data science teams

Abstract: Causal foundation models (CFMs) pre-trained on data generated from various structural causal models (SCMs) have been proposed for estimating causal effects from observational data. However, differences in pre-training environments and evaluation protocols make it difficult to assess how their performance depends on the information available for causal identification. To enable controlled comparisons, we introduce CausalIDView, a multi-view benchmark that holds fixed SCM realization and target estimand while varying only the observational view available to the estimator. Each observational view corresponds to a distinct identification regime under the benchmark's maintained causal assumptions. Across these matched views, no CFM consistently performs best and model rankings vary substantially. Under controlled structural changes, CFMs exhibit model-specific failures to maintain stable estimates when true effects are unchanged and to track genuine effect changes. We also examine whether combining explicit identification with strong predictive estimation is effective. A modular approach that pairs a predictive tabular foundation model with regime-specific identification procedures is competitive with CFMs and outperforms several of them. These findings motivate cross-regime comparisons to assess the empirical value of CFMs.

Abstract: Background. Agentic AI systems independently decompose tasks such as literature search, data analysis, and programming into subtasks, search the web, access databases, and execute code. This allows them to perform digital research tasks at high speed. Objectives. Under what conditions does the use of agentic systems produce reliable efficiency gains, and which tasks remain with researchers? Materials and methods. Summary of current studies on literature searches, data analysis, software development, and clinical decision support. Results. For digital activities, work shifts from execution to steering and review. Efficiency gains are greatest when expected behavior can be formalized in advance and tested automatically. In complex agentic systems, recorded sequences of reasoning steps and tool calls can quickly become too extensive for human review. Furthermore, explanations generated by the model do not reliably reflect how an output was produced. One possible step toward more reliable systems is the validation of individual components. The limited reviewability extends beyond research itself; the review of scientific articles and grant proposals is also reaching capacity limits. In pathology, curated and annotated data, researchers' own analytical skills, and institutional exchange of experience are becoming increasingly important. Conclusions. Researchers remain responsible for their results. They must determine what to delegate and how to review the results. The importance of a research question to patients, the field, and society cannot be fully assessed using formalized criteria and remains a matter of expert judgment. Agentic systems can free up time for this.

Abstract: Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, sequences of observations generally provide only a partial view of the dynamics of the underlying system, with future observations being shaped by latent dynamics. Recent latent-space forecasting methods thus achieve improved performance by predicting future observations from latent-space representations of historical observations rather than directly forecasting future observations in the observation space. Next, while future observations are also shaped by external factors, how to incorporate external, often multimodal, information into forecasting, so that it can shape latent-state formation and evolution directly, remains underexplored. We propose WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance. Specifically, WorldTS employs a two-stage training strategy. First, it learns forecasting-relevant latent state dynamics conditioned on multimodal covariates, yielding encoded future states. Next, the learned state dynamics are frozen, and an observation decoder is trained to map the predicted future states back to future observations. Extensive experiments on 21 real-world datasets offer insight into WorldTS and its effectiveness.

Abstract: Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what the change is. A small perturbation of the parameters, retraining on new data, and a new architecture are different events, and each existing method is evaluated against the one it was built for. Reported robustness scores, therefore, answer different questions and cannot be compared. We propose a unified cross-family evaluation protocol that holds factual instances and generated counterfactuals fixed while testing every method against the same eight types of model change. The benchmark compares six robust methods and two standard baselines on four tabular datasets. It characterizes every changed classifier through its outputs and reports empirical robustness together with coverage, base validity, and proximity. We find that relative performance and failure modes vary across change families. Bounded parameter perturbations change 0.95\% of test predictions on average, compared with 4.9\% for bootstrap retraining. Methods with guarantees for these perturbations do not necessarily transfer to other changes. RobX transfers most consistently in our experiments, although greater stability can require larger interventions. We argue that robust CFE methods should be evaluated through a common protocol that specifies the model changes, measures their realized behavioral magnitude, and keeps generation performance separate from robustness.

Abstract: We consider the problem of learning the underlying causal directed acyclic graph (DAG) structure corresponding to a structural equation model (SEM) with non-Gaussian errors. Motivated by an intentionally misspecified non-Gaussian SEM with all Laplace errors, we first introduce the mean absolute residual risk, defined over the space of all real matrices, and show that, asymptotically, the risk of the true weighted causal DAG matrix is strictly smaller than that of any other matrix. Nevertheless, to enhance generality and account for high-dimensional and finite-sample settings, we further incorporate row-specific sparsity penalties along with a soft DAG constraint to derive a continuous score function over the space of real matrices. Accordingly, we propose a score-based DAG learning method, named MARCEDES, formulated as an unconstrained score minimization problem, which can be efficiently solved using gradient-based optimization techniques, thereby circumventing the challenges associated with constrained optimization. Furthermore, we develop a computational algorithm to handle the non-smoothness of the score objective and to enable optimal tuning of row-specific sparsity penalties under a generalized Bayes framework. Finally, we demonstrate the efficiency and improved performance of the proposed method over existing approaches through an extensive simulation study.

Abstract: Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate the demonstrated solution but to produce any output accepted by a verifier. This mismatch is seen in verifiable domains with multiple correct solutions, such as mathematical reasoning and code generation, where training data may contain only one expert solution per problem. We show that minimizing cross-entropy can be misaligned with minimizing verifier risk; two policies can assign identical likelihood to the observed demonstrations while placing different probability mass on incorrect outputs. This is formalized through a learning-theoretic counterexample in which CE minimization selects a suboptimal policy. We identify that controlling the support of the learned policy can solve this problem by preventing probability mass from spreading to unsupported outputs. Since support size is non-differentiable and computationally intractable, we propose entropy-regularized cross-entropy (ER-CE), using token-level Shannon entropy as a tractable proxy. Finally, across mathematical reasoning and code-generation benchmarks, we find that entropy-regularized training consistently improves verifier accuracy over standard cross-entropy. Our results identify a simple failure mode of imitation-based post-training in verifiable tasks and provide a practical objective that is better aligned with producing correct outputs.

