Time_Series
-
Learning What to Share: Expert Specialization for Time-Series Forecasting
2026-10-24 17:36:57Bashar Khoury, Shadi Omari, Assaf SchusterAbstract
A central challenge in multivariate forecasting is deciding what to share across channels and where to specialize. Mixture-of-experts models offer flexible sharing, yet it remains unclear how much of their forecasting gains comes from added capacity or expert allocation. Through controlled comparisons across eleven datasets and three backbones, we show that informative channel assignments improve forecasting beyond matched shared capacity and random allocation. On frozen transformer backbones, persistent channel-specific mixtures outperform input-dependent routing on average. To examine when and how much specialization helps, we introduce GalaxyTS, a controlled synthetic dataset with exact shared and channel-specific forecasting references. It reveals how persistent channel mixtures exploit predictive differences concealed by short input windows and measures gains over matched shared corrections. These insights motivate Persistent Closed-Form Routing (PCR), a plug-and-play method that alternates exact conditional estimation of channel-specific mixture weights with gradient-based training of low-rank residual experts around a frozen pretrained forecaster. Averaged over four forecasting horizons, PCR-K4 achieves dataset-balanced mean squared error reductions of 3.86-14.25% relative to the three frozen backbones. In matched comparisons, PCR outperforms competing specialization methods on average while requiring substantially fewer trainable parameters.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33822
PDF
-
Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning
2026-10-24 16:46:53Huaming Du, Zhixian Xie, Gaoyang Zhen, Gang Kou, Guisong Liu, Yanchao Tan, Wendan Tao, Yuhao Xu, Carl YangAbstract
Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support. However, existing approaches to universal PPG representation learning are predominantly trained on high-quality large-scale datasets obtained from oximeters in hospital settings and often struggle to adapt to sparse and low-quality real-world datasets, thereby limiting their generalization to clinically relevant tasks on prevalent PPG data such as collected from wearable devices. Surprisingly, even after full fine-tuning, PPG foundation models cannot consistently outperform general-purpose time-series models. Therefore, a key question is how to effectively adapt PPG foundation models to target prediction tasks. Through empirical studies on various PPG foundation models, we find that pretrained models often exhibit inherent sparsity and computational redundancy, suggesting that PPG foundation models have learned to activate task-relevant network substructures for different prediction tasks. To preserve this valuable prior knowledge, we propose a structured pruning-and-fine-tuning framework, SPAFT, which regularizes the adaptive fine-tuning process by constraining it to a more relevant and compact parameter space based on parameter importance and structural redundancy. Extensive experiments across four PPG foundation models, five benchmark datasets, and ten downstream tasks demonstrate that SPAFT achieves win rates of 82.8% and 87.5% on regression and classification tasks, respectively. This prune-then-finetune paradigm often enables PPG foundation models to achieve state-of-the-art performance, laying a promising foundation for the real-world clinical deployment of PPG foundation models and the development of personalized PPG foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33788
PDF
-
The Future Is Finer: Multivariate Time Series Super-Resolution Forecasting
2026-10-24 05:48:17Shuhao Li, Weidong Yang, Yue Cui, Fan Zhang, Lu QinAbstract
Web platforms run on multivariate time series, from service telemetry and Web traffic logs to sensor streams served through Web APIs. Yet, retention policies often archive them at coarse granularity to save storage and bandwidth. Decisions such as autoscaling, alerting, and billing operate at finer granularity than existing forecasters reach, since these models predict at the resolution of their input. We therefore introduce Multivariate Time Series Super-Resolution Forecasting (MTS-SRF), which forecasts fine-grained futures from coarse histories, and propose TimeMagnifier to address its three challenges. Fourier Anchor counters data sparsity by fitting each input window to a trend-Fourier structure with sparse cross-variable gating; De-noise Only constrains fine-grained ambiguity by refining along the resolution axis rather than the noise axis, lengthening the grid level by level; and banded DTW Alignment corrects cross-resolution misalignment against the coarse forecast. On the first MTS-SRF benchmark, with ten datasets from five domains, real archived cross-resolution pairs, strengthened baseline adaptations, and five-seed significance tests, TimeMagnifier is best on every dataset, resolution coefficient, and metric against 15 baselines and cuts MSE by 12.3% on average. Its De-noise Only and DTW stages also transfer as a plug-in that lowers the MSE of existing forecasters by 5.1% to 9.0%. Code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33470
