Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.
Exathlon: A benchmark for explainable anomaly detection over time series
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Access to high-quality data repositories and benchmarks have been instrumental in advancing the state of the art in many experimental research domains. While advanced analytics tasks over time series data have been gaining lots of attention, lack of such community resources severely limits scientific progress. In this paper, we present Exathlon, the first comprehensive public benchmark for explainable anomaly detection over high-dimensional time series data. Exathlon has been systematically constructed based on real data traces from repeated executions of large-scale stream processing jobs on an Apache Spark cluster. Some of these executions were intentionally disturbed by introducing instances of six different types of anomalous events (e.g., misbehaving inputs, resource contention, process failures). For each of the anomaly instances, ground truth labels for the root cause interval as well as those for the extended effect interval are provided, supporting the development and evaluation of a wide range of anomaly detection (AD) and explanation discovery (ED) tasks. We demonstrate the practical utility of Exathlon's dataset, evaluation methodology, and end-to-end data science pipeline design through an experimental study with three state-of-the-art AD and ED techniques.
fields
cs.LG 3representative citing papers
Extending Matrix Profile to multidimensional time series yields the only method among 19 baselines that maintains high anomaly detection performance across unsupervised, supervised, and semi-supervised regimes on 119 datasets.
A conditional attribution framework retrieves contextually similar normal states from learned VAE/UMAP embeddings to produce dependency-preserving root cause explanations for time-series anomalies.
citing papers explorer
-
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.
-
Matrix Profile for Anomaly Detection on Multidimensional Time Series
Extending Matrix Profile to multidimensional time series yields the only method among 19 baselines that maintains high anomaly detection performance across unsupervised, supervised, and semi-supervised regimes on 119 datasets.
-
Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection
A conditional attribution framework retrieves contextually similar normal states from learned VAE/UMAP embeddings to produce dependency-preserving root cause explanations for time-series anomalies.