Abstract: Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation design for TFMs as a problem in its own right: the representation should preserve local temporal transitions while maintaining a shared feature definition across samples. We propose SwitchPFN, which learns a shared projection and regime codebook from the training sequences, making local dynamic operators and transition features directly comparable across samples. Across the evaluated benchmarks, SwitchPFN achieves the highest mean accuracy among the evaluated methods, improving over the strongest baseline by 4.47% relatively. Ablation studies, parameter sensitivity analyses, and reduced-training-data experiments further examine the contributions of the representation, its main design choices, and its behavior when labeled data are limited.

Abstract: Fully continuous diffusion language models (dLMs) denoise continuous representations without intermediate discretization, then decode all response tokens in parallel at the final step. Their performance on challenging reasoning tasks remains less established than that of autoregressive (AR) LLMs and masked dLMs. We scale Embedded Language Flows (ELF) to mathematical reasoning and code generation on GSM8K, MATH-500, HumanEval, and MBPP. We introduce ELF-REG, which improves learning with representation alignment and entanglement (REPA+REG), where a frozen AR teacher supervises intermediate denoiser features and supplies a global representation that is jointly denoised with the response. ELF-REG-L achieves 55.96% pass@1 on GSM8K at 64 network function evaluations (NFE), and 13.39% on MATH-500 and 22.56% on HumanEval at 128 NFE. It outperforms the evaluated comparable-scale dLMs in pass@1 on GSM8K and code, and improves MATH-500 pass@1 from 10.55% for the ELF-L baseline to 13.39% with ELF-REG-L. Without few-step training, the same task-specific checkpoints support strong low-NFE performance through early-stop, which decodes an intermediate clean prediction without completing the denoising trajectory. At 16 NFE, ELF-REG-L reaches 41.21% HumanEval pass@10, outperforming recent continuous dLMs of comparable scale.

Abstract: What reusable computation should a tabular foundation model learn when every table defines a new supervised task? We develop in-situ representation refinement: support labels guide updates to the episode's representations, and these updates transfer to unlabeled queries without changing model parameters. A regularized leave-one-out objective yields a support correction and its query extension. The leading term separates attention-based reading from state-dependent scaling, motivating RefineICL: an attention-gated, FFN-free contextual stack with selected low-rank feature interaction and typed memory. RefineICL-L24 reaches 0.93836 OVR-AUC and 0.87173 accuracy on AMLB29. A benchmark-informed continuation reaches 1644.8 Elo on the 38-dataset TabArena snapshot, 31.4 Elo above TabPFN-3 under the same evaluation. It also improves all four reported metrics over TabPFN-v3 on both TabZilla views. In a matched 100K-update depth grid, an expanded FFN gives no consistent validation benefit and uses 60.2% more peak inference memory at L8. Internal interventions show that support representations are more than a static source of labels: removing one intermediate support update, while preserving the query output, increases final query cross-entropy in all 72 tested episodes. Together, the derivation and interventions explain how attention-gated updates can construct a task-specific predictor in context.

Abstract: We study prediction in new environments when training data contain rare, large shifts. Anchor regression penalizes the average of the squared mean residual across environments. It protects against shifts in an ellipsoid determined by the second moment of the training shifts. Covering rare shifts may therefore require a large penalty, expanding the ellipsoid in every direction and reducing accuracy on common environments. We propose CVaR anchor regression, which replaces the average of the squared mean residuals with a tail average. Unlike CVaR or GroupDRO applied directly to prediction risks, it does not give environments more weight solely because their noise levels are high. We prove an exact worst-case risk guarantee under a linear structural model that allows for heteroscedastic noise. For discrete environments, decreasing the CVaR tail fraction expands the robustness set from an ellipsoid to a scaled convex hull of the training shifts and their negatives. A separate parameter controls its scale. Examples show how the method can improve protection against rare shifts while retaining accuracy on common environments. We illustrate the method on New York City taxi data.

Abstract: Clustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters, such as the number of clusters or neighborhood size. Conversely, we propose automatic depth-based local center clustering (A-DLCC), a fully data-driven method that eliminates numerical parameter tuning. A-DLCC uses the $β$-integrated local depth to identify stable exemplars, points consistently central across multiple locality levels, termed local centers, which are ranked by their representativeness. Each local center induces a group of similar points, with group-level similarity measured by a proposed nonparametric metric called group-level local similarity. To guide merging, we incorporate the bottleneck path idea from graph theory, which forms the basis of our adaptive merging criterion. Based on this criterion, we design a single agglomeration rule in which a group is either absorbed by a neighbor it reaches better than itself or bonded to a neighbor that both sides find more reachable than their own background, every merge being additionally required to be carried by a contact stronger than a configuration-model null expects. The rule automatically estimates the number of clusters and decides when to stop merging. Experiments on synthetic and real data show that A-DLCC produces interpretable clustering results without parameter tuning.

Abstract: Sparse Gaussian processes achieve $O(N)$ inference by replacing the kernel with an appropriate expansion in a fixed basis $\{φ_j\}$ on the input space. Given a compute budget $M \ll N$, practitioners conventionally truncate the basis to its first $M$ entries. Nothing in the formalism, however, prevents one from selecting only those $M$ basis functions that matter for the data at hand. This would avoid spending budget on basis functions where there is no signal, but it requires a criterion for ranking the candidates. We propose three such criteria derived from an information-theoretic view of the basis-function selection problem. Each criterion matches a different state of knowledge at selection time: a no-data state, a no-prior state, and an in-between state. We then study the performance of truncation versus selection strategies on six UCI regression benchmarks across three basis families: Hilbert-space Gaussian processes (HSGP), variational Fourier features (VFF), and variational inducing spherical harmonics (VISH). We observe that the no-data criterion is a safe default, matching or improving on truncation for HSGP, VFF and VISH, with substantial gains for VISH and improvements over a recently developed selection heuristic for that basis family. The data-aware no-prior and in-between criteria provide substantial gains over truncation specifically for HSGP, which is the most broadly used of the three families in practice.