PDF
-
Benchmarking System One Models for Time-Series Decision Making: A Case Study of Jev
2026-10-24 02:58:51Jianye Wang, Kexin Zhang, Jiayin Xiong, Hao XueAbstract
Time-series tasks require both accurate predictions and fast decisions. Advances in large models have introduced decision-oriented models that directly output answers and their probabilities, which we call Structured System 1 models. Their applicability to time-series tasks remains underexplored. Using Jev 1.13.0 as a case study, we evaluate time-series classification, event type prediction, oil temperature direction and stock movement prediction, converting continuous forecasting targets into discrete decisions to fit the model interface. We establish a unified evaluation framework using accuracy and AUC. Results show stronger performance on selected explicit temporal patterns and event type prediction, but near-chance discrimination on many numerical sequence classification tasks and stock movement prediction. Some datasets also reveal a gap between ranking quality and final decision accuracy. These findings motivate improvements in temporal representation, domain adaptation, and decision-score alignment. Standardized sample construction, model calls, and result recording support extending the evaluation to future models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33410
PDF
-
Real Time Motion Detection in Video Inspired by Photonic Time Stretch
2026-10-23 22:39:22Callen MacPhee, Yiming Zhou, Bahram JalaliAbstract
Motion perception is fundamental to computer vision and physical AI, and plays a central role in robotics, autonomous vehicles, human-computer interaction, and video compression. Traditional approaches such as background subtraction, frame-differencing and optical flow algorithms often struggle in complex or dynamic scenes, typically sacrificing spatial resolution for computational tractability. Here we introduce MoViD (Motion estimation via Virtual dispersion and phase Detection), a physics-inspired algorithm grounded in the principles that govern photonic time stretch - a highly successful ultrafast realtime data acquisition platform. Drawing inspiration from the optical physics therein, MoViD treats video as a collection of optical time series waveforms associated with pixels. Motion of an object through a pixel broadens the time series spectrum and, after group delay dispersion, induces a temporal phase that exists only if there is motion. Spatiotemporal group delay dispersion templates, corresponding to dielectric functions, classify specific motion trajectories. Unlike conventional empirical phase-based motion-analysis pipelines that require narrow-band spatial channelization and pyramid reconstruction, the physics-based MoViD operates directly on the broadband video signal, vastly increasing its computational speed. The resulting algorithm achieves unprecedented performance in both motion characterization and motion magnification, providing full-resolution motion mapping in real time at nearly 200 frames per second at 4K resolution and 70 frames per second for 8K video - orders of magnitude faster than classical optical flow approaches or learning-based methods. Notably, such extreme performance enables real time motion analysis at ultrahigh resolution for motion detection and compensation in robotics and other autonomous devices.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33351
PDF
-
TempShap: When and How Much a Feature Matters in Time-Series Forecasting
2026-10-23 22:08:16Chi Zhao, Anastasiia Chelnokova, Jing Liu, Elena ParilinaAbstract
