{"total":38,"items":[{"citing_arxiv_id":"2606.05513","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts","primary_cat":"cs.AI","submitted_at":"2026-06-03T23:40:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EpiEvolve achieves 0.629 accuracy in streaming COVID-19 forecasting by using episodic memory, reflection on delayed labels, and regime-aware retrieval, outperforming static LLMs (0.561) and CDC ensembles (0.325) while halving recovery lag after regime shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05413","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-03T20:27:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02497","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bridging the Last Mile of Time Series Forecasting with LLM Agents","primary_cat":"cs.AI","submitted_at":"2026-06-01T17:03:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An LLM-agent system is proposed to revise statistical time series forecasts with weakly structured business context via tool use and constrained reasoning actions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26320","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding","primary_cat":"cs.LG","submitted_at":"2026-05-25T20:35:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MultiSeismo is a new multimodal seismic dataset with 16K events and SeisModal is a domain-adapted model that outperforms general multimodal models on seismic reasoning tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28866","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-22T06:13:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"COM integrates geometric constraints into token initialization and training to preserve continuity and ordinality in time series tokens, improving token-based TS-LLM performance on benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21975","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs","primary_cat":"cs.LG","submitted_at":"2026-05-21T04:09:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"StockR1 unifies LLM-based financial reasoning and time-series forecasting by emitting verifiable forecast actions that condition a decoder, optimized via consistency-grounded RL to improve accuracy on QA and prediction tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21295","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:25:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17340","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density","primary_cat":"cs.LG","submitted_at":"2026-05-17T09:19:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting on TSLib, GIFT-Eval, and GluonTS benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14636","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning","primary_cat":"cs.AI","submitted_at":"2026-05-14T09:49:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TCFT trains LLMs on temporal critique tasks to reduce post-cutoff knowledge leakage by 37-42 percentage points over prompting and standard SFT on Qwen models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14422","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions","primary_cat":"cs.LG","submitted_at":"2026-05-14T06:10:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12375","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts","primary_cat":"cs.LG","submitted_at":"2026-05-12T16:41:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Structured LLM agents correct agricultural yield forecasts from models like XGBoost, cutting MAE by 20-28% and MASE by up to 66% on strawberry and corn datasets.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"static prompts toward iterative loops of reasoning and tool use. This \"ReAct\" style approach [28] allows a model to plan a step, execute an external query, and then adjust its logic based on the result. In time-series work, this has mostly involved using LLMs as sophisticated feature 3 extractors or using fine-tuned models to interpret data directly [13]. Models like Time-LLM [14], for instance, treat time-series data as a linguistic pattern-matching problem to generate forecasts. This trend extends into finance, where researchers are combining historical prices with news sentiment to build more explainable, multi-modal forecasting tools [30]. Some have even used LLMs to \"guess\" the underlying structure of a dataset to help train Graph Neural"},{"citing_arxiv_id":"2605.16361","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification","primary_cat":"cs.LG","submitted_at":"2026-05-09T13:56:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TailedTS supplies 24.69 billion Wikipedia page-view records as a public benchmark for heavy-tailed time series forecasting and periodicity analysis, revealing weaker periodic structure in high-traffic pages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05790","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"GazeMind: A Gaze-Guided LLM Agent for Personalized Cognitive Load Assessment","primary_cat":"cs.HC","submitted_at":"2026-05-07T07:26:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GazeMind encodes gaze data for LLM reasoning to deliver interpretable, personalized cognitive load predictions that generalize across tasks without fine-tuning and outperform baselines by over 20% on a new 152-person dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27351","ref_index":73,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Heterogeneous Scientific Foundation Model Collaboration","primary_cat":"cs.AI","submitted_at":"2026-04-30T03:02:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Sciagents: automating scientific discovery through bioinspired multi-agent intelligent graph reasoning.Advanced Materials, 37(22):2413523, 2025. [72] Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, et al. Time-llm: Time series forecasting by reprogramming large language models.arXiv preprint arXiv:2310.01728, 2023. [73] Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han, and Dongmei Zhang. Table meets llm: Can large language models understand structured table data? a benchmark and empirical study. InProceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 645-654, 2024. [74] Shaghayegh Sadeghi, Alan Bui, Ali Forooghi, Jianguo Lu, and Alioune Ngom."