Abstract: AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natural next step is to improve the research efficiency of the agents themselves. When an AI research agent's own code is the object of optimization, each accepted rewrite becomes the agent that the next round edits. We refer to this loop as recursive self-improvement. Its significance lies in a long-standing trend, in which increased cumulative spending on R&D yields diminishing returns. Sustained self-improvement offers a way to counter this trend. We present AIDE^2, a system that implements this loop for a frontier AI research agent. It proposes changes to its own code, benchmarks modified versions of itself on a suite of AI R&D tasks, and keeps the changes that perform best on hidden evaluations. In an autonomous 8-day run, AIDE^2 discovered seven successive improvements, ranging from a new search policy to memory mechanisms that compress and manage the agent's growing context. These gains generalize to four held-out benchmarks spanning machine learning engineering, heuristic algorithm engineering, and physics-based weather forecasting, the last of which is out of distribution from the selection tasks. On all four, the strongest discovered agent matches or exceeds a human-engineered production research agent that ranks among the strongest on FML-Bench. On a separate held-out task family, the discovered agents also exhibit reduced reward hacking, a property the loop never explicitly optimized for: the rate falls from 55% to 32% during the run, 7 percentage points below the human-engineered agent. Together, these results show that an AI research agent can improve its own research efficiency through recursive self-improvement, and that these gains transfer to tasks and domains the loop never encountered.

Abstract: Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite this, learning from those abductive signals is largely ignored in artificial intelligence. While explainable AI (XAI) increasingly draws on causal models to generate explanations, the converse direction about what explanations can do for causality remains largely unexplored. To fill this gap, we propose xWhyL, a formal framework connecting causality and XAI by learning causal models from explanations. We develop a mathematical theory that translates explanations into a learning signal complementary to observational data, and demonstrate how it enables overcoming the limits of observational causal discovery. As explanations can be derived from incorrect beliefs and clash with data, a tension we call the Causal Tug-of-War, we prove conditions under which our framework rejects misspecified explanations rather than absorbing them. Our practical instantiation, Causal Interactive Learning (CIL), shows how expert explanations can efficiently support causal discovery and distinguish correct from incorrect explanations.

Abstract: A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal prediction in nonparametric uncertainty quantification, standard marginal validity offers limited resolution at the prediction values on which decisions are based, and fully conditional guarantees with respect to the covariates are provably unattainable. We address this gap by introducing a prediction-based conditioning framework that we refer to as Prediction-Interval-Conditional Prediction Intervals (PICPIs). Formally, a PICPI is an interval $I$ satisfying a self-consistency condition: $$\mathbb{E} [Y \mid p(X) \in I] \in I,$$ for predictive model $p$, contextual covariate $X$, and outcome $Y$. Thus, an interval simultaneously defines a stratum of prediction values and certifies that the mean outcome in that stratum lies in the same interval. This self-consistency condition yields data-adaptive strata without altering the original prediction. Such intervals can be constructed using practical algorithms. Under regularity of the prediction distribution, the constructed intervals cover all but an arbitrarily small fraction of prediction values and have widths that decrease at rate $n^{-1/3}$, up to logarithmic factors and the prediction error. Moreover, identifying these locally calibrated intervals can, in turn, inform downstream decision-making. We derive inference procedures for PICPIs in probabilistic prediction and multi-class classification, accompanied by theoretical guarantees. Empirical results are provided that compare PICPIs with existing interval-based baselines.

Abstract: Multivariate time series contain complex patterns that span across both space and time. While covariance-based statistical tools like spatiotemporal Principal Component Analysis (ST-PCA) help identify these patterns, they are limited to linear operations and prone to estimation errors with limited data. Recent covariance-based spatiotemporal neural networks offer more stable, non-linear alternatives, but they ignore correlations across different time steps. To solve this, we introduce the Kronecker coVariance Neural Network (KVNN), a temporal graph neural network that represents the spatiotemporal covariance matrix via a sum of Kronecker products where spatial and temporal dependencies are decoupled. By implementing filtering operations on spatial and temporal components, KVNNs achieve expressive processing capabilities, admit a rigorous spectral analysis, and are provably stable to finite-sample estimation errors, ultimately addressing all of ST-PCA's limitations. We show on five real-world datasets that KVNNs achieve strong forecasting performance, often requiring significantly fewer trainable parameters than competitive methods, and are consistent under estimation noise.

Abstract: Traditional evaluation metrics provides numerical values but often lack comprehensibility, hindering effective differentiation of model performances. Our work addresses this challenge by introducing overlay\_dx, a novel evaluation metric measuring the performance of time series prediction models. Overlay\_dx is a visual metric that represents the percentage of predictions falling within a confidence interval around actual values. Additionally, once evaluation results are plotted, overlay\_dx computes the area under the overlay curve, providing a quantitative measure of alignment between predicted and actual values across different thresholds and predictions. Through extensive experiments, we demonstrate that our approach offers a unified evaluation framework that combines both visual and numerical assessments, enabling improved model comparison and providing valuable insights for further research and optimization efforts in time series prediction.

Abstract: Principal Component Analysis (PCA) minimises aggregate reconstruction error, which can inadvertently represent majority subgroups with substantially higher fidelity than minority subgroups. Fairness-aware extensions of PCA correct this disparity but require group labels as input. We address the logically prior question: given only a data matrix, which binary partition of the data suffers the greatest representational disparity under a shared PCA projection? We formalise this as the max-disparity partition problem and propose a greedy local-search algorithm, grounded in the Fiduccia-Mattheyses bipartitioning framework, that discovers the disparity-maximising partition without any predefined group labels. Two benchmark algorithms, a fixed-projection sorting baseline and a simulated-annealing variant, confirm that the greedy solution is empirically near-optimal. Having identified the partition, we attribute the disparity to specific features via PCA loading scores and association rule mining, enabling a practitioner to assess whether the disadvantaged group corresponds to a human-meaningful minority. On the Predict Students' Dropout and Academic Success dataset, representational disparity is driven predominantly by institutional and programmatic proxies for socioeconomic disadvantage, with gender emerging as a secondary but consistent contributor within the disadvantaged group. The discovered partition is then passed directly to Fair PCA, completing a detect-explain-mitigate pipeline.

