Contamination Map Methodology

Time series / Model

Toto-Open-Base-1.0

Organisation
Datadog
Family
Toto · version 1.0
Released
2025-05-20 (arXiv v1 submission date of the accompanying paper (https://arxiv.org/abs/2505.14766); HF repo Datadog/Toto-Open-Base-1.0 createdAt 2025-04-30 (HF API).)
Checkpoints
Datadog/Toto-Open-Base-1.0
Weights
Open · apache-2.0
Links
PaperModel cardCode

Training data disclosure: Partial list

Level determined for 63% of benchmark cells.

“Alongside the Datadog data, we include public time series datasets, in particular, the GIFT-Eval Pretrain [1] and Chronos [11] collections.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15
“Observability Metrics:** ~1 trillion points from Datadog internal systems (no customer data)”
huggingface.co · model card · Training Data Summary · retrieved 2026-10-15
“Synthetic data constitutes approximately 33% of our training dataset.”
arxiv.org · paper · Appendix B.3 · retrieved 2026-10-15

Training corpora

Other declared training data

Declared exclusions

Benchmark cells

GIFT-Eval

Not seen Jena Weather (GIFT-Eval) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen BizITObs - Application · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen BizITObs - Service · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen BizITObs - L2C · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Bitbrains - Fast Storage · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Bitbrains - rnd · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Restaurant (Recruit Restaurant Visitor Forecasting) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen ETT1 (GIFT-Eval) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen ETT2 (GIFT-Eval) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Loop Seattle (LibCity) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen SZ-Taxi (LibCity) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M_DENSE (LibCity) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Solar (LSTNet, 137 Alabama PV plants) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Hierarchical Sales (Mancuso et al., 2020) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Yearly · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Quarterly · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Monthly · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Weekly · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Daily · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen M4 Hourly · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Hospital · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen COVID Deaths · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen US Births · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Saugeen River Flow · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Temperature Rain · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen KDD Cup 2018 · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen Car Parts · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Not seen ElectricityLoadDiagrams20112014 (UCI) · the authors state its test portion was excluded from training

Evidence (1)
“Importantly, we remove the subset of the Chronos datasets that overlap with the GIFT-Eval benchmark in order to avoid any leakage from the test data.”
arxiv.org · paper · Section 3.2 · retrieved 2026-10-15

Long-horizon forecasting (ETT, Electricity, Traffic, Weather, Exchange, ILI)

Unknown ETTh1 · training data not disclosed in enough detail

Unknown ETTh2 · training data not disclosed in enough detail

Unknown ETTm1 · training data not disclosed in enough detail

Unknown ETTm2 · training data not disclosed in enough detail

Unknown Electricity (ECL, 321 clients) · training data not disclosed in enough detail

Seen, split unclear Traffic (PeMS San Francisco Bay, 862 sensors) · the dataset was used; the source does not say which part (via GIFT-Eval Pretrain (GiftEvalPretrain))

Evidence (3)
“Our pre-training dataset incorporates a diverse collection of time series from the GIFT-Eval Pretrain collection [26] and non-overlapping Chronos datasets [11].”
arxiv.org · paper · Appendix B.2 · retrieved 2026-10-15
“[GIFT-Eval Pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain)”
huggingface.co · model card · Training Data Summary · retrieved 2026-10-15
“Traffic Hourly”
arxiv.org · paper · Table 14 (dataset column) · retrieved 2026-10-15

Unknown Weather (Jena, 2020; Autoformer) · training data not disclosed in enough detail

Seen, split unclear Exchange-Rate · the dataset was used; the source does not say which part

Evidence (1)
“These datasets include ercot, exchange_rate, weatherbench_daily, weatherbench_hourly, weatherbench_monthly, dominick, mexico_city_bikes, ushcn_daily, and wiki_daily_100k.”
arxiv.org · paper · Appendix B.2 · retrieved 2026-10-15

Related data seen ILI (CDC influenza-like illness, national) · related dataset CDC FluView ILINet (LOTSA) was used (via GIFT-Eval Pretrain (GiftEvalPretrain))

Evidence (6)
“Our pre-training dataset incorporates a diverse collection of time series from the GIFT-Eval Pretrain collection [26] and non-overlapping Chronos datasets [11].”
arxiv.org · paper · Appendix B.2 · retrieved 2026-10-15
“[GIFT-Eval Pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain)”
huggingface.co · model card · Training Data Summary · retrieved 2026-10-15
“CDC Fluview ILINet”
arxiv.org · paper · Table 14 (dataset column) · retrieved 2026-10-15
“includes the weekly recorded influenza-like illness (ILI) patients data from Centers for Disease Control and Prevention of the United States between 2002 and 2021”
arxiv.org · paper · Section 4 (Datasets) · retrieved 2026-10-15
“https://gis.cdc.gov/grasp/fluview/fluportaldashboard.html”
arxiv.org · paper · Section 4, footnote 4 · retrieved 2026-10-15
“CDC Fluview ILINet CDC Fluview WHO NREVSS”
arxiv.org · paper · Table 14 (dataset column) · retrieved 2026-10-15

Time-series anomaly detection

Unknown TSB-AD-U (TSB-AD univariate) · training data not disclosed in enough detail

Unknown TSB-AD-M (TSB-AD multivariate) · training data not disclosed in enough detail

Unknown UCR Time Series Anomaly Archive (Hexagon ML/UCR, KDD Cup 2021) · training data not disclosed in enough detail

Unknown Server Machine Dataset (SMD) · training data not disclosed in enough detail

Unknown Mars Science Laboratory (MSL) telemetry anomaly dataset · training data not disclosed in enough detail

Unknown Soil Moisture Active Passive (SMAP) telemetry anomaly dataset · training data not disclosed in enough detail

Unknown Pooled Server Metrics (PSM) · training data not disclosed in enough detail

Unknown Secure Water Treatment (SWaT) · training data not disclosed in enough detail

Unknown Yahoo S5 Labeled Anomaly Detection Dataset (Yahoo Webscope S5) · training data not disclosed in enough detail

Unknown Numenta Anomaly Benchmark (NAB) · training data not disclosed in enough detail

Time-series classification

Unknown UCR Time Series Classification Archive (2018) · training data not disclosed in enough detail

Unknown UEA Multivariate Time Series Classification Archive (2018) · training data not disclosed in enough detail

Notes

151M parameters; ~2.36T points (43% Datadog internal observability metrics, ~33% synthetic incl. kernel_synth_1m, rest GIFT-Eval Pretrain + Chronos datasets minus GIFT-Eval overlap). Evaluated zero-shot on LSF (ETT, Electricity, Weather); no statement on overlap between its public data and LSF. exchange_rate (long-horizon Exchange source) is named among training datasets. Other stated exclusions, not tracked here: BOOM (all).

Sources