Landscape and Taxonomy of Online Parser-Supported Log Anomaly Detection Methods
Bibliographic record
Abstract
As production system estates become larger and more complex, ensuring stability through traditional monitoring approaches becomes more challenging. Rule-based monitoring is common in industrial settings, but it has limitations. These include the difficulty of crafting rules capable of detecting unforeseen issues and the burden of manually maintaining rule sets. A potential solution to effectively manage complex system states is log anomaly detection. Workflows for log anomaly detection utilize several fundamental components. These include preprocessors for data cleansing, parsers to extract structured information from raw log data, encoding algorithms to convert extracted data into usable model input features, anomaly detection methods to isolate anomalous signals, and feedback mechanisms to incrementally improve model performance. This study explores the current state of research into online parser-supported log anomaly detection methods, investigates recent research trends, compares the performances of parser and anomaly detection methods using common public datasets and metrics, and assesses their performance evolution over time. Additionally, it classifies available methods using a newly introduced taxonomy, highlights current research gaps, and recommends future research directions.
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 | 0.018 | 0.051 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.013 | 0.009 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.009 |
| Open science | 0.010 | 0.003 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".