On Synergies between Diversity and Task Decomposition in Constructing Complex Systems with GP
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
Complexity in genetic programming is unfortunately often associated with undesirable properties such as code bloat. In this work, we review developments in which complex systems are promoted through: 1) the evolution of teams of programs, and then 2) the context specific reuse of previously evolved code. To do so, two classes of diversity are identified: intra-team diversity and inter-team diversity. Intra-team diversity promotes task decomposition/cooperative coevolution between multiple programs, i.e. teams of programs. A fundamental requirement is that programs can learn context. Inter-team diversity is promoted through maintaining model and task diversity during evolution. The combination of both result in the ability to identify teams of programs and associate them with specific contexts, and then organize teams of programs hierarchically so solve multiple tasks. Finally, the concept of cumulative population wide performance is used to illustrate how inter model diversity in particular introduces useful biases into the types of solutions evolved.
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) | 0.000 | 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 | 0.000 |
| 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