Representation search through generate and test
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
Learning representations from data is one of the funda-mental problems of artificial intelligence and machine learning. Many different approaches exist for learning representations, but what constitutes a good representa-tion is not yet well understood. In this work, we view the problem of representation learning as one of learning features (e.g., hidden units of neural networks) such that performance of the underlying base system continually improves. We study an important case where learning is done fully online (i.e., on an example-by-example ba-sis) from an unending stream of data. In the presence of an unending stream of data, the computational cost of the learning element should not grow with time and cannot be much more than that of the performance ele-ment. Few methods can be used effectively in this case. We show that a search approach to representation learn-ing can naturally fit with this setting. In this approach good representations are searched by generating differ-ent features and then testing them for utility. We de-velop new representation-search methods and show that the generate-and-test approach can be utilized in a sim-ple and effective way for learning representations. Our methods are fully online and add only a small fraction to the overall computation. They constitute an impor-tant step toward effective and inexpensive solutions to representation learning problems.
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