An analysis of semi-supervised learning with the Guelph Cluster Class algorithm
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
Training a classifier requires a supply of example problems and the correct classification (label) for each. In some practical situations examples are plentiful, but obtaining labels for them is costly. Several algorithms exist for learning classification when only a small number of examples are "labelled" at the outset and the remainder are "unlabelled." This thesis presents continued work on the Guelph Cluster Class algorithm developed by Dara, Stacey and Kremer. Specifically, it investigates how the algorithm performs on ten real-world data sets over a range of parameter settings, and whether cluster validity indices can guide the setting of the parameters. An examination of a simple clustering problem points to explanations for the algorithm's behaviour, and tests of a variant algorithm that capitalizes on these observations are presented. Finally, this thesis explores whether clustering information can guide the selection of examples which, if labelled, would be especially informative for classifier training.
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 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 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