Abstract: Hierarchical data is ubiquitous in the empirical sciences and is most commonly analyzed with generalized linear mixed-effects models (GLMMs). Bayesian inference for GLMMs yields calibrated uncertainty but requires MCMC; the No-U-Turn Sampler (NUTS) is the gold standard but is slow and must restart from scratch for every new dataset, model and prior. We introduce metabeta, a pretrained neural network for prior-amortized in-context Bayesian inference over GLMMs. Unlike previous neural posterior estimators that fix the prior at training time, metabeta accepts prior families and hyperparameters as inputs at test time, enabling zero-shot generalization. Two set transformers and conditional normalizing flows mirror the posterior's two-level structure (global parameters shared across groups, local parameters per group). The model is trained on millions of realistic simulated datasets spanning continuous, binary, and count outcomes. By default, the flow posterior is refined by Independence Metropolis-Hastings against the unnormalized posterior, so its correctness rests on the sampler rather than the network; this yields tuning-free inference two to three orders of magnitude faster than NUTS. Alternatively, the flow can warm-start NUTS, giving nearly identical inference with substantially increased speed and stability. On controlled benchmarks with ground-truth parameters, metabeta matches NUTS in parameter recovery, calibration and out-of-sample prediction. On out-of-distribution real datasets, its posteriors closely match those of NUTS across all parameter types, and they remain faithful under misspecified likelihoods and priors, out-of-distribution predictors, collinear designs, and data-poor regimes. The model is open-source and open-weights and thus immediately deployable.

Abstract: Black-box machine learning models increasingly deliver strong predictions, but extracting useful information from them, such as a set of important features, remains challenging. Existing model-agnostic methods primarily estimate feature importance or conduct inference on it rather than directly selecting features, whereas many feature selection methods are model-specific or rely on the model-X assumption. We introduce LOCO-guided Adaptive Minipatch Sampling (LAMPS), a model-agnostic ensemble framework that uses any black-box regression algorithm as its base learner to select features important for predicting the response. The base learner need only produce predictions and need not perform feature selection itself. LAMPS operates within a minipatch ensemble framework that subsamples both observations and features, allowing leave-one-covariate-out (LOCO) feature importance scores to be easily computed. It adaptively concentrates minipatch sampling on features with high LOCO scores while maintaining exploration. The resulting sampling probabilities rapidly separate signal from noise features after a few iterations, enabling selection through simple thresholding. We establish that LAMPS achieves exact feature selection in high-dimensional settings, provided that the base predictive models are sufficiently well trained on average. Extensive experiments on synthetic and real data show that LAMPS outperforms state-of-the-art feature selection methods, with particularly strong performance in the presence of correlated features.

Abstract: Robust linear fits can resist response contamination yet remain too dense or unstable for useful global explanations. We propose penalized distillation, which fits a smoothly clipped absolute deviation (SCAD) estimator to a robust initial estimator's empirical fitted surface along a safeguarded coordinate-descent path and evaluates candidate states separately for fidelity, parsimony, perturbation stability, and held-out prediction. The new results attach to the states the algorithm actually computes. Conditional on a fixed uncontaminated design, deterministic bounds transfer response-replacement boundedness from the initial fit to every retained path state. Turning to fixed dimension, we characterize the oracle-support branch by its empirical-Gram projection and influence function, give conditions for covariance-weighted least-squares approximation equivalence, and establish a path-conditional generalized information criterion. By contrast, at large dimension-to-sample ratios the full-coordinate robust fit collapses without warning, and screening restores the construction. Under a sure-screening framework, the robustness bound and the support and selection guarantees transfer to the screened fit. Simulations separate robustness transfer from support recovery, efficiency, and computation across the dimension-to-sample ratio, with p up to 240, and the signal density, which isolates what the sparse stage adds once the screen over-selects. In a duplicate-grouped superconductivity study, the distilled estimator remains predictively stable under prespecified training-response shifts but retains 66.8--68.8 of 81 slopes. Stronger sparsification reduces the model to 12.6--14.0 slopes only at visible fidelity and prediction cost. Distillation therefore preserves predictive stability on these data without substantiating a compact coordinate-level explanation.

Abstract: Modern conditional generative models face significant challenges when learning complex covariate dependencies. While sufficient dimension reduction (SDR) provides a principled approach to compress these dependencies, traditional SDR frameworks were not formulated for conditional generation. To bridge this gap, we propose Belted Engression, a unified and architecturally parameter-efficient framework for generative distributional regression. Our approach establishes an end-to-end compress-then-generate paradigm driven by sufficient representation learning, embedding a structural bottleneck into the generative architecture. Theoretically, we prove that the standard SDR condition is equivalent to a law-preserving generative factorization, which is achieved at the global optimum of the population Belted Engression objective. Furthermore, by uncovering a localized Bernstein-type control for the energy-score loss, we establish finite-sample convergence rates that are sharper than those of existing results. We also prove that this belted architecture is strictly smaller, operating with an asymptotically vanishing parameter count relative to the unstructured baseline. Extensive simulations and real-world applications demonstrate that Belted Engression achieves superior distributional prediction and SDR recovery with fewer trainable parameters.

Abstract: Reproducibility is essential for scientific progress, enabling validation, fair comparison, and building upon prior work. In computational network science (CNS), however, reproducibility remains limited due to missing code, inaccessible datasets, and insufficient reporting of experimental details. This paper presents a taxonomy of reproducibility in CNS, structured around artifact availability, algorithmic clarity, experimental environments, and data processing and experimental pipelines. To systematically examine these challenges, we conduct four case studies spanning diverse methodological settings: topic-based influential user detection (network science and natural language processing-based methods), influence-based community detection (pure network-based methods), influence maximization (classical, heuristic, approximation, and AI-based mixed approaches), and reinforcement learning for network analysis (learning-based methods). Across these domains, we observe a consistent lack of publicly available artifacts, particularly code and datasets, hindering verification and comparison of results. We identify key causes of this reproducibility gap, including limited incentives for sharing artifacts, data access restrictions, incomplete experimental descriptions, and a complex methodological pipeline. Finally, we outline recommendations to improve reproducibility, including mandatory artifact sharing policies, standardized benchmarks, and comprehensive reporting of experimental setups. Addressing these gaps is critical to ensure transparency, comparability, and sustained progress in computational network science.

