Synthesizing Design Performance: An Evolutionary Approach to Multidisciplinary Design Search
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
Design is a goal oriented decision-making activity. Design is ill defined and requiring of synthetic approaches to weighing and understanding tradeoffs amongst soft and hard objectives, and the imprecise and or computationally explicit criteria and goals. In this regard designers in contemporary practice face a crisis of sorts. How do we achieve performance under large degrees of uncertainty and limited design cycle time? How do we better design for integrating performance? Fundamentally design teams, are not typically given enough time nor the best tools to design explore, to generate design alternatives, and then evolve solution quality to search for best fit through expansive design solution spaces. Given the complex criteria for defining performance in architecture our research approach experiments upon an evolutionary and integrative computational strategy to expand the solution space of a design problem as well as pre-sort and qualify candidate designs. We present technology and methodology that supports rapid development of design problem solution spaces in which three design domains objectives have multi-directional impact on each other. The research describes the use of an evolutionary approach in which a genetic algorithm is used as a means to automate the design alternative population as well as to facilitate multidisciplinary design domain optimization. The paper provides a technical description of the prototype design, one that integrates associative parametric modeling with an energy use intensity evaluation and with a financial pro forma. The initial results of the research are presented and analyzed including impacts on design process; the impacts on design uncertainty and design cycle latency; and the affordances for Âdesigning-in performance and managing project complexity. A summary discussion is developed which describes a future cloud implementation and the future extensions into other domains, scales, tectonic and system detail.
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 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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