},{"citing_arxiv_id":"2604.26762","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework","primary_cat":"cs.LG","submitted_at":"2026-04-29T14:57:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ST-PT turns transformers into explicit factor graphs for time series, enabling structural injection of symbolic priors, per-sample conditional generation, and principled latent autoregressive forecasting via MFVI iterations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"in [10] suggest that raw expressive power is not a substitute for an appropriate inductive bias. Time Series Forecasting under Data Scarcity.Under data scarcity, the dominant strategies compensate withexternal data. Meta-learning adapts MAML-style objectives to temporal tasks [ 31, 32], and time-series foundation models such as TimeGPT [33], large pretrained LM-repurposing approaches [34, 35], and in-context fine-tuning [36] leverage massive source corpora. These paradigms assume statistical overlap between source and target; under pronounced domain shift their benefits diminish. A complementary and less-explored direction is to compensate withstructural human knowledgeinstead of external data-precisely the setting in which the prior-injection capability of ST-PT (RQ1)"},{"citing_arxiv_id":"2604.21479","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction","primary_cat":"cs.CV","submitted_at":"2026-04-23T09:39:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A framework encodes observed trajectories and HD maps into tokens for frozen LLMs to perform spatio-temporal reasoning and predict future vehicle paths with a linear decoder.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18305","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2026-04-20T14:14:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAARL decomposes co-evolving time series into autoregressive segments, builds a temporal dependency graph, serializes it into a narrative, and uses LLMs for interpretable forecasting via chain-of-thought reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17295","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics","primary_cat":"cs.AI","submitted_at":"2026-04-19T07:25:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLaTiSA is a vision-language model trained on a new 83k-sample hierarchical time series reasoning dataset that shows superior performance and out-of-distribution generalization on stratified TSR tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10291","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale","primary_cat":"cs.AI","submitted_at":"2026-04-11T17:15:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"[17] Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. Gpt-4o system card.arXiv preprint arXiv:2410.21276, 2024. [18] Aya Abdelsalam Ismail, Mohamed Gunady, Hector Corrada Bravo, and Soheil Feizi. Bench- marking deep learning interpretability in time series predictions.Advances in neural information processing systems, 33:6441-6452, 2020. [19] Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, et al. Time-llm: Time series forecasting by reprogramming large language models.arXiv preprint arXiv:2310.01728, 2023. [20] Slava Kalyuga. Expertise reversal effect and its implications for learner-tailored instruction. Educational psychology review, 19(4):509-539, 2007."},{"citing_arxiv_id":"2605.05211","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective","primary_cat":"q-fin.PR","submitted_at":"2026-04-10T17:36:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"This review synthesizes LLM uses in stock forecasting and catalogs key practical pitfalls from a hedge-fund viewpoint.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"heterogeneous graph, and predicts market index trends with a knowledge-enhanced Heterogeneous Graph Transformer, outperforming baselines. D. Tokenization/Symbolization of Stock Prices Utilizing the pattern recognition capabilities in LLMs, time series numeric values can be first discretized into inter- vals or bins [44] and then mapped to tokens (or embeddings) [10], [39], [15], [40], [41]. The resulting token sequence is used as input to an LLM. In this setup, time series forecasting is represented as simply next-token prediction of the token sequence. Because LLMs excel at capturing long- range dependencies and repetitiveness in text, this technique enables models to learn seasonality, trend, and autocorre- lation patterns, which may be highly relevant in predicting"},{"citing_arxiv_id":"2604.05504","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Semantic Communication with an LLM-enabled Knowledge Base","primary_cat":"eess.SP","submitted_at":"2026-04-07T06:58:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SC-LMKB uses LLM-generated data with cross-domain fusion to cut hallucinations and delivers up to 72.6% gains on cross-modality retrieval tasks over standard semantic communication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.04475","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Discrete Prototypical Memories for Federated Time Series Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-04-06T06:57:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.04175","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Uncertainty-Aware Foundation Models for Clinical