About the sensitivity of ordinal classifiers to non-monotone noise
Bibliographic record
Abstract
Ordinal classifiers have become quite popular in recent years. However, no one has systematically tested yet how sensitive theyare to noise. This research investigates for the first time the effect of non-monotone noise on the accuracy related rankings of tenclassifiers in a controlled manner. The findings of this experiment are reported here. They clearly show that some models aremore sensitive than others to non-monotone noise. Some classifiers which ranked higher in absence of noise performed poorlywhen the noise level increased even modestly. Others, which ranked relatively low in noiseless datasets, ranked much betterwhen the noise levels increased. Two classifiers which assure monotone classifications became practically useless at relativelylow levels of noise, while other classifiers’ accuracies deteriorated at a much slower pace. Three alternative accuracy-relatedmeasures were used: Accuracy, Kappa and the Gini Index, and all were subjected to statistical tests. The lesson to be learnedfrom this experiment is that it is very important to measure and report, among other things, the levels of noise which are presentin datasets used for the evaluation of classification models.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.132 | 0.499 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.006 |
| Scholarly communication | 0.007 | 0.010 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.005 | 0.007 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".