Attribution for a time-series forecaster should answer two questions that a feature-level scalar cannot: when in the input window a feature acts, and how much its influence changes across the forecast horizon. Most existing Shapley explainers treat each feature as one player and therefore collapse both axes. We propose TempShap, a retrospective, loss-based Shapley framework whose players are the individual input cells $(t,i)$. Its attribution tensor yields temporal-localization and horizon-impact profiles. We validate these against planted temporal structures, a tractable exact cell game, and a closed-form attribution oracle for a real linear forecaster. Permutation sharing estimates the cell-level game at localized perturbation cost. Under redundant inputs, one-at-a-time scores under-credit substitutable information, whereas the signed Shapley decomposition preserves total value and yields more reliable held-out deletion rankings under mean masking. A planted counterexample isolates the redundancy mechanism. Experiments show a deletion-ranking advantage across Shapley estimators, forecasting benchmarks, and model families. TempShap therefore makes fine-grained Shapley attribution both practical and operationally useful.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33330
PDF
-
TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
2026-10-23 08:30:30Dongchan Cho, Juwon Hwang, Keumyeong Kang, Jiho Han, Namsoon JungAbstract
In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of abnormal system behavior. Since latent-space scoring can mitigate this limitation, we reframe one-class MTSAD as current-point system-state compatibility estimation and propose TENET, the Time-point Encoding Network for Multivariate Time Series Anomaly Detection. We define the current-point system state as a latent representation of the target time point, constructed from variable-level temporal context in the input window. TENET constructs this state through a temporal layer that retrieves window context relative to the current point, encodes time with current-point-centered embeddings, and adaptively mixes the retrieved context with the current representation. With this design, TENET treats the input window not as the object to reconstruct, forecast, summarize, or score, but as context for constructing a latent representation evaluated with a fixed standard-normal negative log-likelihood score. Across benchmark datasets, TENET achieves state-of-the-art performance. Additional experiments further show that TENET remains effective under alternative one-class objectives and outperforms substitutions based on generic sequence encoders, suggesting that its advantage comes from decision-aligned representation construction rather than from a specialized scoring rule. These results indicate that one-class MTSAD can be strong when the latent representation is designed around the current time point.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32337
PDF
-
TT-SAX: A Two-Track Time Series Symbolization for Natural Language Shape Querying
2026-10-22 01:49:10Zhao Tan, Xianglong Bao, Zhipeng Xi, Ming JinAbstract
Natural language querying for time series databases aims to let users find what they need in long histories of data by asking in plain language. Shape queries ask how a series moves. They are the main challenge of this task. Recent work makes them feasible by using symbolization as a bridge between the query and the long history. However, existing symbolizations were designed for compression, similarity indexing, or classification. What a symbolization should provide for natural language querying has not been systematically studied. We therefore examine the definitions of six classical symbolizations against this task and identify three limitations. (1) Direction is missing from the string, (2) direction is measured at too small a scale, and (3) the letters are arbitrary. Three design principles follow. We follow these principles and make a minimal redesign of SAX called TT-SAX (two-track SAX). The level letters stay. Each segment gains a trend letter. It is measured across neighboring segments rather than inside one, and graded to match the adjectives that queries use. We conduct extensive experiments on the public NLQTSBench benchmark, comparing TT-SAX with the six classical symbolizations across six LLMs. TT-SAX outperforms all six on shape queries, and ablations trace its gains back to the three limitations one by one. This paper is the first systematic study of time series symbolization with natural language querying as the design goal. It provides a foundation for future research on this task. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30593
PDF
-
Rethinking Agentic Model Orchestration for Time Series Forecasting
2026-10-21 09:55:04Tong Guan, Tianxiang Zhan, Shirui Pan, Ming JinAbstract
