Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.09081 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918520704466944 |
|---|---|
| author | Othman, Karim Petersen, Jonas Ignuta-Ciuncanu, Matei Mazzoleni, Camilla Martelli, Federico Lombardi, Alessandro Maggioni, Riccardo Petersen, Philipp |
| author_facet | Othman, Karim Petersen, Jonas Ignuta-Ciuncanu, Matei Mazzoleni, Camilla Martelli, Federico Lombardi, Alessandro Maggioni, Riccardo Petersen, Philipp |
| contents | We introduce the first universal pretraining corpus for industrial time-series data: FactoryNet. 51M datapoints across 23k end-to-end task executions (13.3k real, 9.8k synthetic) on six embodiments, unified by a shared schema that enables robust zero-shot cross-embodiment transfer and highly parameter-efficient anomaly detection. We introduce a novel schema: Setpoint, Effort, Feedback, Context (S-E-F-C) underlying the whole pipeline that maps any actuated system into a common representational frame. The corpus spans 27 annotated anomaly types alongside healthy baselines and counterfactual pairs across robotic manipulation and machining domains. Cross-embodiment transfer experiments yield positive results: under bias-aware metrics our model demonstrates fair cross-embodiment transfer capabilities on the evaluated source-target pair, while 24 schema-aligned signals achieves competitive anomaly detection performance compared to high-dimensional baselines. We release FactoryNet as a growing, multi-embodiment dataset to drive progress toward industrial foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09081 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models Othman, Karim Petersen, Jonas Ignuta-Ciuncanu, Matei Mazzoleni, Camilla Martelli, Federico Lombardi, Alessandro Maggioni, Riccardo Petersen, Philipp Machine Learning Artificial Intelligence We introduce the first universal pretraining corpus for industrial time-series data: FactoryNet. 51M datapoints across 23k end-to-end task executions (13.3k real, 9.8k synthetic) on six embodiments, unified by a shared schema that enables robust zero-shot cross-embodiment transfer and highly parameter-efficient anomaly detection. We introduce a novel schema: Setpoint, Effort, Feedback, Context (S-E-F-C) underlying the whole pipeline that maps any actuated system into a common representational frame. The corpus spans 27 annotated anomaly types alongside healthy baselines and counterfactual pairs across robotic manipulation and machining domains. Cross-embodiment transfer experiments yield positive results: under bias-aware metrics our model demonstrates fair cross-embodiment transfer capabilities on the evaluated source-target pair, while 24 schema-aligned signals achieves competitive anomaly detection performance compared to high-dimensional baselines. We release FactoryNet as a growing, multi-embodiment dataset to drive progress toward industrial foundation models. |
| title | FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.09081 |