AI Paper Atlas

Research map / Time series / Foundation models for time series

CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data

Shifeng Xie, Vasilii Feofanov, Jianfeng Zhang, Themis Palpanas, Ievgen Redko

ICLR 2026 · Time series › Foundation models for time series · approach: Time series foundation models · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace TabPFN-style SCM data with CauKer data (ablation)Mantis/MOMENT pretraining · UCR zero-shotaccuracy: Mantis 73.49 -> 78.31; MOMENT 59.23 -> 74.24Improved
Add non-zero mean functions to KernelSynth GP (ablation)KernelSynth · UCR zero-shotaccuracy: Mantis 77.70 -> 78.20; MOMENT 69.31 -> 72.56Improved
Add SCM causal structure on top of Mean+KernelSynth (ablation)CauKer · UCR zero-shotaccuracy: Mantis 78.20 -> 78.31; MOMENT 72.56 -> 74.24Improved
Scale CauKer pretraining data from 10K/100K to 10M (ablation)MOMENT / Mantis · UCR zero-shotaccuracy: MOMENT 74.24 -> 77.49; Mantis 76.91 -> 79.09Improved
Scale UEA real pretraining data to full size (ablation)MOMENT / Mantis · UCR zero-shotaccuracy: Mantis 76.21 (127K) -> 71.93 (12.67M)No clear effect
Increase kernels and parents per node together (ablation)CauKer · UCR zero-shotaccuracy: 0.7848 -> 0.7810No clear effect
Use only DotProduct kernels instead of rich kernel bank (ablation)CauKer · UCR zero-shotaccuracy: 76.79 vs 78.07 (RBF-only)Hurt
Pretrain on 100K CauKer instead of 1.89M real seriesMantis · UCR zero-shotaccuracy: drop less than 0.1%No clear effect
Pretrain on 10M CauKer instead of 13M real seriesMOMENT · UCR zero-shotaccuracy: drop barely exceeds 1%Mixed
Add SCM layer to KernelSynth generationCauKer generation cost · 1000 series, length 512generation time: 182.25 -> 121.64 sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy