Skip to main content
Back to challenges
Challenge

Multifamily Conversion Floorplate & Plumbing Layout Parser

Adapting office properties to multifamily usage requires rapid evaluation of core-to-window depths and existing plumbing stacks. Construct a computer vision and document parsing tool to analyze floor plan schematics and flag unviable living unit deep space zones. Achieve 90% accuracy in identifying non-compliant windowless dwelling spaces.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a floor plan parsing pipeline to extract core-to-window distances and evaluate multifamily layout compliance.

Delivery guide

How work is evaluated

Evaluation

Evaluates accurate calculation of deep floor space percentage lacking natural light.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

pct_close

Ensures unviable space percentage is calculated accurately.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

area_mae

Mean Absolute Error in dark zone square footage calculation. • target: 50 • range: 0-1000

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Process commercial floor plan images or vector PDFs to extract outer perimeter and structural core boundaries

  • Calculate maximum distance from habitable space to exterior light source windows

  • Flag residential layout unit designs violating municipal daylight codes (>30 ft depth)

  • Output structured spatial metrics for conversion architects

Resources and assets

Reference links and supporting material

Dataset notes

Geometric polygon representations of commercial building floorplates with varying core and exterior dimension configurations.

Challenge setup

Evaluates accurate calculation of deep floor space percentage lacking natural light.

Challenge input

JSON object with floor_width_ft, floor_length_ft, core_width_ft, core_length_ft

Shapely

Standard Python geometric manipulation tool.

Evaluated output

JSON object with dark_zone_area_sqft, unviable_space_pct

Evaluation checks
  • Ensures unviable space percentage is calculated accurately.
  • Mean Absolute Error in dark zone square footage calculation. • target: 50 • range: 0-1000
Configured evaluation evidence
  • Benchmark: SpatialGeometryBench
  • Area Mae target: 50
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Twin · Required
  • Coplay AI · Optional
  • Pydantic AI · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • pct_close · Weight 1
  • area_mae · Weight 1

Metrics

  • area_mae · Target 50

Benchmarks

  • SpatialGeometryBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with floor_width_ft, floor_length_ft, core_width_ft, core_length_ft

    Output: JSON object with dark_zone_area_sqft, unviable_space_pct

    Execution harness: Python

Evaluation tools

  • Shapely · Spatial Geometry Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Multifamily Conversion Floorplate & Plumbing Layout Parser