Abstract: We introduce an iterative framework that automates the extraction of interpretable, schema-bound categorical features from unstructured text for tabular prediction models. To navigate the feature space, a generator LLM proposes semantic definitions, a separate extractor LLM materializes the features, and a downstream tabular model evaluates their predictive performance. We optimize this search by translating explicit model errors, such as AUC ranking inversions, into natural-language feedback, steering the LLM to resolve specific predictive failures. Evaluated across three public datasets, this error-driven loop accelerates feature discovery by up to $3\times$ compared to unguided search. Empirically, the generated features demonstrate strong multi-view complementarity, strictly outperforming any subset when combined with TF-IDF and dense embeddings. Finally, the framework guarantees instance-level interpretability: the discovered features dominate SHAP importance rankings and provide a fully transparent, semantic audit trail for every prediction.

Abstract: Computational notebooks make problem-solving visible, but typically only one notebook at a time. Meanwhile, in data science platforms like Kaggle, one competition can accumulate hundreds of notebooks. Effective collection-level analysis requires characterizing recurring solution patterns across all notebooks, as well as isolating specific notebooks for closer examination and learning. However, standard notebooks provide no common basis for this. Their workflows are nonlinear, cells declare no intent, and identical code can serve different ends, leaving hundreds of notebooks as separate documents. In this paper, we present Notrix, an interactive visual analytics tool for profiling hundreds of notebooks as one collection. Inspired by a formative study (N = 11), Notrix classifies every cell into one of thirteen machine learning (ML) stages, turning each notebook into a stage sequence, and clusters those sequences by structure rather than by code. To keep the representation constant as the scope narrows from the whole collection to a single cell, Notrix features three coordinated views---Workflow, Structural Matrix, and Detail---that appear at all four levels of granularity. In a within-subject study (N = 17) using two Kaggle collections of over 400 notebooks each, we observed participants answered questions about all notebooks more accurately with Notrix (median 88% vs. 50%) while opening 80% fewer notebooks per minute. Notably, four of the fourteen answered it without opening a single notebook (interaction logs, N = 14). Participants also reported significantly lower mental demand, temporal demand, and stress with Notrix (Holm-Bonferroni adjusted).

Abstract: Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment.

Abstract: In a computational notebook, a human can point to a rendered result and ask about "this," while an agent acts through cells, dependencies, and runtime state. When what the human sees and what the agent operates on are disconnected, the human must describe what they mean and trace what the agent did in prose that strips away situated visual and computational context. We present marimo-lens, an extension to the reactive Python notebook marimo for grounded human-agent analysis. Lens connects a human's marked output and note to its producing cell and relevant contributing computation, giving the agent computational context for the request. It surfaces agent activity, returns selected results to the notebook, and preserves the initiating selection for human review and reopening. We illustrate the lifecycle through an exploratory human-agent analysis of a real-world open dataset, showing how visually situated questions lead to computational inspection, notebook action, and returned evidence for human review.

Abstract: Retrieval-Augmented Generation (RAG) is increasingly used to ground large language model (LLM) outputs in scientific literature. However, in open-ended literature exploration, the evidence context used for generation is often produced through hidden retrieval, reranking, assessment, and filtering steps. Users may receive retrieval summaries without knowing how the system constructed the evidence context, which evidence units were retained or discarded, or whether potentially useful evidence was excluded before synthesis. We present FootprintRAG, an LLM-agent-powered visual analytics system for evidence context refinement in RAG-based scientific literature exploration. The core idea is to treat the RAG evidence context as an explicit, inspectable, and revisable analytical object before generation. FootprintRAG parses scientific literature into text and figure evidence units, expands an initial query into parallel query variants, retrieves and assesses evidence across iterative rounds, and surfaces ERS-ranked supplementary candidates from the corpus-level evidence space. Through coordinated views, the system connects retrieval trajectories, evidence-state revision, and provenance-aware summary generation into a user-steerable workflow. We evaluate FootprintRAG through two case studies, a user study, and a workflow-level comparison with representative RAG systems. The results show that FootprintRAG helps users compare retrieval directions, revise candidate evidence, recover potentially overlooked evidence, and trace generated summaries back to supporting evidence units. FootprintRAG is available at https://github.com/meteorshowering/FootprintRAGVA.git.

Abstract: Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving too many features, while probabilistic relaxations have remained largely limited to categorical classification. We present a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and continuous regression. By mapping instances to the Boolean hypercube, our linear explanations strictly generalize subset-based approaches: they capture both the magnitude and direction of feature contributions while enforcing a prescribed sparsity budget $k$. We show that minimizing the relevance error for such explanations is \ClassNPPP-hard when the underlying model is a neural network, and we relate this intractable objective to a tractable surrogate---the fidelity error. For a parameterized family of local distributions, the relevance error of any $k$-sparse explanation is bounded by its fidelity error up to a multiplicative factor that remains small locally. We address the resulting empirical problem using two complementary approaches: a Mixed Integer Programming (MIP) formulation that yields provably optimal empirical solutions while maintaining polynomial sample complexity, and a polynomial-time Iterative Hard Thresholding (IHT) algorithm with provable approximation guarantees. Empirical evaluations show that, unlike state-of-the-art baselines such as LIME and MAPLE, our explanations satisfy both the anchoring and sparsity constraints by construction, while consistently achieving lower relevance error.

Abstract: Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outputs. Responses may appear reasonable while hallucinating the required object: numerical sequences can violate shape, scale, channel order, or temporal alignment, and textual decisions can fall outside the legal label space. We formulate reliable time-series language modeling, separating task-object reliability from predictive quality. We introduce ExecTS-QA, a contract-grounded benchmark spanning forecasting, imputation, classification, anomaly detection, and waveform analysis. We further propose WaveTLM, a unified compiler-executor model whose task compiler transforms user requests, visible arguments, and wave-grounded evidence into typed task states, while task-native executors construct numerical tensors, legal decisions, or structured records. On ExecTS-QA, a single WaveTLM checkpoint achieves 99.40% contract-valid coverage, compared with 37.83% for the strongest evaluated string-first baseline, while retaining balanced predictive performance across all five task families. Evaluations on SciTS, TSQA, IRTS-ToolBench, and ARFBench provide additional evidence of transfer. The code, construction scripts, and ExecTS-QA dataset will be publicly released upon publication. These results show that task compilation can convert plausible language generation into reliable time-series outputs.

