BOOM
Summary
BOOM is Datadog’s Benchmark of Observability Metrics. It is the benchmark paired with the Toto model line and is the wiki’s main dataset anchor for observability forecasting.
Official Artifacts
- Official Hugging Face: https://huggingface.co/datasets/Datadog/BOOM
- Official leaderboard: https://huggingface.co/spaces/Datadog/BOOM
- Official code: https://github.com/DataDog/toto/tree/main/boom
- Dataset metadata snapshot: boom-2025
Role In The Wiki
BOOM should be used when the question is high-cardinality observability forecasting over grouped metric variates. It is high-dimensional enough to stress cross-variate modeling at the hundreds-of-variates scale, but it is not an action-conditioned operations benchmark.
Relation To Foundation TSFM Agenda
Use the source-level agenda mappings rather than duplicating verdict rows here:
At the entity level, BOOM should be used when the question is high-cardinality observability forecasting over grouped metric variates. It is high-dimensional enough to stress cross-variate modeling at the hundreds-of-variates scale, but it is not an action-conditioned operations benchmark. This page should stay as the object card; source pages carry slot-level verdicts, evidence, and missing pieces.