_mm
Primary settlement component from source worksheet
Scores if within ±3% of the reference value.
total_settlement_mm
Immediate plus primary settlement
Scores if within ±3% of the reference value.
settlement_margin_mm
Allowable settlement minus total settlement
Scores if within ±3% of the reference value.
certificate_match_percent
Matched certificate fields divided by required certificate fields
Scores if within ±3% of the reference value.
overall_pass_score
1.0 when improvement, bearing, settlement, and certificate checks pass
Scores if within ±3% of the reference value.
Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.
For this template, difficulty scales through parameter and scenario ranges rather than hidden information.
The exact instruction and parameter contract used to generate this task, pinned to the published library source.
/workspace
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 ground improvement acceptance and foundation recheck package for `SSC-07-LH-06`.2 3Use only the task-owned synthetic source pack values shown below for numeric grading.4 5## Source Pack6 7- Ground improvement certificate: `GI-07-CERT-01`8- Post-improvement SPT log: `SPT-07-POST-01`9- Foundation recheck plan: `FDN-07-RECHECK-01`10- Bearing and settlement worksheet: `SETTLE-07-RECHECK-01`11- Foundation review memo: `MEMO-07-FOUND-01`12 13## Source Values14 15| Item | Value |16|---|---:|17| Pre-improvement N1,60 | {{ pre_improvement_n1_60 }} |18| Post-improvement N1,60 | {{ post_improvement_n1_60 }} |19| Target N1,60 | {{ target_n1_60 }} |20| Applied bearing pressure | {{ applied_bearing_pressure_kpa }} kPa |21| Bearing factor per blow | {{ bearing_factor_per_blow_kpa }} kPa |22| Footing width | {{ footing_width_m }} m |23| Elastic modulus | {{ elastic_modulus_kpa }} kPa |24| Poisson ratio | {{ poisson_ratio }} |25| Primary settlement | {{ primary_settlement_mm }} mm |26| Allowable settlement | {{ allowable_settlement_mm }} mm |27| Required certificate items | {{ required_certificate_items }} |28| Matching certificate items | {{ matching_certificate_items }} |29 30Compute improvement ratio, post-improvement N margin, allowable bearing, bearing utilization and margin, immediate settlement, total settlement, settlement margin, certificate match percent, and overall pass score.31 32Write a compact source-bound foundation review memo to `/workspace/output.md`. Preserve the source IDs above. Include a source-boundary statement that this is a task-owned synthetic source pack.33 34Do not claim authority approval, accepted project evidence, executable real source-pack parsing, full standards compliance, generated benchmark readiness, or benchmark readiness.35 36Include a fenced JSON block with exactly these numeric keys:37 38```json39{40 "improvement_ratio": <numeric_value>,41 "post_improvement_n_margin": <numeric_value>,42 "allowable_bearing_capacity_kpa": <numeric_value>,43 "bearing_utilization": <numeric_value>,44 "bearing_margin_kpa": <numeric_value>,45 "immediate_settlement_mm": <numeric_value>,46 "primary_settlement_mm": <numeric_value>,47 "total_settlement_mm": <numeric_value>,48 "settlement_margin_mm": <numeric_value>,49 "certificate_match_percent": <numeric_value>,50 "overall_pass_score": <numeric_value>51}52```53 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_ground_improvement_case
Ground investigation package for one improvement certificate and foundation recheck
ground-improvement-ssc07-ground-improvement-case-preview — hard difficulty, all inputs given.
Ground investigation package for one improvement certificate and foundation recheck. ground-improvement. Required outputs: improvement_ratio, post_improvement_n_margin, allowable_bearing_capacity_kpa, bearing_utilization, bearing_margin_kpa, immediate_settlement_mm
Scenario context and visible inputs.
Executable tool: ground-improvement-foundation-recheck-package_calc.py
Inputs withheld at this difficulty.
Nothing. All inputs are supplied.
The scored JSON answer schema.
{
"improvement_ratio": <number>,
"post_improvement_n_margin": <number>,
"allowable_bearing_capacity_kpa": <number>,
"bearing_utilization": <number>,
"bearing_margin_kpa": <number>,
"immediate_settlement_mm": <number>,
"primary_settlement_mm": <number>,
"total_settlement_mm": <number>,
"settlement_margin_mm": <number>,
"certificate_match_percent": <number>,
"overall_pass_score": <number>
}