Papers for
financial data analysts
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
MammothDP protects health data with private boosted decision trees
MammothDP: Private Boosted Decision Trees Ready for Trusted Hardware and Leakage-free Hyperparameters
Abstract: Data spaces like the European Health Data Space (EHDS) require the protection of sensitive data in studies during the data's processing and the study's release alike. In this work, we investigate how to implement this mandate using established trusted execution environments (TEEs) and timing side-channel hardening to protect the processing even under a compromised server, and the state-of-the-art differential privacy (DP) notion to protect the release of studies on tabular data. This combined setup could seem to complete the picture, but in fact raises unexpected security challenges that we mitigate by introducing MammothDP: a significant milestone towards a holistic machine learning system based on the recent gradient boosted decision tree learner S-BDT that is provably DP if used within a privacy filter, timing side-channel hardened, and deployed on a TEE. To achieve a strong privacy-utility tradeoff, we introduce two novel components: an early stopping criterion that adaptively selects the number of trees without any privacy overhead, and an improved rollback protection that is no longer vulnerable under timing side-channel attacks.
Gaussian process method finds changes in time series data reliably
Time Series Change Point Detection with Gaussian Processes
Abstract: This paper proposes a novel general Gaussian process framework for change point detection in time series. A change is defined as an alteration of the hyperparameters of the Gaussian process prior. We formulate the problem in the context of statistical hypothesis testing and demonstrate its performance over both offline and online multiple change points detection. The approach provides theoretical guaranties of its performance. An important advantage of the developed framework is that it does not need a detailed specification of the time series function before and after a change. The hyperparameter values are learned from the data. Comprehensive evaluation of the proposed framework is provided both on synthetic and real data and its efficiency is demonstrated.
Benchmark compares ways to keep important facts with limited text
CoRA-Bench: Evaluating Evidence Preservation by Context Selectors Under Token Budgets
Abstract: Context selection can reduce input length during long-input inference but can remove evidence required to answer a query. We introduce CoRA-Bench, a benchmark for evaluating evidence preservation under shared token budgets. We compare head and tail truncation, BM25, dense retrieval, dense retrieval with reranking, LLMLingua-2, and Provence across BABILong, LOONG Financial Spotlight, a custom NoLiMa diagnostic, and LongMemEval. Evidence-preservation results reveal task-dependent tradeoffs: BM25 achieves 0.921 supporting-fact recall on BABILong at 128K, dense retrieval and dense reranking each achieve 0.908 needle recall on NoLiMa at 64K, and dense retrieval achieves 0.993 answer-bearing-turn recall on LongMemEval at 64K. Evidence, token retention, and complementary reader evaluations use the same selected contexts. Reader evaluations use dataset-native answer metrics and three runs on the same questions, with paired bootstrap confidence intervals. At a 32K budget, BM25 achieves 46.20% BABILong answer accuracy and dense retrieval achieves 71.13% LongMemEval accuracy. The results show that method rankings vary across evidence types and between evidence recall and downstream accuracy.
Functional data privacy works better when smoothing comes first
On the Order of Privacy and Smoothing in Functional Mean Estimation
Abstract: Differential privacy (DP) is a leading framework for privacy protection, yet privacy mechanisms tailored to functional data analysis (FDA) remain relatively underexplored. For functional mean estimation, we investigate a fundamental question regarding the ordering of privatization and estimation by comparing two canonical pipelines: Fit-Then-Protect (FTP), which smooths trajectories before privatization, and Protect-Then-Fit (PTF), which privatizes observations at discrete time points before smoothing. When data are observed without error, we prove that FTP achieves strictly smaller mean squared error than PTF asymptotically (as the sample size increases) under the same $μ$-Gaussian differential privacy ($μ$-GDP) budget in both finite-dimensional Hilbert spaces and infinite-dimensional reproducing kernel Hilbert spaces (RKHS). Simulation studies support our theory and explore settings with observation error and fitting constraints, demonstrating that FTP outperforms PTF under small observation noise, whereas PTF can become preferable in high-noise settings. In addition to this comparison, we establish a novel GDP guarantee for Gaussian perturbations taking values in a Banach space, extending existing results beyond the RKHS setting.
Parallel speedup of sparse nonlinear system identification on multicore CPUs
Parallel Sparse Identification of Nonlinear Dynamics in Python: Task- and Data-Parallel SINDy with Numba, OpenMP, Threads and Multiprocessing for the Lorenz and Rössler Systems
Abstract: The sparse identification of nonlinear dynamics (SINDy) recovers interpretable governing equations from time-series data by sparse regression over a library of candidate functions. As data sets, candidate libraries and the number of repeated fits grow, the cost of SINDy becomes dominated by the evaluation of the library matrix and its least-squares problems. We present an open-source Python implementation of SINDy in which a single set of loop-based kernels is just-in-time compiled with Numba and executed on a shared-memory multicore node by four interchangeable back ends: Numba prange, OpenMP directives through PyOMP, Python threads that release the global interpreter lock, and multiprocessing with shared memory. The normal equations are accumulated in one cache-blocked pass over the data, with an automatic fallback to a tall-skinny QR reduction for ill-conditioned problems. Two decompositions are studied on the Lorenz and Rössler systems: an ensemble (task-parallel) workload of 960 independent identifications and a library (data-parallel) workload of one trajectory with $2\times10^7$ samples and a fifth-order library of 56 candidate terms. All back ends recover the exact sparsity pattern in every identification, with coefficient errors identical to PySINDy. On a dual-socket Intel Xeon E5-2650 v4 node of the University of Houston-Downtown HPC cluster (24 cores, 48 hardware threads), the compiled serial code is 4.3-5.6x faster than PySINDy, the parallel back ends reach speed-ups of 14.8-20.3 on 24 cores (parallel efficiency 0.61-0.84), and the overall time to solution is reduced by up to 117x with respect to PySINDy. We analyse the differences between the back ends, the effect of the two sockets and of hyper-threading, and give practical recommendations.
Calibrated repairs improve accuracy in financial question answering
When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering
Abstract: Financial question answering can fail even when a model extracts a plausible number from the supplied evidence: the answer may attach it to the wrong entity, period, unit, or accounting concept. Asking the model to verify and revise its draft can help, but open-ended revision may alter content that was already correct or inspect the wrong relation and reinforce the original error. We formulate repair as a decision that balances the information it may recover against the correct content it may damage. Based on this trade-off, we introduce Calibrated Answer Repair (CAR), which first estimates whether a draft is likely to benefit from repair, then selects a targeted check, localizes the relevant evidence or draft span, and limits the permitted edit. Across FinRank, Fin-RATE, and FinQA with three open-weight models, CAR outperforms generic verification in all dataset-model settings. At the system level, it recovers 14.6% of initially missed answer requirements while damaging 2.1% of initially correct ones. Its post-draft token cost is over 30 percent lower than the iterative revision alternatives. Ablations on two dataset-model settings show that evidence localization and bounded editing are the main contributors to CAR's gains.
