Skip to content
View original post on X: Prime IntellectOfficial· 49/100AI score49/100

Prime Intellect builds AnomalyXL, a 4B model trained to localize anomalies in long time series

AISummary

Prime Intellect RL resident @nzuma0 built AnomalyXL, an infinitely scalable synthetic time-series generator with programmatic ground truth, written in verifiers.

He trained a 4B TimeRLM on it with prime-rl, generating fresh data every step, with the model recursively calling sub-agents via nano-rlm to localize anomalies across 131k datapoints.

The post says the model transfers zero-shot to ECG, sleep and observability data.

Post on XView on X
Prime IntellectVerified on X
@PrimeIntellect

Most open RL environments cluster around the same few domains. Almost none are long-context time series.

Prime Intellect RL resident @nzuma0 built one. AnomalyXL is an infinitely scalable synthetic generator with programmatic ground truth, written in verifiers.

He then trained a 4B TimeRLM on it with prime-rl, generating fresh data every step, with the model recursively calling sub-agents via nano-rlm to localize anomalies across 131k datapoints. It transfers zero-shot to ECG, sleep and observability data.

nicozumarraga@nzuma0
Frontier Time Series Language Models struggle with precise anomaly localization over long contexts, when useful signals might be hidden in hours of recordings. In our new paper we trained a tiny Recursive Language Model to SoTA performance on long context time series. We introduce AnomalyXL, an infinitely scalable synthetic time-series generator with programmatic ground truth answers. Training our RLM formulation on this RL environment transfers to real world anomaly detection in Software Observability, ECG and Sleep data. 🧵👇
View quoted post on X

Source: Prime Intellect · x.comPublished · added here

Topics

Data & trainingPapers & researchEvals & benchmarks