Time series foundation models (TSFMs) perform unevenly across forecasting tasks. Recent work uses agentic model orchestration (AMO) to select or combine TSFMs, often outperforming individual forecasters. Yet these gains may reflect stronger or more complementary candidates rather than better orchestration. To disentangle these effects, we introduce FairAMO, a controlled evaluation protocol with frozen candidate forecasts. Experiments on GIFT-Eval show that AMO improves accuracy, but its gains are bounded by the candidate TSFMs. The best orchestrators reduce MASE by less than 6% relative to the best single TSFM across all tasks. These gains depend on complementarity (different candidates excel on different tasks) rather than the number of candidates. Adding members yields diminishing returns, and a redundant member can erase these gains. The value of historical evidence also saturates quickly. A few recent windows capture all gains, and further history adds none. These findings separate system-level forecasting gains from the contribution of orchestration itself.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29504
PDF
-
Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection
2026-10-21 01:42:19Dongchan Cho, Jiho Han, Juwon Hwang, Changhee Min, Minsang Kim, Namsoon JungAbstract
Time series anomalies take diverse forms, and individual detectors encode different anomaly scoring principles that rarely cover all anomaly types. Recent unsupervised time-series anomaly detectors provide complementary scoring signals, yet deploying them as an ensemble preserves the inference and maintenance cost of every individual detector. We study whether heterogeneous teacher detectors can be distilled into a single lightweight detector in the unsupervised setting, where no anomaly labels are available to define a shared target. AnoMix addresses this by extracting weak pairwise supervision from the training-set anomaly scores of frozen teachers. It normalizes each teacher score sequence independently and trains the student with CoRank, a multi-teacher ranking-distillation objective that converts teacher score gaps into pairwise supervision through teacher consensus. Across seven benchmark datasets, AnoMix successfully integrates complementary teacher scoring principles into a single deployable model, improving over individual detectors and static score ensembles while using a compact student with under 80k parameters on the benchmark settings. A zero-shot variant further shows that the distilled ranking signal transfers to unseen datasets and can outperform large pretrained time-series foundation models for anomaly detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29063
PDF
-
GRAIL: From Saliency to Semantics in Time-Series Explanation
2026-10-21 01:09:56Enver Menadjiev, Yiqiu Shen, Jaesik Choi, Julia StoyanovichAbstract
Explaining a time-series model requires both locating the evidence and extracting meaningful knowledge from it. Yet a single timestep is not a semantic unit: the meaningful patterns live across many samples, not in any one of them. Per-timestep saliency is therefore noisy, high-dimensional, and unstable. Existing methods address this by introducing fixed-size windows and treating them as independent players in a cooperative game. Evaluating a coalition of such players requires defining a ``baseline'' region, which prior work tackles with fixed counterfactuals (e.g., a flat line, noise, or a spectral surrogate). This choice frequently dominates the resulting explanation, obscuring the model's true decisions. To address these issues, we propose GRAIL, a region-based time-series explanation framework that uses domain-specific intervals, such as the P-wave and the QRS complex of an electrocardiogram (ECG) beat, as players. We describe each region with human-readable features and generate counterfactual baselines with an on-manifold conditional generator. Such a choice of players also admits non-temporal features: static covariates enter as singleton players attributed with the temporal regions on one scale, so a patient's tabular evidence (e.g., age, sex) is weighed directly against the signal. We attribute the predictions to the features via Owen values with common-random-number variance reduction. Experimental results on both synthetic and real data show that the proposed framework produces faithful and robust explanations, evaluated under matched on- and off-manifold operators, offering meaningful knowledge to domain experts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29036
PDF
-
Rethinking Time Series Tokenization from a Frequency Perspective
2026-10-20 23:51:24Zelong Tian, Ming Jin, Bo Du, Shirui PanAbstract
