# Perseus: Interactive Time Series Segmentation with Sparse Supervision via Stateful Memory

arXiv: https://arxiv.org/abs/2510.09930 · HTML: https://mlsanity.com/paper/2510.09930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters](https://mlsanity.com/paper/2308.08469/) (2023)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging](https://mlsanity.com/paper/1910.11162/) (2019)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data](https://mlsanity.com/paper/1706.03161/) (2017)
- [Root Cause Analysis In Microservice Using Neural Granger Causal Discovery](https://mlsanity.com/paper/2402.01140/) (2024)
- [Hierarchical Classification Auxiliary Network for Time Series Forecasting](https://mlsanity.com/paper/2405.18975/) (2024)
- [Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift](https://mlsanity.com/paper/2310.14838/) (2023)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series](https://mlsanity.com/paper/2506.10412/) (2025)
- [Label-efficient Time Series Representation Learning: A Review](https://mlsanity.com/paper/2302.06433/) (2023)
- [M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training](https://mlsanity.com/paper/2404.17391/) (2024)
- [PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations](https://mlsanity.com/paper/2302.10182/) (2023)
- [COKE: Causal Discovery with Chronological Order and Expert Knowledge in High Proportion of Missing Manufacturing Data](https://mlsanity.com/paper/2407.12254/) (2024)
- [Text2Freq: Learning Series Patterns from Text via Frequency Domain](https://mlsanity.com/paper/2411.00929/) (2024)
- [Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series](https://mlsanity.com/paper/2410.12606/) (2024)
- [PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation](https://mlsanity.com/paper/2506.11170/) (2025)

## Abstract (arXiv)

Real-world systems, ranging from industrial manufacturing to wearable healthcare, generate multivariate time series with hierarchical states ranging from coarse regimes to fine-grained events. Unlike zero- or few-shot segmentation, our setting uses dense state labels for model training. Sparse expert prompts provide inference-time corrections that resolve sequence-specific ambiguities without retraining. In practice, this feedback is grouped around selected events or transitions, leaving large portions of the timeline unprompted. The prompt-based sliding-window baselines evaluated here are stateless with respect to user interaction history: they use guidance only within the current window and cannot retain it across these gaps. To address this, we propose Perseus (Persistent Segmentation with User Supervision), a framework that transitions from synchronous processing to asynchronous state management. Perseus decouples supervision from inference via a distinct Write-Read architecture: grouped user cues are asynchronously encoded into a persistent memory bank (Write), which is then actively queried by the inference engine (Read) to service unprompted windows. This mechanism bridges supervision gaps by conditioning predictions on a global history of interactions rather than solely on local inputs. Extensive experiments on six datasets demonstrate that while evaluated stateless prompting baselines degrade significantly under grouped supervision, Perseus maintains robustness and achieves up to 85% accuracy improvement in multi-granularity settings. Code and preprocessing instructions are available at https://github.com/blacksnail789521/Perseus.