Research map / Time series / Anomaly detection
Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction
Chih-Yu Lai, Fan-Keng Sun, Zhengqi Gao, Jeffrey Lang, Duane S Boning
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add nominality-gated soft induced anomaly score on top of point reconstruction (ablation) | NPSR M_pt · trimSyn | F1*: 0.100 -> 0.434 | Improved |
| add soft-gated induced anomaly score (ablation) | NPSR M_pt · SMD | F1*: 0.485 -> 0.525 | Improved |
| add soft-gated induced anomaly score (ablation) | NPSR M_pt · MSL | F1*: 0.366 -> 0.465 | Improved |
| add soft-gated induced anomaly score (ablation) | NPSR M_pt · SWaT | F1*: 0.839 -> 0.837 | No clear effect |
| add soft-gated induced anomaly score (ablation) | NPSR M_pt · PSM | F1*: 0.626 -> 0.636 | Improved |
| replace simple smoothing (no gate) with soft nominality gate (ablation) | NPSR · SMD | F1*: 0.492 -> 0.525 | Improved |
| replace simple smoothing (no gate) with soft nominality gate (ablation) | NPSR · trimSyn | F1*: 0.144 -> 0.434 | Improved |
| replace simple smoothing with soft gate (ablation) | NPSR · SMAP | F1*: 0.389 -> 0.388 | No clear effect |
| smooth point-based anomaly score without gate (ablation) | NPSR M_pt · MSL | F1*: 0.366 -> 0.451 | Improved |
| use point-based reconstruction error instead of sequence-based (ablation) | NPSR · WADI | F1*: 0.559 -> 0.629 | Improved |
| use point-based reconstruction error instead of sequence-based (ablation) | NPSR · trimSyn | F1*: 0.345 -> 0.100 | Hurt |
| train multi-entity MSL entities separately instead of combined (ablation) | NPSR · MSL | F1*: 0.261 -> 0.551 | Improved |
Closest papers by meaning
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.88)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.88)
- Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing (NeurIPS 2026 · similarity 0.88)
- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability. (NeurIPS 2026 · similarity 0.87)
- When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection (AAAI 2024 · similarity 0.87)
- Position: Quo Vadis, Unsupervised Time Series Anomaly Detection? (ICML 2024 · similarity 0.86)
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.