Financial agents benchmark measures real-world task skills and accuracy
AgenticFinBench: Benchmarking Financial Agents on Diverse Tasks from Real-World Requests
Abstract: Financial agents are becoming an important class of real-world AI systems. Financial tasks vary widely in type and difficulty, and many are open-ended with no ground-truth answers. However, existing benchmarks neither capture this breadth and open-endedness nor separate grounding from correctness. To bridge this gap, we introduce $\textbf{AgenticFinBench}$, a benchmark of 230 real-world financial tasks spanning 8 categories, 2 languages, and 4 complexity levels. We also propose a reference-free evaluation framework that combines question-specific rubrics with a two-stage claim audit that detects hallucinations, defined as claims absent from the agent's trace and refuted by external evidence. This framework better matches how financial work is assessed in practice. Experiments across 18 agent configurations reveal three key findings: (1) Ignoring hallucinations can overstate agent performance: hallucination auditing lowers the baseline leader's score by 7.58 points and moves it to fourth place. (2) Harness differences explain more variation in evidence grounding than model differences (28.6% vs 8.8%). (3) Quality scores fall from 89.44 on direct retrieval to 79.18 on the most complex tasks. Case studies show that agents struggle to explain how events affect company profits or stock prices, compare financial data on a consistent basis, and justify their conclusions. By releasing AgenticFinBench, we aim to advance financial reasoning, factual verification, and agent design for more reliable responses to diverse real-world financial requests. Our project page is at $\textbf{https://nashnovaresearch.github.io/AgenticFinBench/}$.
Tree based rules improve neural network training performance
TreePIN$^{2}$: Tree-Prior Initialized Neural Networks
Abstract: Fitted decision trees provide predictive knowledge for neural network initialization. We present Tree-Prior Initialized Neural Networks (TreePIN$^{2}$), a method that translates split rules, decision paths and leaf predictions into initial network weights and biases for classification and regression. Sigmoid units encode split responses, hidden units combine them along decision paths, and leaf predictions initialize the output layer. We calibrate split softness using local training margins, sample support and impurity reduction, relating the initial responses to the data at each node. All weights and biases remain trainable, allowing gradient-based optimization to refine the transferred decisions and their combinations. Across six classification and six regression tasks with twenty paired seeds, TreePIN$^{2}$ improves mean initial and early validation performance over initialization baselines on most tasks. After fifty epochs, it achieves the best or tied-best mean validation performance among the six compared methods on ten tasks. Paired ablations show how split calibration and leaf-informed output initialization contribute to the starting predictor and its subsequent learning.
Causal discovery assumptions often fail in real financial data studies
Where Causal Discovery Breaks on Real Data: Measuring the Assumptions One Property at a Time
Abstract: Causal discovery is usually evaluated on simulators or on systems whose ground truth follows from physics or design. When it fails on other real data, the failure is attributed to assumptions that may not hold, but which ones fail, and by how much, is rarely measured. We measure the observable properties of the data they bear on, one property at a time, on a real panel. The case study follows 2,901 US public firms over 31 quarters, with 71 types of corporate action from SEC 8-K filings, 11 financial-statement items, and an expert graph over 651 action-state pairs. The panel breaks measurable requirements of discovery: tails that survive winsorisation, balance-sheet items and revenue close to random walks, and interventions too rare to detect effects of a tenth of a standard deviation in 40 of 71 actions. Even so, a marginal test ranks expert-labelled direct above not-direct pairs within each action (AUROC 0.658) better than every null we built, so the panel does carry information about which pairs are direct. Tuned discovery methods, in configurations feasible at this panel size, recover less of it than a simple pairwise cross-correlation when pairs are ranked within each action, and no more when they are ranked within each target, which removes what the target alone predicts. Most direct pairs (132 of 222) involve actions below the support needed for 80% power against a 0.1-SD effect. For flow targets, conditioning on the target's other expert-labelled parents, often filed alongside the action, erodes the marginal discrimination, and most not-direct associations survive it: even with the graph's parent sets supplied, the expected separation does not emerge. For each property, we give a diagnostic computable before any discovery method is run.
Multimodal learning improves long financial text analysis with tables
Grounding Long Financial Text with Semantically-Enriched Tables via Multimodal Learning
Abstract: We propose a multimodal transformer framework for efficiently modeling long1 financial documents that combine structured tabular data with noisy, unstructured2 textual disclosures. The framework represents financial tables as semantically3 enriched token sequences and integrates them with long-form text through a cross-4 attention mechanism that explicitly captures cross-modal dependencies. In par-5 ticular, we augment each numerical variable with a semantic embedding derived6 from its textual definition, enabling the model to encode both numerical magnitude7 and economic meaning. This design yields a more expressive and parameter-8 efficient representation of tabular data compared to value-only embeddings. Using9 a large-scale dataset of financial statements and MD&A disclosures, we show that10 structured numerical features remain the dominant source of predictive signal;11 however, textual information provides consistent incremental gains when incor-12 porated via cross-attention rather than simple concatenation. Our results further13 demonstrate that noisy textual disclosures are most useful when conditioned on a14 stable, semantically structured tabular representation. In particular, using frozen15 variable-level tabular representations as cross-attention queries enables the model16 to weight MD&A chunks differently for each financial variable and observation.17 These findings suggest that cross-attention provides an efficient mechanism for18 table-conditioned aggregation of long-form narrative evidence.
Adaptive trend analysis improves anomaly detection in time series data
AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection
Abstract: The rapid proliferation of Industrial Internet of Things devices has led to increasingly large-scale and non-stationary time-series data, posing significant challenges for time-series anomaly detection (TSAD). Existing approaches often focus on reconstructing or forecasting observations while overlooking the role of trend dynamics, which constitute a major source of non-stationarity and contain valuable information for anomaly identification. To address this limitation, we propose AdaTrendLike, a TSAD framework that directly estimates trend likelihoods for anomaly detection. Specifically, we introduce Standardization Embedding to capture local statistical characteristics as latent representations and AdaDetrending to adaptively decompose input series into trend and detrended components. The detrended component is processed through a Fast Fourier Transform and a complex-valued convolutional neural network to learn normal periodic patterns, while TrendEst models the distribution of the trend component. Based on the estimated distribution, TrendLike computes anomaly scores by measuring the likelihood of observed trends, enabling effective detection of deviations from normal behavior. In addition to improving detection performance, the proposed framework provides feature-level interpretability by identifying anomalies through deviations in the estimated trend distribution. Extensive experiments on five public benchmark datasets demonstrate that AdaTrendLike consistently outperforms state-of-the-art TSAD methods, validating its effectiveness and robustness across diverse application scenarios.
