ArchiGen: a conceptual form design tool using an evolutionary computing approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Computer aided design (CAD), the use of computer systems for design and documentation, is prevalent in industrial and architectural design, but largely features passive software to follow user interaction. In the past decade, there have been multiple efforts in implementing multi-objective optimization algorithms and machine learning for data analytics in the area of computational optimization of building designs. This research initially explored the technical review of presented designs, and subsequently began to explore the creation of novel forms based on design constraints in addition to parameter optimization. Most notably in the conceptualization phase of the process, the designer is largely unassisted as current existing CAD software focuses on the modeling and basic structural analysis of already created designs. In this position paper, we propose a conceptual framework to leverage computer-assisted creativity in building and form design using evolutionary algorithms, complimented with a comprehensive review of the approaches of other research. We present the preliminary results of our rudimentary implementation of ArchiGen (Architectural Generator), a tool for assisting designers in the conceptualization of a design by presenting alternative forms based on design constraints. ArchiGen uses Genetic Algorithms (GA) to create alternative designs of a pillar-pod-antenna structured observation tower as a case study and explores the potential of combining optimal and sub-optimal solutions based on the specified design constraints.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it