{"total":13,"items":[{"citing_arxiv_id":"2606.27282","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How Good Can Linear Models Be for Time-Series Forecasting?","primary_cat":"cs.LG","submitted_at":"2026-06-25T16:57:50+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Optimized Ridge regression with series-specific preprocessing beats prior linear forecasters and exceeds Transformer, MLP, and CNN baselines on six of eight time-series benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20580","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:38:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A dynamics-informed Temporal Fusion Transformer surrogate emulates stochastic tipping events in global ocean transport simulations with 465x speedup and high-fidelity timing predictions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13678","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:36:46+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"STAIR's three-stage training enables simple temporal models to match or exceed complex baselines on long-term forecasting benchmarks by combining shared learning, individual adaptation, and residual cross-variable modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18839","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making","primary_cat":"cs.LG","submitted_at":"2026-05-13T03:14:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Multi-horizon time series forecasting framework with DLinear/NLinear models for ED boarding time prediction, integrated with external contextual data and deployed via an MLOps prototype.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23474","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GeoCert: Certified Geometric AI for Reliable Forecasting","primary_cat":"cs.LG","submitted_at":"2026-04-25T23:54:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GeoCert uses hyperbolic geometry to unify forecasting with physical reasoning and built-in formal certification, claiming major gains in accuracy and efficiency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16325","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration","primary_cat":"cs.LG","submitted_at":"2026-03-06T05:00:28+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":"2509.23597","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Characteristic Root Analysis and Regularization for Linear Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2025-09-28T03:06:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.14933","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables","primary_cat":"cs.LG","submitted_at":"2025-09-18T13:14:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DAG proposes a dual correlation network for time series forecasting with exogenous variables that captures temporal and channel correlations to better leverage future covariates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.15774","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Time Series Forecasting Through the Lens of Dynamics","primary_cat":"cs.LG","submitted_at":"2025-07-21T16:29:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.11017","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2025-05-16T09:10:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Logo-LLM improves time series forecasting by pulling local dynamics from shallow LLM layers and global trends from deeper layers, then aligning them via new Local-Mixer and Global-Mixer modules.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.00816","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sundial: A Family of Highly Capable Time Series Foundation Models","primary_cat":"cs.LG","submitted_at":"2025-02-02T14:52:50+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2407.13278","ref_index":97,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","primary_cat":"cs.LG","submitted_at":"2024-07-18T08:31:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"operated on both inter-series and intra-series scales to capture channel-wise and time-wise dependencies in multivariate data. Recent works have moved beyond using simple linear layers over discrete time points. TimeMixer suggests that time series exhibit distinct patterns in different sampling scales and proposes an MLP-based multiscale mixing ar- chitecture. TiDE [97] incorporates exogenous variables to enhance the time series prediction. Based on Koopman theory and Dynamic Mode Decomposition (DMD) [98], which is a dominant approach for analyzing complicated dynamical systems, Koopa [99] hierarchically disentangles dynamics through an end-to-end predictive training framework and can utilize real-time incoming series for online development."},{"citing_arxiv_id":"2310.06625","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2023-10-10T13:44:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Baselines We carefully choose 10 well-acknowledged forecasting models as our benchmark, including (1) Transformer-based methods: Autoformer (Wu et al., 2021), FEDformer (Zhou et al., 2022), Stationary (Liu et al., 2022b), Crossformer (Zhang & Yan, 2023), PatchTST (Nie et al., 2023); (2) Linear-based methods: DLinear (Zeng et al., 2023), TiDE (Das et al., 2023), RLinear (Li et al., 2023); and (3) TCN-based methods: SCINet (Liu et al., 2022a), TimesNet (Wu et al., 2023). Main results Comprehensive forecasting results are listed in Table 1 with the best inred and the second underlined. The lower MSE/MAE indicates the more accurate prediction result. Compared with other forecasters, iTransformer is particularly good at forecasting high-dimensional time series."}],"limit":50,"offset":0}