Table 1_Generative artificial intelligence for sustainable architectural design within urb

A structured dataset of paired design alternatives, consisting of baseline solutions and AI-generated variants developed at multiple levels of representational definition. The dataset, created by Francesco Sica and last updated in May 2026, supports a two-phase comparative framework linking representational variability to economic outcomes for sustainable architectural and urban design.

Use Cases

• Calculate cost-dissimilarity relationships across design scenarios based on the paired alternatives.
• Test hypotheses about cost uncertainty increasing with reduced representational definition using the structured dataset.
• Assess first-order resource implications of design alternatives using cost-based proxies for material intensity and construction systems.
• Compare geometric variation and changes in inferred quantities between baseline and AI-generated design variants.

Strengths

• Dataset is structured for reproducible workflow coupling representational analysis with cost translation.
• Analysis incorporates cost-based proxies linked to material intensity and construction systems for sustainability assessment.
• Dataset is licensed under CC-BY-4.0, permitting sharing and adaptation with attribution.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small (9.1 KB), indicating limited scope or a highly focused sample.

Provenance

Source

Francesco Sica via figshare

Collection Method

Likely compiled for empirical analysis in a research paper on generative AI for sustainable architectural design.

Freshness

Last updated 2026-05-07 04:45:28; freshness should be verified.