Tokenization that partitions time series into subsequences has become a foundational paradigm in modern time series modeling. However, we find that current tokenization strategies inherently introduce spectral distortions, forcing the learned representations to diverge from the true underlying patterns such as trend, periodicity, and seasonality, thereby impairing model performance. Through theoretical analysis from a frequency perspective, we derive the boundary conditions under which such distortions occur. To overcome this distortion, we propose TimeFT, a nearly distortion-free frequency-based tokenizer for time series data. TimeFT obtains tokens through frequency-domain partitioning, frequency shifting, and Nyquist sampling. The method is parameter-free, incurs negligible computational complexity, and can serve as a drop-in replacement for existing tokenizers. Our extensive experiments on diverse tasks such as forecasting, classification, and anomaly detection demonstrate that TimeFT consistently and significantly improves performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28997
PDF
-
Turning TS2Vec into a Foundation Model for Time Series Classification
2026-10-20 17:47:51Vasilii Feofanov, Zhenghan Tai, Andrei Ermakov, Irina RishAbstract
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every dataset: self-supervised pre-training followed by linear probing. Since then, the field has shifted towards foundation models that reuse one encoder across datasets. Yet TS2Vec offers a compact convolutional architecture that operates directly on temporal samples and accepts variable-length inputs without resampling. We ask whether these properties can be retained when the encoder is pre-trained only once, and show that they can: TS2Vec can essentially be turned into a foundation model. Three changes suffice: pre-train on a synthetic corpus, feed the encoder a raw amplitude view and an instance-normalized shape view of the input through two small stems, and distill one specialist encoder per view into a single encoder. The result, TS2Vec-FM, is a 1.6M-parameter dilated convolutional network that, kept frozen, reaches 83.3% on UCR-128 and 75.3% on UEA-27 under linear probing, within 0.3 pp of MantisV2, the current state of the art, and above TS2Vec trained separately on each target dataset. What we find most interesting is how different TS2Vec-FM is from other foundation models in design: near-parity is reached without attention, without a patch tokenizer, and without intermediate-layer extraction, using an "old-school" convolutional encoder and a two-layer MLP stem.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28602
PDF
-
Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks
2026-10-20 16:39:59Erik Stolt, Sanja Karilanova, Ayca OzcelikkaleAbstract
Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of deep SSMs, where computing blocks communicate through spikes, discrete single-bit events rather than continuous activation functions. A particularly important task in time-series processing is forecasting, i.e. predicting future values of a sequence from past observations alone. However, how to best perform forecasting with SNNs is an open question, where the standard autoregressive nature of the data processing with SNNs requires values that are not available during the forecasting phase. In this article, we address this challenge. We explore two closed-loop forecasting strategies, in which the network's own generated values are fed back into the network as if they were observed past values: (i) model-level and (ii) layer-level closed-loop forecasting. We evaluate these approaches on the ETT-small datasets, a standard benchmark for time-series forecasting, under both spike-based and continuous activation functions. We compare the proposed closed-loop approaches against state-of-the-art methods such as SpaceTime, as well as the zero-masking baseline in S4. Both of the proposed approaches perform comparably to or better than zero-masking with S4, and in most cases match SpaceTime. These findings highlight the trade-off between continuous and low-bit quantized activations, and demonstrate that the proposed Deep SSM architectures provide a competitive framework for forecasting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28495
PDF
-
Parameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting
2026-10-20 13:40:48Aliullah, Julian Oelhaf, Edouard Fouch\'e, Jessica Deuschel, Christian Bergler, Andreas Maier, Siming BayerAbstract
Accurate electrical load forecasting supports power-system operation across countries, regions, cities, and buildings, but repeated development of target-specific models is costly. Time series foundation models (TSFMs) provide reusable pretrained backbones, although multi-domain pretraining may not fully capture load-specific characteristics. This paper compares pretrained inference, full fine-tuning, and low-rank adaptation (LoRA) in terms of forecasting accuracy and adaptation efficiency across four electrical load aggregation levels. MOIRAI 1.0 Large serves as the primary backbone, while Chronos-2 assesses whether the findings transfer across model families. The evaluation covers both in-distribution (ID) and