TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis

TL;DR

TelecomTS provides a large-scale, high-resolution multi-modal observability dataset from a 5G network, featuring de-anonymized covariates with absolute scale and comprehensive annotations for anomalies, jamming, and QA. By benchmarking state-of-the-art time-series, language, and reasoning models, the paper shows that existing approaches struggle with the abrupt, noisy, and high-variance dynamics typical of observability data, and it highlights the critical importance of preserving scale information. The dataset enables native tasks beyond forecasting, including anomaly detection, root-cause analysis, and multi-modal reasoning, and reveals significant room for improving scale-aware and cross-modal modeling in practical engineering contexts. The work argues for developing foundation time-series models that natively leverage covariate scale and heterogeneity to achieve reliable practical performance in observability scenarios, with TelecomTS serving as a challenging, realistic benchmark platform.

Abstract

Modern enterprises generate vast streams of time series metrics when monitoring complex systems, known as observability data. Unlike conventional time series from domains such as weather, observability data are zero-inflated, highly stochastic, and exhibit minimal temporal structure. Despite their importance, observability datasets are underrepresented in public benchmarks due to proprietary restrictions. Existing datasets are often anonymized and normalized, removing scale information and limiting their use for tasks beyond forecasting, such as anomaly detection, root-cause analysis, and multi-modal reasoning. To address this gap, we introduce TelecomTS, a large-scale observability dataset derived from a 5G telecommunications network. TelecomTS features heterogeneous, de-anonymized covariates with explicit scale information and supports a suite of downstream tasks, including anomaly detection, root-cause analysis, and a question-answering benchmark requiring multi-modal reasoning. Benchmarking state-of-the-art time series, language, and reasoning models reveals that existing approaches struggle with the abrupt, noisy, and high-variance dynamics of observability data. Our experiments also underscore the importance of preserving covariates' absolute scale, emphasizing the need for foundation time series models that natively leverage scale information for practical observability applications.

Figures (17)

• Figure 1: An overview of TelecomTS, illustrating its data curation pipeline, covariate characteristics, and the range of supported multi-modal downstream tasks.
• Figure 2: Overview of the 5G wireless network used for data collection: (a) mobile devices used to generate network traffic; (b) server infrastructure hosting the core network, and base-station workloads; (c) programmable jammer used to introduce controlled over-the-air interference.
• Figure 3: An overview of the anomalies curation process.
• Figure 4: An illustrative difference between UCR Archive Anomaly dataset and the anomalies found in TelecomTS. The anomalies found in the former typically manifest as a clear deviation from an otherwise smooth and predictable trend.
• Figure 5: An overview of the Q&A dataset.