Bio-Inspired Growth: Introducing Emergence into Computational Design
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
In today's age of neural networks and brain study, creativity is being introduced into lifeless systems by modelling the concept of learning.Many believe the artificial intelligence that is leading technology will eventually do most of a designer's work.However, this artificial intelligence only results after long hours of training and is limited to the area within which it is trained.In nature, many systems can produce unpredictable solutions without the retention of information -such as trees.Although computers cannot accurately model nature's growth mechanisms, it can be approximated with the concept of predictive nondeterminism -where what is not understood is treated as random -and the rest of the system built around this.This paper lays out a four-tiered structure, inspired by growth principles seen in nature, for introducing emergence into the design system.The models presented are grown by random functions, controlled by a restriction of misfit and guided by the concept of fitness.It gives a bottom up approach to the design, with the user providing the desired functionality and asking what the possible designs are.The resulting models grown by these stochastic rules are emergent, providing the computer with the chance of creating unexpected and innovative solutions.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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