Latent embedding patch transformer detects anomalies in time series data
LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection
Abstract: Time-series anomaly detection is dominated by reconstruction-based neural detectors, whose objective is structurally flawed. Since the target is also the input, an expressive model can learn to reconstruct anomalies too, leaving uninformative residuals. Recent large-scale benchmarks show that, on curated data, elaborate deep detectors rarely beat simple statistical baselines, while current leaders rely on representation learning. We propose LEAP (Latent Embedding Anomaly Patch-Transformer), which combines masked prediction with latent representation-based anomaly evidence, without relying on reconstruction or attention-based scoring. The model removes patches from a window and predicts them from the remaining temporal and cross-channel context, so prediction errors measure how well learned dynamics explain hidden segments. Deterministic complementary group masking ensures every time step is scored while hidden, with identical visible fractions during training and inference. LEAP adds three label-free evidence sources: latent-embedding novelty calibrated by local density, local temporal contrast, and per-channel novelty pooled over channels selected by six label-free criteria. Under the TSB-AD protocol, the full model achieves a VUS-PR of $0.5179 \pm 0.0022$ on $180$ held-out multivariate series. On TSB-AD-U, a univariate variant combining multi-scale masked-prediction scoring with latent novelty, without contrast or channel-pool novelty, achieves $0.6194 \pm 0.0016$ on $350$ held-out series. Both results average three random seeds. A five-stage ablation on TSB-AD-M, supported by paired Wilcoxon signed-rank tests, shows statistically significant gains from each successive component.
Predictive methods improve flow matching under changing data distributions
Minimax-Optimal Predictive Flow Matching under Distribution Drift
Abstract: Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive. We study this predictive problem for a fixed, possibly nonconvex, neural class, with dynamic regret against the best represented field of each round. We propose DyProd-FM, which refits flow matching on dyadic historical prefixes and selects among the fits with a sleeping Prod master. Without knowing any drift budget, it attains regret $\widetilde{O}(\min\{N_ω+1,1+\sqrt{TΩ}\})$ in the relative velocity risk variation $Ω$ and $\widetilde{O}(\min\{N_μ+1,1+T^{1/3}V_μ^{2/3}\})$ in the target-law variation $V_μ=\sum_t W_2(μ_{t+1},μ_t)$, up to approximation and fitting costs. Matching lower bounds for fixed classes show that both rates are optimal in $T$ and in the budgets up to logarithmic factors. Prior optimal dynamic-regret guarantees rely on a convex decision set with strongly convex or exp-concave losses, whereas our class may be nonconvex and no curvature in its parameters is assumed. The target-law rate rests on a second-order link between the two variations, which the base noise of flow matching provides.
Agentic rule discovery improves auditing of data quality rules
AuDQ: Auditable Data Quality through Agentic Rule Discovery
Abstract: High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable through immutable execution traces. As a first step toward validating this vision, we present a concrete implementation of its agentic rule-discovery core with two rule acquisition modes (Full-Agentic and Guided) and a human-in-the-loop (HITL) review interface. We define an evaluation framework and run experiments addressing whether our fully autonomous, divide-and-conquer agentic rule discovery produces rules of the same quality and diversity as those specified by a human expert, reporting preliminary results on two real world industry datasets in the finance and retail domains.
Arabic natural language processing advances financial document understanding
Arabic Financial NLP
Abstract: Financial communication connects numerical accounts of economic activity with explanations of performance, responsibility and future expectations. Arabic financial natural language processing offers methods for studying these connections across corporate reports, market disclosures, journalism and banking interactions. Its contribution to digital humanities depends on retaining the relationship between a computational representation and the document from which it was made. This chapter follows that relationship from source collection and Arabic text processing to the analysis of vocabulary, evaluation, entities, causal attribution and multilingual reporting. It then examines what financial summaries and retrieval-grounded answers preserve or lose, and how dialectal intent detection changes the perspective from institutions speaking to institutions listening. Published Arabic resources are discussed in relation to the questions they were designed to answer, with a distinction between financial pretraining corpora, annotated datasets and evaluation benchmarks. A running constructed example connects the methodological discussion without presenting illustrative analysis as empirical findings. The chapter argues for an account of Arabic financial NLP in which linguistic context, documentary provenance and interpretive judgement remain part of the evidence throughout the analytical process.
FracTS generates diverse long-range multivariate time series efficiently
FracTS: Hierarchical and Autoregressive Time Series Generation
Abstract: Time series are ubiquitous across different domains, and the growing use of synthetic data for privacy-preserving sharing, data augmentation, and stress testing makes time series generation increasingly important. Early generative approaches are predominantly autoregressive, which can suffer from low sample diversity, error accumulation, and difficulty modeling long-range dependencies. In this paper, we introduce FracTS, a hierarchical, coarse-to-fine autoregressive model for multivariate time series generation. Inspired by fractal generative modeling developed for images, FracTS adapts the paradigm from 2D to 1D sequences by learning a multi-scale representation that captures global trajectory structure at coarse scales and local dynamics at fine scales while following the autoregressive nature of time series. In contrast to unstructured images, time series are structured, allowing easy automated or designated temporal feature processing optimized for the model, and global (static) feature extraction describing the instances that generate the corresponding time series in the collection. We incorporate them in the generation process to further improve the generation quality. The design naturally handles multivariate dependencies and improves long-horizon temporal coherence without requiring fixed-length inputs. Experiments on five datasets (two conditional, three unconditional) conducted against seven baselines show that FracTS consistently outperforms baselines across marginal distribution and predictive ML utility, and correlation preservation in the unconditional setting. In particular, the predictive ML utility is averagely improved by 100.0% and 75.0-81.0% for unconditional and conditional time series datasets compared to the best baseline (relative error computed on dataset-averaged raw values). Code is available at: https://github.com/BetterdataLabs/fracts.
Long horizon forecasting improved by reusing a compact forecasting block
Compose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off
Abstract: Most long-horizon forecasters emit the complete future in one pass. We ask whether a compact operator can instead be reused to emit contiguous future blocks, trading stored parameters for sequential computation. Recursive Functional Decomposition (RFD) factorizes the horizon mapping into three parameter-shared block predictions. The blocks occupy disjoint future intervals and are concatenated, not added as trend, seasonal, or residual components, and each emitted block joins the rolling context that conditions the next application. In controlled three-seed experiments, removing forward feedback hurts all four evaluated datasets while stopping gradients through it changes little, so the useful signal is the evolving forecast state itself; reapplying the shared operator helps consistently, but by less than widening it. The model uses 0.08--0.46M parameters, yet its sequential channel-wise execution is slower and more memory-intensive than an iterative baseline at high channel count. In a frozen long-context evaluation against ten strong baseline families, RFD records lower test error in 23 of 24 cells; the comparison is cross-protocol, with RFD using 512/720-step context and the baselines using 96.
Large language models predict stock returns but struggle with earnings forecasts
From SEC Filings to Financial Signals: Evaluating LLMs on Stock Market Reactions and Analyst Forecasts
Abstract: Form 10-Q MD&A sections combine long-form management narrative with accounting and forward-looking information. Benchmarks for financial filings commonly evaluate question answering or numerical reasoning, leaving unclear whether outputs from large language models (LLMs) align with market and analyst outcomes. We evaluate prompted, zero-shot outputs from 13 general-purpose and finance-specialized LLMs on 45,964 Form 10-Q filing events from 2001 to 2024, linking MD&A text to cross-sectional fundamental ranks, pre-filing analyst forecasts, and realized abnormal returns. The evaluation covers return ranking under five controlled information views and next-quarter EPS forecasting under direct and consensus-anchored interfaces. Relative to disclosure alone, adding cross-sectional fundamental ranks raises mean effective-date rank correlation (RankIC) by 0.0089 for effective-event-date returns and 0.0098 for following-day returns, whereas analyst-summary context provides no comparable average gain. Across the four disclosure-containing views, finance-specialized models show an effective-event-date group advantage but no statistically reliable following-day advantage, while general-purpose Qwen models produce the strongest individual return-ranking results. Under the full-information view, direct LLM forecasts average the 43.4th percentile of the analyst distribution and do not consistently beat individual analysts. Consensus anchoring raises the mean inside-range share from 41.1% to 59.5% but increases reported-EPS error.
