# CORD: Learning Reusable Degradation Representations Across Heterogeneous Physical Systems

arXiv: https://arxiv.org/abs/2609.39784 · HTML: https://mlsanity.com/paper/2609.39784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [Remaining Useful Lifetime Prediction via Deep Domain Adaptation](https://mlsanity.com/paper/1907.07480/) (2019)
- [TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling](https://mlsanity.com/paper/2402.02475/) (2024)
- [T-Rep: Representation Learning for Time Series using Time-Embeddings](https://mlsanity.com/paper/2310.04486/) (2023)
- [FeDaL: Federated Dataset Learning for General Time Series Foundation Models](https://mlsanity.com/paper/2508.04045/) (2025)
- [Predicting the impact of formation protocols on battery lifetime immediately after manufacturing](https://mlsanity.com/paper/2203.14158/) (2022)
- [Repurposing Foundation Model for Generalizable Medical Time Series Classification](https://mlsanity.com/paper/2410.03794/) (2024)
- [GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data](https://mlsanity.com/paper/2502.03264/) (2025)
- [Towards Unified and Data-Efficient Prognostics and Health Management with Tabular Foundation Models](https://mlsanity.com/paper/2606.05481/) (2026)

## Abstract (arXiv)

Can heterogeneous physical degradation systems benefit from joint pretraining and move beyond system-specific prognostics toward reusable cross-system representation learning? CORD combines type-specific observation interfaces with a shared degradation backbone. Its two self-supervised objectives learn at complementary scales: Intra-Observation Structure Modeling (ISM) captures structure within observations, while Inter-Observation Dynamics Modeling (IDM) captures latent degradation evolution across observation histories. We evaluate CORD under two transfer boundaries: Pretraining-Included System Types, where downstream datasets and held-out units are unseen but their system types are represented during source pretraining, and Pretraining-Excluded System Types, where the entire turbofan-engine type is absent from pretraining. Across bearings, batteries, and cutting tools, CORD (Multi-domain) consistently improves over CORD (Single-domain) under Frozen adaptation, provides further gains under Full FT in most settings, and remains competitive with representative external baselines. Source-pretrained initialization also improves low-label adaptation to the pretraining-excluded engine type. Frozen-representation analysis further shows improved cross-unit lifecycle consistency after multi-domain pretraining. Joint pretraining across heterogeneous physical systems thus produces degradation representations reusable across devices, datasets, and system types.