Data","primary_cat":"cs.LG","submitted_at":"2026-04-05T16:44:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The work introduces uncertainty-aware foundation models for clinical data by learning set-valued patient representations that enforce consistency across partial observations and integrate multimodal self-supervised objectives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.12451","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Overcoming the Modality Gap in Context-Aided Forecasting","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:05:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A semi-synthetic augmentation creates the CAF-7M dataset and demonstrates that improved context data enables multimodal models to outperform unimodal baselines in context-aided forecasting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.14200","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning","primary_cat":"cs.LG","submitted_at":"2026-02-15T15:50:02+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":"2602.08318","ref_index":52,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","primary_cat":"stat.ML","submitted_at":"2026-02-09T06:48:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.17683","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates","primary_cat":"cs.LG","submitted_at":"2026-02-04T17:48:52+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":"2511.20577","ref_index":21,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","primary_cat":"cs.LG","submitted_at":"2025-11-25T18:09:42+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":"2511.08947","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting","primary_cat":"cs.AI","submitted_at":"2025-11-12T03:48:05+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AlphaCast is a training-free LLM framework that performs interactive multi-stage reasoning for time series forecasting by integrating feature extraction, knowledge bases, case libraries, and contextual pools.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.01101","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","primary_cat":"cs.CL","submitted_at":"2025-11-02T22:33:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.23090","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MAP4TS: A Multi-Aspect Prompting Framework for Time-Series Forecasting with Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-10-27T07:51:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MAP4TS combines global, local, statistical, and temporal prompts derived from classical time-series analysis with raw embeddings via cross-modality alignment to improve LLM forecasting performance across eight datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.12089","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RadarPLM: Adapting Pre-trained Language Models for Marine Radar Target Detection by Selective Fine-tuning","primary_cat":"eess.SP","submitted_at":"2025-09-15T16:16:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RadarPLM adapts PLMs for marine radar target detection with lightweight adaptation and selective fine-tuning based on online learning values, reporting at least 6.35% average detection gains in low SCR conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.05215","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BEDTime: A Unified Benchmark for Automatically Describing Time Series","primary_cat":"cs.CL","submitted_at":"2025-09-05T16:18:20+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BEDTime benchmark tests 17 models on describing time series structure and finds vision-language models outperform dedicated time-series-language models and language-only approaches, with all models fragile to robustness tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.02967","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2025-09-03T03:11:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AR-KAN combines a pre-trained AR module with KAN to reduce redundancy while preserving temporal features, delivering lower probabilistic approximation error and stronger forecasting results on synthetic almost-periodic signals and real datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.10630","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:15:50+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":"2502.09741","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","primary_cat":"cs.CL","submitted_at":"2025-02-13T19:54:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FoNE encodes numbers as single tokens via Fourier features and outperforms subword and digit-wise embeddings on addition, subtraction, and multiplication with far less data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.04047","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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},{"citing_arxiv_id":"2407.13278","ref_index":214,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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":"learning [146] and instruction following [208]. Therefore, the paradigm of leveraging natural language instructions or task examples to guide the model in addressing novel tasks has emerged as a groundbreaking approach [209], [210], [211], which has become a potential solution for time series analysis tasks [212]. Recent literature, such as PromptCast [212], UniTime [213], and TimeLLM [214] focus on investigating a prompt template to enable LLMs to perform the forecasting task. There are other works represented by Autotimes [55], [215], that attempt to design soft prompts for time series data. However, existing prompting approaches are tailored for forecasting, and how to empower LLMs to other time series tasks besides forecasting is relatively unexplored."}],"limit":50,"offset":0}