Guides

design-research-problems is the benchmark-task layer of the CMU Design Research Collective design-research ecosystem. It owns packaged task definitions, metadata, statements, evaluators, and task-specific assets.

Primary Path

1. Installation — create a supported Python environment and choose extras.

2. Quickstart — load and inspect a problem using the base install.

3. Concepts and Typical Workflow — learn the kind model and handoff flow.

4. Examples — run examples across the packaged problem kinds.

5. API — confirm the compatibility-guaranteed import surface.

Catalog and Integration Guides

• Catalog Guide provides a curated problem-selection path.

• Problems explains the five public problem kinds.

• Problem Catalog is the generated problem-by-problem inventory.

• Downstream Metadata Contract defines the orchestration compatibility mapping.

• Run An Example In VS Code provides an editor-first setup and debugging path.

• Dependencies and Extras maps optional integrations to install profiles.

Compatibility and Ecosystem

The curated top-level API and downstream metadata contract are the public compatibility boundary. The integration module derives both ProblemBinding.family and the parallel problem_kind metadata alias from ProblemMetadata.kind. Experiments copies the binding’s family into problem_family. Ideation is a catalog subset of text, not a sixth problem kind.

• design-research-agents owns participant execution.

• design-research-experiments owns study design and orchestration.

• design-research-analysis owns validation and downstream analysis.