Abstract: Model explainability is essential for understanding and trusting machine learning models. Existing explainable AI methods often explain predictions through feature importance, counterfactual explanations, or rules. However, a region-level characterization of when and only when a prediction behavior arises remains less explored. This paper proposes Causal Sufficient and Necessary Regional Explanations (SNRE), a framework that learns an input region $A$ and output region $B$ such that membership in $A$ is both sufficient and necessary for the model output to fall in $B$. Motivated by the classical Probability of Necessity and Sufficiency (PNS), we formulate a region-level PNS measure through stochastic interventions and derive a differentiable finite-sample estimator for optimization. SNRE parameterizes the input-output region pair with explicit and interpretable algebraic region families, together with a learnable feature mask, balancing expressiveness and interpretability. Experiments demonstrate that SNRE learns region pairs with strong sufficiency-necessity performance, robust explanation behavior, and practical utility for model analysis.

Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by recalling APIs from memory and writing code, an approach that hides what a library offers, delays errors until runtime, and loses experimental state between turns. We present TuiML, a self-contained machine-learning library built for AI agents, with native algorithms across supervised, unsupervised, time-series, data handling, tuning, and evaluation tasks. Every component describes itself through machine-readable metadata and parameter schemas, so an agent can search the library, inspect components, compose validated workflows, and register new ones that become discoverable in turn. Every call is validated, seeded, and traced, and sessions export as runnable notebooks, making experiments reproducible by construction. One specification layer drives the Model Context Protocol (MCP), agent-framework adapters, a Python API, a CLI, and local model serving, while data and models never leave the machine. Benchmarks show TuiML remains predictively competitive with scikit-learn and Weka. While looking like a conventional library to a human user, TuiML is designed for agents first, allowing them to read, extend, and operate machine learning autonomously. TuiML is open source, with documentation at https://tuiml.ai.

Abstract: We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines across a broad range of tabular problems. TabPFN-3.5 sets a new state of the art on standard tabular prediction in TabArena, and extends it to the data practitioners encounter in practice: non-i.i.d. data with temporal or grouped splits, tables with strings, text and images, high-cardinality categorical features, and wide tables with many features. These gains carry over to our task-specific harnesses: state of the art on relational data and stronger time-series forecasting. For faster inference, our variant TabPFN-3.5-Fast runs up to 3x faster than TabPFN-3 while keeping most of the accuracy gains. In addition, we upgrade TabPFN-3.5-Plus, expanding our multimodal capabilities with advanced text and date handling alongside proprietary inference optimizations. Finally, we release a new version of our Thinking mode, TabPFN-3.5-Thinking, which scales inference-time computation to push the state of the art further. It benefits from our stronger base model and from inference-time improvements that make it up to 12x faster than TabPFN-3-Thinking.

Abstract: The manifold hypothesis suggests a natural criterion for clustering: partition data according to the manifold component from which each point is drawn. Whether two components are separable depends on a geometric tradeoff: the ambient separation between components versus the largest gap in sampling. In practice, this tradeoff is rarely assessed explicitly, leading standard methods to over-commit to a single clustering assignment even when the data do not support a unique answer. We formalize this tradeoff by combining intrinsic manifold geometry (volume growth and reach) with sample-level quantities (fill distance and density), yielding a threshold phenomenon for mutual-$k$-nearest-neighbor graphs: when the offset-to-fill ratio exceeds a conservative upper threshold, component separation is preserved; below a lower threshold, components fuse. The gap between these thresholds defines a geometric uncertainty zone in which the number of clusters is not identifiable from the data. Nevertheless, conventional approaches still seek one: sweeping parameters (an engineering approach) or fitting a generative mixture model (a model-based approach). Rather than forcing a single estimate of the number of clusters, we propose Manifold-Based Clustering (MBC), which returns an explicit bracket interval to quantify the underlying data uncertainty. This bracket acts as an empirically calibrated diagnostic: it narrows when a single resolution is supported, widens when multiple resolutions coexist, and collapses to one when no separated structure is detectable. Empirically, we find that many real datasets lie within the uncertainty zone rather than admitting one clear answer. Our results suggest that ambiguity in cluster number is often intrinsic, and should be quantified rather than resolved.

Abstract: We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io

Abstract: We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.

Abstract: Multi-target regression requires a model to simultaneously predict several related outputs. Conformal prediction provides distribution-free, finite-sample marginal coverage guarantees, but extending these to joint multi-dimensional regions in a model-agnostic, sample-efficient manner remains challenging: max-aggregation ignores scale differences, copula-based methods are only asymptotically valid, rectangular methods typically split the calibration set, and quantile or density-based methods require training a specialised model beyond a plain point predictor. We propose the scaling-score conformal method, which is model-agnostic (requires only component-wise absolute residuals), uses a single calibration set, and yields four nested output types: an outer rectangle (SCO) with valid joint coverage, the exact set R $α$ , a staircase (SC 2 ) over approximation of R $α$ , and an inner rectangle (SCI). A single hyperparameter $γ$ $\in$ (0, 1) controls the base-rectangle quantile level independently of $α$. We prove downward-closedness and a rectangular sandwich bound and derive a closed-form outer rectangle. Experiments on 29 realworld datasets confirm valid joint coverage; SC 2 with $γ$ = 1-$α$ consistently achieves competitive volume relative to baselines, with the advantage growing with output dimension d.

Abstract: Weighted majority votes are central to many successful ensemble methods. PAC-Bayesian theory provides tight generalization guarantees for such models by analyzing the expected risk of stochastic classifiers, while analyzing the risk of deterministic majority votes relies on surrogate bounds. To avoid these surrogates, Zantedeschi et al. ( 2021) introduced guarantees for stochastic majority votes, but the resulting models remain randomized. In this paper, we propose a derandomization framework for stochastic majority votes. To do so, we apply recent advances in disintegrated PAC-Bayesian theory directly to the space of majority vote weight vectors, transforming stochastic guarantees into certificates for a single deterministic majority vote. We derive two families of high-probability generalization bounds, covering both data-independent and data-dependent constructions of the ensemble, which naturally lead to a self-bounding learning algorithm optimizing deterministic majority vote guarantees.