out-of-distribution (OOD) settings and examines whether compact adaptation provides consistent gains over strong pretrained checkpoints. Pretrained foundation models outperform the implemented seasonal naive and XGBoost baselines across the evaluated aggregation levels. On MOIRAI Large, rank-16 LoRA reduces normalized mean absolute error (NMAE) by 7.5% on average while updating 3.146 million parameters, about 1% of the model, and retains most of the improvement from full fine-tuning. Chronos-2 achieves lower pretrained NMAE than MOIRAI but benefits less from adaptation. OOD results show that adaptation benefits vary by target, with the clearest gains for the local-area series and several buildings. Overall, LoRA provides a favorable accuracy-efficiency trade-off when adaptation yields a meaningful gain over a strong pretrained checkpoint.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28200
PDF
-
Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
2026-10-20 01:38:24Laurent Mombaerts, Jonathan Taws, Jacopo Gargano, Dinesh Gaddam, Kevin George, Srijan Tiwari, Shreyas RajeshAbstract
Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of text: a guidance block, evolved by outcome-driven reflection and used in a frozen LLM forecaster's prompt. On a refreshed multimodal benchmark (weekly search indices, daily currencies, daily commodities, each window paired with web-retrieved news), we run GEPA-style prompt evolution under strict contamination control to prevent the data leakage common in timeseries benchmarks: the forecaster's knowledge cutoff predates every evaluated window. A 900-word evolved guidance carried by Llama-3.3-70B beats TimeSeries Foundation Models (TSFMs) on held-out data (GM MASE 0.776 vs. 0.898 for TabPFN-TS-3), transfers to more recent models without measurable loss, and costs dollars rather than GPU-days to update. We characterize the loop: out-of-loop gains concentrate in the first reflection, in-loop improvements overstate out-of-loop gains 2-3x unless an untouched monitor arbitrates, and error-only objectives silently suppress the text modality. We provide two extensions. First, compiling the guidance into executable code with a TSFM as a callable tool recovers most of the gain deterministically. Second, ablations show the advantage widens at short horizons and that removing the news text does not hurt the guided forecaster, consistent with the text's value being distilled into policy during learning. We argue that continual prompt evolution is a practical, training-free alternative to retraining for multimodal forecasting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27468
PDF
-
Interpretable PM2.5 Forecasting for Urban Air Quality: A Comparative Study of Adaptive Time-Series Models
2026-10-19 21:47:54Moazzam Umer Gondal, Hamad ul Qudous, Asma Ahmad Farhan, Sultan AlamriAbstract
Accurate short-term air-quality forecasting is essential for public health protection and urban management, yet many recent forecasting frameworks rely on complex, data-intensive, and computationally demanding models. This study investigates whether lightweight and interpretable forecasting approaches can provide competitive performance for hourly PM2.5 prediction in Beijing, China. Using multi-year pollutant and meteorological time-series data, we developed a leakage-aware forecasting workflow that combined chronological data partitioning, preprocessing, feature selection, and exogenous-driver modeling under the Perfect Prognosis setting. Three forecasting families were evaluated: SARIMAX, Facebook Prophet, and NeuralProphet. To assess practical deployment behavior, the models were tested under two adaptive regimes: weekly walk-forward refitting and frozen forecasting with online residual correction. Results showed clear differences in both predictive accuracy and computational efficiency. Under walk-forward refitting, Facebook Prophet achieved the strongest completed performance, with an MAE of $37.61$ and an RMSE of $50.10$, while also requiring substantially less execution time than NeuralProphet. In the frozen-model regime, online residual correction improved Facebook Prophet and SARIMAX, with corrected SARIMAX yielding the lowest overall error (MAE $32.50$; RMSE $46.85$). NeuralProphet remained less accurate and less stable across both regimes, and residual correction did not improve its forecasts. Notably, corrected Facebook Prophet reached nearly the same error as its walk-forward counterpart while reducing runtime from $15$ min $21.91$ sec to $46.60$ sec. These findings show that lightweight additive forecasting strategies can remain highly competitive for urban air-quality prediction, offering a practical balance between accuracy, interpretability, ...
