Research map / Time series / Causal and generative time series
Uncovering Hidden Degeneration: A Physics-Guided Bidirectional Inference Framework for Industrial Time Series Prediction
Xingwang Li, Fei Teng, Xin Wu, Qiang Duan
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 CDM physics simulator (ablation) | PIBI · Heavy-haul Railway Tracks | F1: 65.35 -> 70.21 | Improved |
| add CDM physics simulator (ablation) | PIBI · Heavy-haul Railway Tracks | ROC-AUC: 74.10 -> 82.21 | Improved |
| add maximum-entropy inference (ablation) | PIBI · Heavy-haul Railway Tracks | F1: 67.81 -> 70.21 | Improved |
| add Arrhenius environmental term (ablation) | PIBI · Heavy-haul Railway Tracks | F1: 68.90 -> 70.21 | Improved |
| add Arrhenius environmental term (ablation) | PIBI · Heavy-haul Railway Tracks | ROC-AUC: 79.40 -> 82.21 | Improved |
| use PIBI vs best baseline (AttnPINN) | PIBI · Heavy-haul Railway Tracks | F1: 67.83 -> 70.21 | Improved |
| use PIBI vs best baseline (AttnPINN) | PIBI · Heavy-haul Railway Tracks | MCC: 68.01 -> 71.42 | Improved |
| use PIBI vs SARAD | PIBI · Heavy-haul Railway Tracks | Recall: 67.73 -> 66.04 | Hurt |
| use PIBI vs MENTORPDM | PIBI · Heavy-haul Railway Tracks | PR-AUC: 71.92 -> 71.68 | Hurt |
| use PIBI vs PhyMPGN | PIBI · KW51 | F1: 84.01 -> 86.32 | Improved |
| use PIBI vs MENTORPDM | PIBI · KW51 | PR-AUC: 85.41 -> 84.66 | Hurt |
| use PIBI vs PhyMPGN | PIBI · KW51 | G-mean: 88.02 -> 87.20 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- SARAD — SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series (NeurIPS 2024) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme (NeurIPS 2025 · similarity 0.83)
- Benchmarking Sensor-Fault Robustness in Forecasting (NeurIPS 2026 · similarity 0.81)
- DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules (NeurIPS 2026 · similarity 0.81)
- How to Re-enable PDE Loss for Physical Systems Modeling Under Partial Observation (AAAI 2025 · similarity 0.81)
- AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution (NeurIPS 2026 · similarity 0.81)
- Exactness Matters for Physical Rule Enforcement (NeurIPS 2026 · similarity 0.81)
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.