Dataflow system boosts streaming llm inference efficiency and cuts resource use
Accelerated Dataflow: scaling inference in streaming data analytics with efficiency
Abstract: Streaming data analytics helps businesses identify opportunities and spot risks in a timely fashion. As large language model (LLM) usage grows, people are exploring incorporating agents or LLMs in streaming data pipelines to help find patterns in datasets without supervision or interpret natural languages for content moderation. However, most streaming systems are currently optimized for data movement and perform poorly on GPU intensive workloads such as performing inference with LLMs. We introduce a system on Google Cloud Dataflow designed to tackle hybrid streaming machine learning workloads with co-designed autoscaling on heterogeneous worker pools and prefix-aware batching. This increases throughput 1.5x to 2x for streaming pipelines using LLMs while maintaining similar latency with up to 75% peak resource savings and 84% lower peak tail latency compared with existing streaming data processing systems.
TPUs accelerate large scale analytical queries with high speed
The Case for TPU-Accelerated Analytical Query Processing
Abstract: Large-scale analytical query processing requires computing substrates capable of immense distributed scale-out. Tensor Processing Units (TPUs) perfectly embody this extreme-scale architecture, offering massive computational density and highly scalable optical pod-level interconnects. Despite these advantages, TPUs have so far remained largely unexplored for analytical database workloads. In this paper, we present the first comprehensive case for TPU-accelerated analytical query processing by running all the TPC-H queries entirely on the TPUs. We introduce Native TPU Accelerator (NTA) for analytical query processing, which provides hardware-conscious algorithm design and optimizations in JAX/XLA. By exposing the TPU's structural mechanics, we demonstrate how dynamic, memory-bound database operations can be rewritten into deterministic JAX programs. We engineer a suite of novel execution strategies that leverage both the TPU's TensorCore and SparseCore to trade sparse, unpredictable memory accesses for dense, hardware-aligned ones. At the core of NTA, a compiler uses catalog statistics to assign guarded static capacities and a hardware-calibrated local cost model to select a TPU-native implementation for each relational operator before JIT compilation. We evaluate our system using the TPC-H benchmark. Taking full advantage of TPU slices and JAX distributed computing, we seamlessly scale our execution environment to run TPC-H benchmark up to Scale Factor 1000 (SF1000). Evaluated against a rigorous CPU ground truth (DuckDB), our native TPU accelerator achieves state-of-the-art performance, achieving a 7.0x single-device speedup over DuckDB at SF100 and a 68.6x speedup with 16 TPUs at SF1000 (1TB). The results establish TPUs not merely as dense neural compute hardware, but as a highly competitive, massively scalable substrate for the next generation of analytical query processing.
Causal discovery methods extended to handle missing data reliably
Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
Abstract: While causal discovery methods have matured for complete data, such algorithms for handling missing values remain limited. We establish general sufficient conditions under which causal graphs remain identifiable (i.e., uniquely determined from the available data distribution) under various missingness categories, including Missing Not At Random, and provide a framework to extend correctness guarantees from causal discovery algorithms for complete data to missing data settings. Our results show that identifiability of causal graphs with no unobserved confounders is preserved when (1) missingness mechanisms do not causally interact, (2) no variable directly causes its own missingness, and (3) either faithfulness holds for missingness mechanisms, or they follow generalized linear models. Guided by these theoretical results, we introduce two asymptotically correct algorithms for Additive Noise Models (ANMs) that recover the underlying causal graph and provide consistent parameter estimates.
Forecast-error entropy reveals hidden predictive links in complex time series
Beyond RMSE and Granger Gain: Multi-Horizon Forecast-Error Entropy for Nonlinear Predictive Coupling
Abstract: We investigate whether the past of an auxiliary time series provides predictive information about a target beyond that contained in the target's own history. We compare matched out-of-sample target-only and target-plus-source forecasts and introduce the forecast-error distribution entropy (FEDE) predictive-causality framework, where predictive causality is understood in the Granger sense: auxiliary history is informative when it improves prediction beyond the target's own past. FEDE quantifies how the full signed forecast-error distribution changes across prediction horizons. Controlled nonlinear benchmarks hide source-target dependence behind nonlinear transformations not supplied to the predictors. LightGBM recovers these hidden channels, whereas Ridge does not. Across four equal-power nonlinearities and four noise levels, the mean response-sensitivity statistic for FEDE remains 29.00, 27.47, 23.22, and 28.67, compared with 14.09, 10.68, 12.67, and 12.71 for mean log-RMSE gain. Directional and source controls separate the true source-to-target channel from the reverse direction and from independent periodic, quasiperiodic, chaotic, and autoregressive auxiliaries. Chronological Granger-style comparisons show strong model-form dependence: a degree-2 polynomial model is exceptionally sensitive to the matched quadratic channel but becomes weak or oppositely aligned for other nonlinearities, while basic convergent cross mapping is weak or directionally inconsistent in this stochastic, partly non-invertible setting. FEDE remains positively aligned across all 108 tested combinations of window length, history length, and maximum forecast horizon. Together, these results establish FEDE as a sensitive and robust horizon-resolved tool that extracts predictive information beyond conventional error-magnitude measures when the nonlinear interaction form is unknown. Code available in Zenodo.
Faster exact data deletion in federated fair clustering improves hospital and finance uses
Machine Unlearning for Federated Socially Fair k-Means Clustering
Abstract: Federated clustering can support applications such as patient stratification across hospitals and customer segmentation across distributed financial datasets. Responsible AI calls for fair representation of demographic groups and support for data deletion, motivated in part by rights such as the GDPR's right to erasure. These goals interact: deleting records can change the balance between groups and alter the clustering of the remaining population. We study exact machine unlearning for federated socially fair $k$-means, whose objective is to minimize the largest group-average squared distance to the nearest center. Our approach keeps separate local summaries for each group, so summaries at unaffected institutions remain valid as global fairness weights change. For two groups, we prove an initialization approximation guarantee independent of client group proportions under ideal sampling, and we show that same-seed replay reproduces retraining exactly. Reuse pays off most when a whole client withdraws: across three datasets, replay is $35.8\times$ faster than retraining for the initialization-only model and remains $2.4\times$ and $1.7\times$ faster with one and two fair-refinement rounds, which improve worst-group cost. For individual record deletions, gains are modest (about $1.06\times$), and certifying cached assignments can cost more than it saves. These results map where exact unlearning can profitably reuse computation. Code and reproducibility materials are available at https://github.com/arareddy/mufsc.