Abstract (translated)
URL
https://arxiv.org/abs/2603.25495
PDF
-
TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences
2026-10-19 20:25:47Rabimba Karanjai, Yiming Bian, Yun-Shiuan Chuang, Jenna L. Ballard, Zijie Pan, Shivani Shekhar, Yixi Li, Yirou Ge, Avinash Thangali, Richard Williamson, Linsey Pang, Prakhar MehrotraAbstract
Analyzing merchant transaction histories requires dynamic temporal filtering, entity resolution, and aggregation over irregular event streams--operations poorly captured by static tabular or time-series forecasting benchmarks. We introduce TxnQA, an analytical QA benchmark comprising 27 task families (81 templates) alongside a 5-scenario fraud-risk reasoning suite that evaluates both verdicts and supporting evidence over synthetic, privacy-mitigated transaction data. Ground-truth answers are computed programmatically, and model performance is decomposed into format-following rate (FFR), conditional content accuracy (CA), and end-to-end correctness (E2E). Evaluating prompted proprietary baselines and six LoRA-adapted open-weight models shows that adaptation reliably enforces output schemas but leaves arithmetic bottlenecks: Gemma-4-31B-IT and Qwen3-8B attain E2E scores of 0.867 and 0.816, whereas evaluated MoE checkpoints reach only 0.632-0.713. Furthermore, on the 500-instance fraud suite, verdict accuracy frequently exceeds 80%, yet joint accuracy (requiring exact evidence attribution) collapses to at most ~23%. These findings identify schema compliance, semantic calculation, and evidence attribution as three distinct bottlenecks in transaction-sequence QA.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27256
PDF
-
Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting
2026-10-19 05:28:22Songlin Du, Ling Luo, Uwe AickelinAbstract
Quantifying uncertainty in time series forecasting is particularly demanding because sequential data exhibit temporal dependence and are prone to distributional changes. Conformal inference has emerged as a powerful uncertainty quantification approach through the construction of prediction sets. Recent advances have introduced online conformal methods that adaptively adjust prediction thresholds through feedback mechanisms. However, the existing feedback mechanism typically relies solely on miscoverage indicators (actual feedback), whether the true label falls within the interval at each time step, while overlooking the empirical prediction threshold (estimated feedback) that is derived from the oracle conformal method. In this paper, we propose Dynamic Dual-feedback Conformal Inference (DDCI), which incorporates a dual-feedback mechanism consisting of actual feedback and estimated feedback. The former drives the primary adjustment of the intervals based on true observations, while the latter dampens excessive expansions or contractions by leveraging empirical thresholds from conformal inference during updates. By balancing these two signals, DDCI achieves more stable and narrower prediction intervals in sequential settings while maintaining near-nominal coverage in practice.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26987
PDF
-
Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs
2026-10-16 14:23:23Xin Qiu, Junlong Tong, Wei Zhang, Xiaoyu ShenAbstract
Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most work uses LLMs as forecasters and classifiers, reasoning studies are few and narrow, and no suite trains and evaluates the full range of capabilities. In this paper, we build the first such suite, with 337K training and 44K evaluation samples across three progressive capabilities, Perceive, Solve, and Reason, and use it to ask how time series should enter an LLM that must master all three, and in what order. We find that a dedicated encoder is essential: with one, a 4B model surpasses GPT-4o on every perception attribute we test, whereas textualizing the series costs 8--10 points in reasoning accuracy. The capabilities then build on one another: learning them in order beats mixing the same data and rivals reasoning-only training with over three times the reasoning data, but only when an encoder is used. Analyses further reveal that capabilities are transferred through distinct network depths rather than simply stacked, and that a stage converged on its own benchmark is not necessarily ready for the next. Distilled into a simple recipe, these findings yield 4B TS-LLMs that, without any target-domain data, outperform four recent 7B TS-LLMs on seven of eight out-of-domain metrics, by up to 11 points. We therefore advocate treating time series as a first-class modality for LLMs, read through dedicated encoders and taught to perceive before they reason.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23521
PDF
