REVIEW 15 cited by
Toto: Time Series Optimized Transformer for Observability
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Toto: Time Series Optimized Transformer for Observability
read the original abstract
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state of the art on generalized time series benchmarks in domains such as electricity and weather, this model is the first general-purpose time series forecasting foundation model to be specifically tuned for observability metrics. Toto was trained on a dataset of one trillion time series data points, the largest among all currently published time series foundation models. Alongside publicly available time series datasets, 75% of the data used to train Toto consists of fully anonymous numerical metric data points from the Datadog platform. In our experiments, Toto outperforms existing time series foundation models on observability data. It does this while also excelling at general-purpose forecasting tasks, achieving state-of-the-art zero-shot performance on multiple open benchmark datasets.
Forward citations
Cited by 15 Pith papers
-
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
TiRex-2 is a recurrent xLSTM time series foundation model for multivariate forecasting with future covariates and constant-cost streaming that reports SOTA zero-shot results on GIFT-Eval and fev-bench.
-
OpenMHC: Accelerating the Science of Wearable Foundation Models
OpenMHC contributes the largest open-access consumer wearable dataset to date (67M hours, 11,894 participants), a standardized three-track benchmark, and the first open implementations of Apple WBM and Google LSM-2.
-
APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations
APEX, a network-native time-series foundation model pre-trained on 100K AP series from 4500 networks, reduces MAE by 18% versus Toto and achieves F1 0.93 on DHCP degradation anomaly detection while supporting edge deployment.
-
LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data
LakeFM pre-trains on large ecological datasets to forecast irregular lake time series and reports competitive or superior performance with physically plausible outputs.
-
TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version
TimeBlocks maintains a pool of modular model blocks selected via routing to form lightweight task-specific time-series models, paired with StreamCore to enable continual calibration by preserving an approximation of i...
-
Toto 2.0: Time Series Forecasting Enters the Scaling Era
Toto 2.0 is a family of open time series foundation models that demonstrates reliable scaling and sets new state-of-the-art results on three forecasting benchmarks.
-
RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction
RareCP improves interval efficiency for time series conformal prediction by retrieving and weighting regime-specific calibration examples while adapting to drift and maintaining coverage.
-
WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting
WaveMoE uses a dual-path architecture with aligned time-series and wavelet tokens routed through shared experts to improve forecasting performance on diverse benchmarks.
-
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
DynLMC creates synthetic time series data with dynamic inter-channel correlations that improve zero-shot forecasting in foundation models across multiple benchmarks.
-
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
DynLMC creates synthetic multivariate time series with dynamic inter-channel correlations that improve zero-shot forecasting performance when used to fine-tune foundation models across nine benchmarks.
-
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Timer-S1 is a released 8.3B-parameter MoE time series model that achieves state-of-the-art MASE and CRPS scores on GIFT-Eval using serial scaling and Serial-Token Prediction.
-
Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
TSFMs need covariates for competitive EPF, do not consistently beat domain-specific methods, and simple TSFM–domain ensembles capture complementary signal under a contamination-aware two-dataset protocol.
-
Toto 2.0: Time Series Forecasting Enters the Scaling Era
Time series foundation models scale under a single training recipe, with forecast quality improving from 4M to 2.5B parameters and new SOTA results on BOOM, GIFT-Eval, and TIME benchmarks.
-
On Subquadratic Architectures: From Applications to Principles
xLSTM outperforms Mamba-2 and Gated DeltaNet on tasks with complex dependencies because its gating scheme enables more flexible and stable state tracking and memory accumulation.
-
Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G
The paper envisions AI-native 6G networks anchored by a foundation model and multi-agent systems to shift network management to a unified multi-modal optimization problem.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.