Learning linear systems with missing data through structured constraints
Learning structured linear dynamical systems from missing observations
Abstract: We consider the problem of learning structured linear dynamical systems over convex sets $\mathcal{K}$, where only a small subset of the observations are available at each time point. An estimator which minimizes a bias-corrected, potentially non-convex objective function is proposed. Non-asymptotic bounds are obtained for the statistical error, which depend on the local complexity of $\mathcal{K}$, the trajectory length $T$, and the sub-sampling probability $p$. Convergence of the projected gradient descent algorithm is also established. The general theory is applied to settings where (i) $\mathcal{K}$ is a subspace, (ii) $\mathcal{K}$ is the set of bi-isotonic matrices, and (iii) $\mathcal{K}$ is the set of matrices whose rows are formed by sampling Lipschitz functions. We show meaningful recovery of the transition matrix is possible for values of $T$ much smaller than what is required in the unconstrained case, and for $p = o(1)$.
Synchronization measures detect market patterns random-walk tests miss
Synchronization Reveals Market Structure That Classical Randomness Tests Cannot Detect
Abstract: Synchronization among coupled oscillators -- from firing neurons to flashing fireflies to power grids -- is a universal signature of collective behavior in complex systems, and is classically measured by the Kuramoto order parameter. Financial markets have been proposed as another such system, with price dynamics across trading timescales treated as coupled oscillators; prior work applying this measure, however, has been confined to a single asset class, and has never been checked against the discipline's own classical diagnostic for structure, the random-walk hypothesis. Here we show that a Kuramoto-style coherence measure, applied identically across five asset classes and 61 financial instruments -- cryptocurrency, foreign exchange, metals, equity indices, and single-name equities -- detects structure that a calibrated, heteroskedasticity-robust variance-ratio test of the random-walk hypothesis does not: the two diagnostics are statistically independent of one another even when computed from the same price history on the same time windows. The coherence measure tracks the directional cleanliness of recent price moves universally across all five asset classes, and offers a modest, asset-class-dependent forecast of future move magnitude -- strongest in continuously-traded, momentum-prone markets -- while the variance-ratio test finds the same panel statistically indistinguishable from a random walk in the large majority of cases. This independence indicates that a physics-derived synchronization diagnostic accesses a layer of structure that a discipline-native statistical test cannot, a methodological lesson we expect generalizes to other complex systems where tools imported from physics are compared against a field's own classical null-hypothesis tests.
System helps analysts explore data questions step by step
Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis
Abstract: Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language models (LLMs) can supply such knowledge, but their responses are unstructured, leaving analysts no way to see what has been explored, what is missing, or why one direction was chosen over another. We present DAG-EDA, a system that lets analysts and an LLM co-navigate the space of possible analyses through two linked structures. An intent graph, governed by a grammar of analytical intent, decomposes an ambiguous natural-language question into progressively concrete analysis tasks, keeping alternative framings open and letting analysts branch, backtrack, and compare paths. A multi-layered knowledge graph externalizes the LLM's domain knowledge, linking domain concepts to the dataset variables that can measure them, so analysts can inspect and contest how their question is grounded in the data. Both graphs are constructed from only the dataset and the analyst's question, and the analyses the analyst reaches are rendered as interactive dashboards. We illustrate the system through a usage scenario and describe a user study design for examining whether the system scaffold analysts' reasoning and navigation.
Comparison of metrics for summarizing long financial reports with transformers
A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
Abstract: There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single financial year. UK annual reports are very lengthy documents with around 80 pages on average. In this study, we aim to benchmark a variety of summarisation methods on a set of different pre-trained transformers with different extraction techniques. In addition, we considered multiple evaluation metrics in order to investigate their differing behaviour and applicability on a dataset from the Financial Narrative Summarisation (FNS 2020) shared task, which is composed of annual reports published by firms listed on the London Stock Exchange and their corresponding summaries. We hypothesise that some evaluation metrics do not reflect true summarisation ability and propose a novel BRUGEscore metric, as the harmonic mean of ROUGE-2 and BERTscore. Finally, we perform a statistical significance test on our results to verify whether they are statistically robust, alongside an adversarial analysis task with three different corruption methods.
New method improves anomaly detection in changing time-series data
MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection
Abstract: Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies can cause similar local changes, making it difficult to tell whether a deviation reflects abnormality or evolving context. Existing methods typically adapt to detected shifts or learn drift-insensitive representations, but do not resolve this ambiguity. We define this problem as \emph{temporal change disambiguation}: determining whether a local deviation is explained by broader temporal evolution. We introduce MORA, a drift-robust TSAD framework that reconstructs the same local target from paired short- and long-term views. The reconstruction gap measures contextual support for a local deviation, and a data-dependent correction mechanism conservatively adjusts the primary local anomaly score. Context can only reduce the score when it improves reconstruction of the same target. MORA needs neither drift annotations nor online adaptation. Experiments on four TSAD benchmarks show strong robustness to non-stationarity while preserving sensitivity to genuine anomalies.
Database agents use contracts to check and explain query results
No Trace, No Claim: Two Contracts for Database Agents
Abstract: LLM agents can generate database operations and explain their results, but current interfaces often leave a gap between generated plans, execution conditions, and claims presented to users. We argue that agent-facing data systems need two enforceable contracts. A plan contract defines what an agent may execute and reference; an evidence contract records the belief state, completeness, and provenance under which a result supports a claim. We instantiate these contracts in TGMS, a bi-temporal graph system in which an LLM plans over a fixed temporal operator interface. A static verifier checks plans before execution, and a claim verifier checks typed claims against content-addressed traces. Live model runs exposed two failures missed by input-only schemas and value-only grounding: nonexistent result fields and page-local counts reported as complete-result counts. Result-field checking makes the first a repairable rejection. Completeness propagation detects the second in all 15 controlled cases and misses all 15 when disabled. On the frozen CollegeMsg workload, TGMS reaches 0.408 typed-answer accuracy versus 0.064--0.284 for the evaluated baselines. On Bitcoin-OTC, direct SQL over the same bi-temporal store matches TGMS, showing no universal accuracy advantage for the fixed operator interface. On correction probes, TGMS and bi-temporal SQL answer historical-belief questions, while latest-state baselines cannot. Before claim gating, 21 of 220 answers contain an unsupported gated claim; after gating, none of 199 emitted answers does, at the cost of 21 fewer answers. The plan contract makes invalid plans rejectable and execution reproducible under recorded conditions, while the evidence contract makes gated claims faithful to cited evidence. Neither guarantees correct interpretation of user intent.
