{"total":12,"items":[{"citing_arxiv_id":"2606.00304","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection","primary_cat":"cs.LG","submitted_at":"2026-05-29T19:31:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces a node-level spectral energy formulation and energy-aware message passing framework to detect camouflaged anomalies with decreased spectral variation in static and time-series graphs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27486","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation","primary_cat":"cs.LG","submitted_at":"2026-05-26T15:00:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Introduces a cyclic-dynamics dataset for industrial MTSAD and benchmarks federated anomaly detection methods on it and a public dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09685","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Unified Representations of Normalcy for Time Series Anomaly Detection","primary_cat":"cs.LG","submitted_at":"2026-05-10T18:12:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"U²AD learns unified normal data representations via score-based generative modeling and a novel time-dependent score network to outperform prior methods in accuracy and early anomaly detection for multivariate time series.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Density-based techniques aim to approximate the probability density distribution of normal data points [5, 6], while boundary-based methods [ 7, 8] focus on finding a compact hypersphere that encloses the representation of the normal data. Both of these paradigms, however, risk oversimplifying the complex, multi-modal geometry of the underlying data distribution. Even attention-based models [ 9, 10, 11], while excelling at capturing temporal dependencies, face limitations stemming from their primary focus on reconstruction fidelity. Ultimately, a common weakness across these diverse paradigms is their reliance on a single principle to define normalcy, which leaves them vulnerable to specific types of unseen anomalies. To overcome these limitations, a solution must be guided by a more comprehensive set of principles."},{"citing_arxiv_id":"2604.21529","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Architectures for Robust Self-Organizing Energy Systems under Information and Control Constraints","primary_cat":"cs.MA","submitted_at":"2026-04-23T10:52:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper presents architecture variants for observers and controllers in self-organizing cyber-physical energy systems that account for information and control constraints.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17998","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection","primary_cat":"cs.LG","submitted_at":"2026-04-20T09:24:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A transformer model guided by a causal graph prior achieves state-of-the-art anomaly detection and root-cause attribution on ASD and SMD benchmarks by restricting main predictions to graph-supported causes while using an isolated shadow path for residual correlations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17616","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08582","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation","primary_cat":"cs.LG","submitted_at":"2026-03-29T15:18:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DBR-AF decouples cross-variable correlations in reconstruction and applies autoregressive flows to model residual densities for improved anomaly detection in multivariate time series.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.21293","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Physics-Guided Tiny-Mamba Transformer for Reliability-Aware Early Fault Warning","primary_cat":"cs.LG","submitted_at":"2026-01-29T05:46:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PG-TMT couples a physics-aligned tri-branch encoder with EVT-calibrated decision rules to achieve higher PR-AUC and shorter detection times at controlled false-alarm rates across multiple bearing datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.12116","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Neural CDEs as Correctors for Learned Time Series Models","primary_cat":"cs.LG","submitted_at":"2025-12-13T01:17:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.15083","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection","primary_cat":"cs.LG","submitted_at":"2025-11-19T03:45:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Fourier-KAN-Mamba combines Fourier features, KAN nonlinearities, and Mamba state-space modeling with a gating mechanism and reports better anomaly detection performance than prior methods on the MSL, SMAP, and SWaT benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.15066","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:02:50+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.04047","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis","primary_cat":"cs.LG","submitted_at":"2024-10-05T06:04:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}