Abstract: Classification and regression trees are typically constructed using a greedy splitting rule that maximizes the immediate reduction in prediction error at each node. Although this strategy is computationally efficient, it can miss splits that yield small short-term gains but create substantial downstream improvements after further partitioning. We propose a look-ahead tree-building method that evaluates each candidate split by the prediction error reduction achieved after growing a conventional CART subtree below that split. Because the full look-ahead procedure can be computationally expensive, we also describe a smart look-ahead algorithm that learns downstream split values using node-level features. The proposed framework preserves the interpretability of recursive partitioning while improving split selection in hierarchical or interaction-driven settings. We conduct a simulation study comparing conventional, full look-ahead, and smart look-ahead methods under several settings and apply the proposed methods to analyze two real data examples demonstrating the merit of the new methods.

Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-world temporal dynamics. Existing multimodal benchmarks also suffer from limited data and context coverage, fragmented evaluation settings, and overreliance on aggregate evaluation. In this paper, we propose \textbf{MUSE-Bench}, a unified benchmark for multimodal time series forecasting with heterogeneous context. It comprises fourteen datasets across eight domains and six types of context: metadata, events, holidays, news, images, and numerical covariates. We evaluate diverse forecasting paradigms, including statistical, data-specific, foundation, multimodal, and general-purpose LLM forecasting methods under shared non-overlapping forecast windows, common target observations, and consistent point and probabilistic metrics. Extensive experiments yield three main findings. First, numerical time series foundation models dominate the overall ranking, while Aurora, the evaluated multimodal foundation model, trails the leading numerical TSFMs but outperforms all evaluated data-specific models. Second, ablations show that external context improves the four evaluated context-aware models, whereas incorrect or temporally misaligned context degrades performance. Third, general-purpose LLMs perform poorly as direct forecasters, and LLM-guided refinement does not yield consistent improvements. MUSE-Bench enables systematic evaluation of how forecasting models utilize context and provides a foundation for future multimodal forecasting research.

Abstract: Predicting under an acquisition budget requires choosing feature groups whose value can depend on later queries. O-MPAC transfers finite-horizon risk-cost targets from complete training records into a shared source-action scorer. At inference time, the scorer uses partial observations and source metadata, re-scores after each query, and applies a hard cost mask. We analyze how tied teacher targets and the remaining planning horizon affect the learned decisions. Uniform supervision over tied minima preserves the target distribution under source relabeling. In a five-seed routing experiment, it achieves 0.965 accuracy under both original and context-last orders. On six real tasks, validation selects H1 without action cross-entropy in all thirty splits. O-MPAC has the highest mean budget-integrated accuracy on five tasks against source-adapted GDFS, DIME, AACO+NN and a static policy.

Abstract: Variable importance scores from tree-based methods such as random forests favor continuous predictors over categorical ones. We present a theoretical analysis of this bias and propose a simple remedy: add a small amount of noise to each categorical predictor. The correction is demonstrated on a variety of simulated and real-world datasets and combined with integrated path stability selection to perform variable selection with false discovery control for mixed data.

Abstract: Frontier LLMs are increasingly capable of conducting automated research, yet their creativity in this setting has not been systematically evaluated. In this paper, we propose a set of metrics to evaluate creativity along the two dimensions of valueness and novelty. Valueness assesses whether each proposed idea is useful, while novelty is evaluated from three perspectives: whether the same idea has appeared before (Exact-Match P-Novelty), whether a previously unexplored variable or variable combination is explored (Variable-level P-Novelty), and whether the idea directly follows retrieved external knowledge or departs from it (H-Novelty). Our evaluation shows that the models achieve relatively similar scores on most creativity metrics, but differ substantially in Variable-level P-Novelty, which reflects the breadth of research-space exploration. Further correlation and idea-level performance analyses show that Variable-level P-Novelty is the creativity dimension most strongly associated with research performance.

Abstract: When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e., the probability that $Y=1$) exactly matches the forecasted probability $f(X)$. In practice, models inevitably exhibit calibration error, and it is therefore important to be able to measure this miscalibration to assess a model's reliability. The Expected Calibration Error (ECE) is the most widely used measure of miscalibration, but is known to be impossible to estimate the ECE with guaranteed accuracy in an assumption-free setting. In this work, we propose an alternative measure, the rankECE, that is based on comparing points with neighboring values of the predicted probability $f(X)$. Our theoretical guarantees and empirical results establish that rankECE provides a better proxy for ECE as compared to binned approximations to ECE, which are the most commonly-used approximations in practice.

Abstract: In practice, various learning scenarios provide access to auxiliary features exclusively during training. Incorporating such data to enhance model performance gave rise to a paradigm known as Learning Using Privileged Information (LUPI). While this extra information is intended to improve the resulting model, establishing a generalized, cohesive understanding of how privileged information (PI) transfers useful knowledge remains a challenge. Vapnik's original theory and subsequent works offer performance guarantees in certain cases, but these results are inherently per-algorithm and rely on setting-specific proof approaches. Consequently, a more general framework explaining how and when PI transfers useful knowledge is still missing. To bridge this gap, we introduce an algorithm-agnostic, information-theoretic approach based on the PAC-Bayes framework. Rather than asking whether a particular algorithm exploits PI, we ask how much value it could offer: comparing the tightest achievable risk bound with and without PI yields its potential - an upper limit on the extractable gain. We introduce a metric that quantifies this potential directly from empirical training risk, bypassing the need for test-time data access, and validate our findings in both supervised and unsupervised settings. The results demonstrate a robust correspondence between our training-time metric and true test-time performance gains. Ultimately, this work takes a necessary step toward an information-theoretic understanding of LUPI, and quantifying the potential of privileged features before committing to a model.

Abstract: Even with a fixed dataset and research question, data analysis involves many defensible decisions. Understanding how these choices influence the results is scientifically important but remains challenging. Crowdsourcing and agentic AI can generate hundreds of end-to-end analyses, but scaling generation alone can create a processing bottleneck and an analytic ``black hole.'' A common workaround is to impose a shared fixed decision taxonomy, which can limit insight and understate uncertainty. We present ForkSCOPE, a human-AI collaboration framework that induces structure bottom-up from the code corpus of end-to-end analyses, without a taxonomy fixed before or after generation, so the organization and evaluation of the garden can scale with the corpus. ForkSCOPE surfaces the charted garden of forking paths through a human-AI collaboration pipeline and an evidence-linked interactive viewer for steering and verification: it spotlights organically identified forks and structures and produces a derived taxonomy and decision map compatible with existing multiverse tools.

