Model Composition from Interchangeable Components
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
Following the increasing demand to make the creation and manipulation of 3D geometry simpler and more accessible, we introduce a modeling approach that allows even novice users to create sophisticated models in minutes. Our approach is based on the observation that in many modeling settings users create models which belong to a small set of model classes, such as humans or quadrupeds. The models within each class typically share a common component structure. Following this observation, we introduce a modeling system which utilizes this common component structure allowing users to create new models by shuffling interchangeable components between existing models. To enable shuffling, we develop a method for computing a compatible segmentation of input models into meaningful, interchangeable components. Using this segmentation our system lets users create new models with a few mouse clicks, in a fraction of the time required by previous composition techniques. We demonstrate that the shuffling paradigm allows for easy and fast creation of a rich geometric content.
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 | 0.001 | 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