Detecting Anomalies in Logs by Combining NLP features with Embedding or TF-IDF
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
<div><div><div><p>Following image classification, the focus is now shifting to text categorization. Text classification has numerous real-world uses. Using categories to tag information or items to improve browsing or identify related stuff on your website. The practise of categorising text into ordered groupings is known as text classification, sometimes known as text tagging or text categorization. Text classifiers can automatically assess text and assign a set of pre-defined tags or categories depending on its content using Natural Language Processing (NLP). In this study, we will try to create a model that can detect abnormalities in a log data collection by combining NLP features with other methodologies. This is handled as a text categorization challenge. That is why we evaluate two of the most well-known techniques while also using extra features extracted from the data set. We shall contrast the bag of words technique with the embedding technique. As opposed to Bag of words, embedding tries to preserve the meaning of the sentence, which can aid with text classification.</p></div></div></div>
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.004 |
| 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