Taxonomy grounding improves AI repeatability in customer feedback analysis
Same Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback Analysis
Abstract: AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer appears plausible. We introduce a repeat-run evaluation framework that aligns semantically equivalent categories and focuses on two operating metrics: theme churn, the normalized change in the returned category set, and volume disagreement, the change in counts for categories that persist. We evaluate three recurring customer-feedback tasks across eight frontier models, corpus sizes from 100 to 5,000 records, multiple prompts, and three execution designs: raw generation, taxonomy-free hierarchical decomposition, and a taxonomy-grounded agent (TGA) using persistent themes, subthemes, and record-level predictions. With Claude Opus 4.8 and the 1,000-record corpus fixed, TGA reduces theme churn by 86--88% relative to both raw generation and hierarchical decomposition, while matched-theme volumes have zero disagreement. The taxonomy-grounded agent is more stable than every raw model in the screen, remains more stable at each corpus size, and keeps this advantage when theme matching is made stricter or looser. Although evaluated on customer feedback, the framework targets repeated synthesis of unstructured corpora more broadly, including financial reports, legal documents, incident records, and scientific literature. Overall, these results show that taxonomy grounding produces more consistent and repeatable outputs for recurring knowledge work.
StaFIR improves filtering of persistent time series while keeping data close to original
StaFIR: Convex Learning of Stationarity-Aware Causal Filters
Abstract: Reducing nonstationarity in a persistent time series entails deciding how much of its temporal dependence to remove. In finance, fractional differencing is often tuned using the Augmented Dickey--Fuller (ADF) test, limiting the search to a one-parameter family of lag profiles and addressing input preservation only indirectly. We propose StaFIR, a causal finite-impulse-response filter with a learned nonnegative mixture of exponential lag profiles. Its convex learning objective balances empirical stationarity with similarity to the input. We evaluate StaFIR on ARFIMA--GARCH controlled settings and rolling financial series, including a realized-volatility forecasting task. The experiments show that StaFIR adjusts its filtering strength to persistence while limiting unnecessary transformation in stationary regimes. In downstream forecasting, there is no clear accuracy difference from fixed half-order differencing, while StaFIR achieves higher measured similarity to the raw signal. A complementary direct forecasting experiment finds that greater input similarity is associated with smaller forecasting penalties, although the raw representation remains stronger.
Activation alignment cuts tabular model inference cost with less performance loss
Closing the Context Gap: Activation Alignment for Tabular In-Context Learning
Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that separate training from inference, these models must process all training examples in every forward pass, making each prediction expensive. Restricting the number of training examples reduces this cost but substantially degrades performance. Instead of discarding context, we propose activation alignment, a method that leverages the full context to teach a model how to behave when seeing only a subset. This is achieved by training a lightweight linear transformation on synthetic unlabeled data to map the intermediate activations of a data-constrained "student" (using partial context) toward those of a full-context "teacher" (using all data). Training the aligner requires no GPU and converges in seconds to minutes on commodity hardware. We evaluate on 38 classification datasets from the TabArena benchmark using the leading two tabular foundation models, TabPFN-3 and TabFM. Across all context budgets, the aligned student yields broad, statistically significant improvements over the unaligned baseline for both models. In low-data regimes, alignment recovers nearly half of the teacher's predictive advantage. The method provides a practical, low-overhead approach to achieving the inference speed of compact contexts while closing a significant fraction of the performance gap to the full-context teacher.
Neural networks uncover hidden frequency patterns in time series data
Inverse Cross-spectral Neural Networks for Multivariate Time Series
Abstract: CoVariance Neural Networks and their extensions have emerged as effective tools for processing multivariate data, deriving graph shift operators directly from second-order statistics. These architectures, however, are designed for independent and identically distributed observations and do not fully capture the joint structure of temporal and cross-variable dependencies in multivariate time series. In this work, we introduce Inverse Cross-Spectral Neural Networks (iCSNNs), a class of graph neural networks for stationary multivariate time series whose shift operators are the inverse cross-spectral density (iCSD) matrices. These operators encode frequency-specific conditional relationships among variables, exploiting the decomposition provided by the spectral representation theorem. Leveraging spectral smoothness, frequencies are grouped into bands sharing a single iCSD operator, yielding a compact parametrisation that retains the frequency-dependent structure of the process. We further propose a joint learning procedure to estimate both the Fourier-domain dependence structure and the iCSNN parameters, adapting the iCSD operators to the downstream task. When tested on synthetic data, iCSNN outperforms baselines from different methodological families.
Time series foundation models improved for anomaly detection
Normality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection
Abstract: Time Series Foundation Models (TSFMs) achieve strong generalization by learning to reconstruct or forecast broad temporal patterns from large-scale time series during pre-training. Yet this strength can become a weakness for anomaly detection: TSFMs may model rare anomalous patterns as effectively as normal ones, allowing anomalies to be accurately reconstructed or forecasted and thus diminishing their reconstruction/forecasting error-based anomaly scores. This paper proposes $\underline{\textbf{N}}$$\textbf{ormality}$ $\underline{\textbf{C}}$$\textbf{onstraint}$ $\underline{\textbf{L}}$$\textbf{earning}$ ($\textbf{NCL}$), a lightweight plug-and-play framework that adapts pre-trained TSFMs for accurate anomaly detection without modifying their pre-trained parameters. Our key insight is to constrain the broad pattern space of TSFMs to the normal structure of a target time series, preventing their broad modeling capability from obscuring abnormal deviations. Specifically, NCL constructs a compact normality subspace from a few normal patch features and adaptively steers each patch feature toward normality within this subspace, guided by contrastive constraints that form compact and discriminative normality manifolds. The calibrated features are aggregated to reinforce normal components and fused with the original TSFM output, amplifying the discrepancy between normal and abnormal observations for the reconstruction/forecasting error-based anomaly scoring. Extensive experiments across diverse TSFM families and benchmarks show that NCL consistently improves anomaly detection performance, providing a generalizable framework for adapting TSFMs to anomaly detection.
Adaptive classifiers can prevent drift detectors from spotting changes
The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors
Abstract: Monitoring concept drift from an adaptive classifier's error stream creates an operational conflict with the model's own update loop. When internal adaptation outpaces evidence accumulation, accuracy recovers before cumulative detectors (CUSUM, Page-Hinkley) can reach threshold. Instrumenting an Adaptive Random Forest (ARF) shows that surviving trees absorb 98.6% of the post-drift error transient through incremental leaf updates alone. The first background tree swap accounts for just 0.71% of this erased error volume, but drops external detection rates by 31 percentage points. We derive the finite-horizon boundary where cumulative evidence fails to cross threshold and measure a critical magnitude floor ($Δe_c = 0.120$) below which false-alarm budgets preclude detection. This failure manifests as missed shifts on stationary streams and false-alarm flooding triggered by internal tree swaps on noisy baselines. We validate on synthetic shifts, ARMA-GARCH series (ProteuS), and tabular benchmarks (BAF, INSECTS); on the synthetic sweep at a standard threshold, the blind spot appears at $Δe \approx 0.25$, showing why classical benchmarks like SEA ($Δe \le 0.21$) failed to reach it.
