{"ID":5551653,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T13:53:05.627525587Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00958","arxiv_id":"2607.00958","title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","abstract":"Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances. We study how an SSL recipe behaves when its method-specific configuration is reused unchanged after the pretraining signal family changes, framing this as a fixed-recipe stress test rather than a comparison against optimally tuned methods. We introduce Latent Euclidean Next-Embedding Prediction Architecture (LeNEPA), a no-augmentation next-latent-token objective with a causal backbone. LeNEPA replaces the stop-gradient/EMA stabilization used by vanilla NEPA with SIGReg-based isotropy regularization and computes the predictive loss in a lightweight projected space that is discarded for evaluation. We compare LeNEPA with an ECG-tuned JEPA recipe under a fixed-horizon frozen-probe protocol on PTB-XL and Diag, a synthetic diagnostic corpus generated with Aionoscope. Both methods are retrained independently on each dataset while keeping their method-specific recipes unchanged. In this protocol, the ECG-tuned JEPA recipe is strong in-domain on PTB-XL but weaker when reused unchanged on Diag, whereas LeNEPA preserves useful frozen-probe gains on both datasets. Learning curves suggest faster early representation acquisition: LeNEPA reaches 80% of its final AUROC/AUPRC gain after 2--5k updates, compared with 5--10k updates for the faster JEPA readout. As a separate external frozen-encoder check, a CauKer-pretrained LeNEPA variant reaches 77.65% mean UCR-128 Random-Forest accuracy in a single-seed, best-checkpoint run, within 1.16 points of Mantis and within 0.24 points of MOMENT (77.89%). Overall, the results support no-augmentation latent prediction as a useful candidate recipe for low-retuning time-series SSL.","short_abstract":"Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances. We study how an SSL recipe behaves when its method-specific...","url_abs":"https://arxiv.org/abs/2607.00958","url_pdf":"https://arxiv.org/pdf/2607.00958v1","authors":"[\"Alexander Chemeris\",\"Ming Jin\",\"Randall Balestriero\"]","published":"2026-07-01T13:56:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}