Visual bridge helps control time series data for better forecasting
Image Synthesis as an Intermediate for Controllable Time Series Generation
Abstract: Semantic-driven time-series generation offers a promising way to improve downstream learning in few-shot forecasting, but directly generating numerical sequences from language often fails to preserve the intended temporal structure. We propose VisualBridge, which uses time-series plots as a visual intermediate to bridge high-level temporal semantics and numerical sequences. An MLLM first converts plotted series into structured semantic representations, enabling explicit control over temporal properties such as trend, seasonality, and volatility. We then learn a semantic editing policy with downstream forecasting rewards, allowing the generation process to favor temporal patterns that are beneficial for the target task. The resulting sequences are further modeled by a temporal VAE to produce consistent multivariate augmentations. Experiments on standard public forecasting benchmarks demonstrate that VisualBridge improves few-shot forecasting over conventional augmentation methods, with ablations validating the roles of visual semantic grounding, learned semantic control, and VAE-based generation.
Time series models improved by correcting recurring prediction errors
GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory
Abstract: Time-series foundation models (TSFMs) enable zero-shot forecasting through large-scale cross-domain pretraining, while retrieval augmentation further improves their performance by leveraging historical information. However, existing methods typically correct TSFM forecasts using the ground-truth futures of similar historical windows, which contain both predictive components already captured by the foundation model and sample-specific random fluctuation that is difficult to transfer. In contrast, recurring systematic model bias within prediction errors more directly characterizes the failure modes of a frozen TSFM and therefore provides more valuable correction signals. Effectively exploiting such model bias, however, poses two challenges: prediction errors at different numerical levels are difficult to compare due to scale differences, and the recurring bias must be extracted from prediction errors contaminated by random fluctuation. To address these challenges, we propose GRAM, a general retrieval-augmented framework for frozen TSFMs. GRAM first introduces an Amplitude Memory Module (AMM) that scales prediction errors by amplitude and aggregates them into retrievable prototypes. It then employs a Prototype Graph Module (PGM) to model relations among prototypes to aggregate consistent bias information while suppressing random fluctuation. During online forecasting, GRAM retrieves and expands prototypes relevant to the current query and generates per-horizon corrections to refine the original TSFM forecast. Experiments across multiple datasets and foundation models demonstrate consistent forecasting improvements.
LineupRL improves time series captioning using verifiable reinforcement learning
LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification
Abstract: Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural language. Supervised fine-tuning (SFT) relies on a larger model's captions and cannot exceed their quality. Reinforcement learning (RL) can, but its rewards were designed for other modalities and other tasks, and they transfer poorly to open-ended generation in the time series domain. We address this by proposing LineupRL, a reinforcement learning with verifiable rewards (RLVR) pipeline whose reward is caption-to-series identification. The reward model is a frozen large language model (LLM) verifier that reads the generated caption and the candidate time series as raw values, never the chart, and must pick the described time series from multiple distractors. Matching is a far lighter demand on the verifier than writing questions or judging a caption, so an off-the-shelf LLM can supply the reward. Across two captioning benchmarks, and on forecasting and reconstruction where the predictor sees only the caption, LineupRL outperforms SFT and RL baselines on every metric. The 3B vision language model (VLM) trained by LineupRL also outperforms, at 1/24 of the parameters, the 72B VLM whose captions the SFT baseline is distilled from. Our case study shows that LineupRL resists reward hacking, and that the captioner it trains both traces the trend and names the values at key points.
LLM writes fast accurate interpretable anomaly detectors for time series
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
Abstract: Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping the best-scoring detector it finds. The loop discovers two compact detectors, one for univariate and one for multivariate series, that describe short windows by their local spectral features and compare them with the training-region distribution through a covariance-aware distance. On the TSB-AD benchmark these detectors lead the field across metrics, ahead of the strongest classical, deep, and foundation-model baselines including Time-RCD, yet they train no network and use no GPU, and the multivariate detector is faster than every similarly performing baseline. LLM-driven program search is thus a practical route to accurate, efficient, and transparent detectors.
Method reconstructs consistent company financial statements across years
Reclassified to Conform
Abstract: A company's financial statements over many years must be assembled from many filings. Each filing may rename, combine, split or move its lines, and restates only the last two or three years to match. Filings provide no consistent, machine-readable mapping between successive statements, and neither a line's label nor its XBRL tag is fixed. We treat the reconstruction as an optimization problem. A tag that keeps its numbers from one filing to the next is taken to be the same line, and such runs are joined into strands before any edit is weighed. At each boundary between filings, the candidate edits that pass the check their kind requires are listed, each with the strand endpoints it would explain and a price for how much it asks the reader to believe beyond what the filings show. An integer program picks the cheapest set of the listed edits that accounts for every line exactly once, and the chosen edits trace each line through the filings. The result is a statement whose rows follow one line across every year, comparable within each filing's restated window and marked where a number was restated or derived, in any filing's layout, with each number cited to the filing that stated it and each declared total re-checked. On 200 companies drawn at random, 99.9% of the totals that can be checked add up. Among the 124 with a usable vendor comparison, the lines the method follows agree with the vendor's series on 96% of the cells both fill, reach 10% more cells than a tag alone and agree with the vendor on 90% of those. The method also yields a record of what each company changed in its reporting.
Time series clustering method links clusters to actual waveforms
Seeing Time: Visual-Temporal Representation Learning for Interpretable Time Series Clustering
Abstract: Multivariate Time Series (MTS) clustering is an important tool in temporal data mining, aiming to discover latent group structures from complex observations without supervision. Although existing deep clustering methods can learn discriminative temporal representations, the resulting latent clusters are often difficult to relate back to waveform characteristics that practitioners can directly inspect and compare, limiting their ability to assess whether the discovered patterns reflect meaningful temporal behaviors. This paper, therefore, proposes WAVE (Waveform Aligned Visual-temporal Embedding), which treats time series and their deterministically rendered waveform plots as complementary views of the same observations. To produce discriminative representations whose cluster structures can be traced to observable waveform characteristics, WAVE aligns and integrates fine-grained temporal variations with holistic visual patterns, while associating each discovered cluster with its centroid-nearest authentic sample. Accordingly, interpretability in this work specifically refers to waveform-level traceability rather than a general explanation of model decisions. Extensive evaluations across 10 real-world public datasets show that WAVE achieves the highest macro-averaged clustering performance and the best average rank among the compared methods, while qualitative case studies illustrate how the discovered clusters can be inspected through authentic waveform records. The source code is available at https://github.com/Zheng-Zhu1/WAVE.
Time series generation improved with hyperspherical latents and masked modeling
HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling
Abstract: Most existing time series generators rely on a two-stage modeling paradigm: the first stage learns discrete latent representations of time series; the second stage performs autoregressive modeling on these discrete latents through next token prediction. However, this paradigm suffers from two stage-specific limitations: the first stage can lead to information loss when discretizing continuous time series, while the second stage is prone to error accumulation during autoregressive generation. To address these limitations, our core idea is to perform generative modeling in a continuous latent space with a more efficient autoregressive framework. We propose HALO, which enhances time series generation via Hyperspherical Latents and Masked Autoregressive modeling to achieve this goal by tackling two key bottlenecks: (1) variance and scale heterogeneity of continuous latent representations; (2) the difficulty of balancing generation efficiency with temporal correlation modeling. HALO first introduces a hyperspherical VAE that constrains continuous latents to a fixed-radius hyperspherical shell, effectively stabilizing the numerical fluctuations of continuous latent representations. Secondly, we develop a masked autoregressive model that balances parallel decoding and temporal correlation learning, substantially reducing the number of inference steps required for generation and improving generation stability. Our extensive experiments demonstrate that HALO achieves state-of-the-art generation performance while offering significantly improved inference efficiency over existing advanced baselines.
Timees improves forecasting accuracy and uncertainty modeling for changing time series
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
Abstract: Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, which limits their ability to accurately predict both the expected trajectory and its uncertainty in non-stationary time series. Motivated by Evolutionary Spectra (ES) theory, we propose TimeES, a general framework that enables probabilistic and deterministic forecasting via the evolutionary spectra theory. Specifically, we derive a parameterizable evolutionary spectra formulation, recasting non-stationary random process modeling as learning an evolving representation modulated by random variables. Furthermore, we reduce the complexity of the estimated spectra from O(NM) to O(NK), where K << M/2, by exploiting Hermitian symmetry and spectral energy sparsity for frequency selection. Based on a simple linear backbone, our proposed TimeES achieves consistent state-of-the-art performance across both deterministic and probabilistic forecasting tasks, with high efficiency and interpretability. Code is available at: https://github.com/wwy155/TimeES.
Online method detects changes faster and explains them clearly
High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability
Abstract: Change point detection (CPD) identifies abrupt and significant changes in sequential data, with applications in human activity recognition, financial markets, cybersecurity, manufacturing, and autonomous systems. Traditional CPD methods often face computational challenges in high-dimensional settings and typically provide limited explanations for detected changes, which can restrict their practical usability. This paper introduces a CPD framework that improves scalability and interpretability by leveraging the Sliced Wasserstein (SW) distance. Our contributions are fourfold: (1) we transform multivariate sequential data into one-dimensional scores using the SW distance, making the resulting representation compatible with existing CPD methods; (2) we analyze the distributional behavior of random slices of the SW distance and show that, under suitable assumptions, they can be approximated by a Gamma distribution, providing a principled basis for threshold calibration; (3) we propose a self-adapting online CPD algorithm that combines this SW-based score with an adaptive quantile-based threshold; (4) we introduce a model-specific framework for generating contrastive explanations for annotated change points. Empirically, our method reduces false positives by at least $48\%$ on average compared with popular online and offline CPD baselines, while maintaining competitive or superior detection performance. Code is available at https://github.com/jsve96/SWCPD_Code. At the same time, it produces interpretable change-point annotations, making it practical for deployment in high-stakes applications.
Latent flow time series generation aligned to spectral features
Time series generation with spectrally aligned latent flow matching
Abstract: Latent flow models have proven to be a reliable and cost-effective method for time series generation. However, the latent compression induces unwanted artefacts, such as a spectral mismatch with respect to the underlying dataset, thus hindering their use as training surrogates. In this article, we propose a spectrally-aligned latent-flow time series generator, where the latent space for flow matching is trained to preserve dynamical properties that are relevant for the suitability of synthetic samples. We find that incorporating fine-tuning losses based on canonical signal representations such as the Fourier, wavelet and signature transforms helps overcome these issues. The interpretability of these transformations allows us to ensure that the synthetic signals are aligned with the true ones in terms of relevant features, such as smoothness or targeted spectral content, as opposed to relying on pointwise reconstruction losses only. We compare the proposed aligned models against a base latent-flow model and the state of the art over real-world long-range univariate and multivariate benchmark datasets. Our quantitative results validate the superiority of the proposed method in terms of its performance on metrics reflecting signal realness and computational efficiency, while being aligned to the training set with respect to its local structure.
Cryptocurrency price trends reveal timing and central bank impact
Research on the Price Prediction Algorithms of Major Cryptocurrencies and a Basic Transaction Framework
Abstract: Through long-term observation and time series analysis of Bitcoin and Ethereum, we found the similarity in long-term consistent price trends, especially in the weekly K-line. We denoised and smoothed the historical data of their prices, and further derived the periodicity of their price change trends and the timing of buying and selling. We have for the first time proposed that the full application of central bank digital currencies (CBDC) is a key signal for investors to reduce their holdings of cryptocurrencies or even exit the market. In addition, we proposed momentum opening/closing prices to replace the traditional nominal opening/closing prices to accurately describe the price trends of the 24/7 financial trading market. We found that the cryptocurrency market can be regarded as a relatively independent financial market, thereby designing a safer and more efficient arbitrage strategy.
Online method improves warping parameter updates in gaussian processes
Online Gradient Computation for Warping Gaussian Process Transformations
Abstract: Warped Gaussian processes (GPs) handle non-Gaussian observations by mapping them into a latent standard GP via a parametric transformation called warping. Existing streaming variants, however, either optimize the warping parameters periodically or sacrifice analytical tractability for a higher model capacity. To bridge this gap, we show that the gradient of the instantaneous negative log-likelihood of a warped GP admits an exact recursive computation. Based on this result, we propose a novel online method for warped GPs that jointly updates the latent GP moments and optimizes the warping parameters.
Stream cruise control method improves online regression with adaptive drift detection
SCCM : Stream Cruise Control Method for Automated Drift Detection and Adaptation
Abstract: Real-world datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixed hyperparameters further limits model adaptability under changing conditions. Adaptive learning addresses this challenge by continuously updating models online, allowing them to incrementally adjust and remain effective as data distributions evolve. This paper presents the Stream Cruise Control Method (SCCM), a comprehensive framework for drift detection and adaptation in online regression. SCCM enables automated adaptation through early-response, pre-update drift detection, drift magnitude quantification, KPI-window-based thresholding for local false-alarm mitigation, dynamic hyperparameter tuning, and model recalibration. SCCM also adopts an in-memory design for real-time adaptability, unlike purely reactive methods that typically activate adaptation only after performance degradation is observed. By using dynamic thresholding and remaining agnostic to data distributions, SCCM supports KPI-based monitoring across varying data streams, including high-dimensional and large-scale settings. SCCM is integrated with four online regression models and evaluated on 18 synthetic datasets covering abrupt, incremental, and alternating gradual drift, together with eight real-world datasets. The evaluation uses both R2 and MSE and compares against eight detector--adaptation baselines. Results show improved predictive performance and effective drift handling across the evaluated online regression settings.
IGT system improves multilingual financial question answering accuracy
IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA
Abstract: We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four companies. Our central observation is that the 344 development questions divide into two families requiring fundamentally different approaches: structured numeric types (R&D ratio, cash flow, capital expenditure) are best answered by direct keyword extraction on filing text, while synthesis types (investment strategy, capital allocation, top-three revenue focuses) require rule-based multilingual news passage selection. A dataset analysis reveals that 17-18 of 19 ground-truth reference answers per synthesis type share an exact evidence label prefix, whose unigram tokens contribute directly to ROUGE-1 overlap. The final system achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline (approximately 0.247), and ranks 3rd of 12 teams on the official test set with ROUGE-1 = 0.3071, Precision = 0.2821, and Recall = 0.4044.