Abstract: We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the generalized accelerated sketch-and-project solver (GAS), thereby mitigating the computational bottleneck of classical second-order methods. The GAS solver improves upon vanilla, unaccelerated sketch-and-project solvers by achieving accelerated convergence through Nesterov momentum updates, and accommodates a flexible projection metric whose proper choice further reduces computational cost. Building on this design, we establish asymptotic normality of the averaged sketched Newton iterates and characterize their limiting covariance matrix. The resulting covariance recovers that of the unaccelerated sketched Newton method under a specific choice of acceleration parameters, converges more rapidly (in the number of sketching steps) to the minimax-optimal covariance in general, and is smaller than that of the last iterate produced by the accelerated method. Finally, we strengthen these results by establishing a functional central limit theorem for the Newton iterates, which allows us to bypass explicit covariance estimation and develop an online inference procedure based on random scaling. Specifically, we construct a pivotal test statistic by appropriately rescaling the averaged iterates, so that its limiting distribution is free of any unknown parameters, enabling asymptotically valid online inference. Numerical experiments demonstrate superior performance of the proposed inference procedure.

Abstract: Latent embeddings have become a central data abstraction in modern machine learning, especially in biomedicine, where foundation models are increasingly used to encode multimodal data like clinical text, medical images, omics, and physiological signals. However, the utility and value of these representations depends on understanding their quality, structure, and the information they encode. Existing analysis workflows for evaluating representations remain fragmented across custom scripts, isolated metrics, and most importantly lack multimodal analysis, limiting accessibility and reproducibility. We present LatentVerse, a representation analysis resource that combines a web-based visual analytics platform for accessible, report-driven exploration with a command-line interface for scalable technical workflows. LatentVerse unifies diagnostics for various representation quality metrics and extends to multimodal settings by decomposing embeddings into shared and modality-specific components. We evaluate LatentVerse through controlled unimodal and multimodal simulations, discovery-oriented analyses on real biomedical embeddings, and a user study across diverse use cases. By supporting thorough and interpretable evaluation of latent spaces, LatentVerse makes foundation model representations more understandable in biomedical and data science applications.

Abstract: Scientific workflows increasingly use repeated queries, multiple models, and interacting agents. Reliability therefore depends on whether models preserve correct conclusions, accept valid corrections, and contribute errors that a selector can distinguish. Using SycoBench- 600 as a controlled measurement substrate, we evaluate these requirements through selective updating, defined by resistance to misleading suggestions and uptake of correct suggestions. The study covers ten models and 17,055 trajectories. Published models span 13.4 to 71.6 percentage points in selectivity. Under identical local evaluation, Qwen3-4B is selectively adaptive at 45.6 points, Gemma3-4B is destabilized at minus 14.1 points, and SmolLM3-3B follows both correct and wrong explicit suggestions, producing zero selectivity. Matched interventions identify model specific responses to doubt, authority, and explicit advice. Among seven published models, the best reaches 95.3 percent accuracy, plurality reaches 88.6 percent, and the oracle ceiling is 99.8 percent. Mean error correlation of 0.285 reduces seven models to an effective independent count of 2.58. A leave-one-stem-family-out reliability selector reaches 96.2 percent, recovering 67.7 percent of the plurality-to-oracle gap. These results establish selective updating, error diversity, and calibrated adjudication as jointly measurable design targets for multi-model scientific workflows.

Abstract: Reproducibility is essential to scientific progress, yet the growing volume and complexity of scientific publications make exhaustive manual verification increasingly impractical. Although recent advances in large language model (LLM) agents enable automated experiment reproduction, existing evaluations largely focus on final repositories and are typically limited to machine learning (ML). We introduce AgentActionBench, a process-oriented benchmark for evaluating agent-based experiment reproduction across ML and AI4Science domains. Our framework uses an MCP-based Action Recorder to capture agents' behaviour throughout the reproduction process and evaluates the resulting traces with paper-specific rubrics. AgentActionBench contains 150 papers, including 120 ML papers and 30 AI4Science papers. A human-annotated subset covering 10% of the benchmark provides validation data, while model-assisted augmentation expands the full benchmark to more than 10,000 rubric items. Experimental results show that current systems remain limited, with execution as the primary bottleneck. Meanwhile, the strong Pearson and Spearman correlations between model-generated and human-annotated rubrics validate the reliability of our scalable rubric-generation approach.

Abstract: Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes a wide variety of supervised learning such as positive-unlabeled (PU) learning, noisy label learning, and similarity-based learning. Existing UU learning assumes that the test and training distributions have the same class-conditional densities. However, this assumption rarely holds in practice due to distribution shifts. This paper proposes a distribution shift adaptation method for UU learning that uses UU data in the training distribution and a few UU data in the test distribution. The proposed method is based on the importance weighting, which minimizes the test risk by using training data with estimated importance weights. Although existing importance weighting methods cannot handle UU data, we show that it can be done in a principled manner. Thanks to the generality of UU learning, our method can handle various learning problems such as PU and noisy label learning under distribution shift within a single framework while existing methods are usually tailored to a specific problem. Moreover, it does not require any assumption of the shift types such as covariate shift. We experimentally demonstrate the effectiveness of the proposed method with real-world datasets.

Abstract: We develop an exact almost-sure learning theory for smooth parametric models trained by regularly weighted empirical risk minimization on long-range dependent data. The training observations are generated from a fixed finite window of a stationary Gaussian sequence, and the sample weights are regularly varying. If the loss gradient at the population minimizer has Wiener-chaos rank $m$ and a nonzero low-frequency coefficient, then, in the long-memory interior regime, the finite-lag score reduces on the iterated-logarithm scale to a single weighted Hermite chaos. This yields an almost-sure Bahadur representation, an exact limsup law for the learned parameter, and, for $m\ge2$, the functional cluster set of the complete learning trajectory. The polynomial learning exponent is determined by the memory parameter and the chaos rank and is invariant under the admissible power weighting, whereas the sharp pathwise constant and cluster geometry depend on the weights. In the rank-one case, global optimization over the admissible power exponents shows that every optimizer is positive. Time-series prediction and classification examples illustrate the results.

Abstract: Feature transformation improves predictive performance on tabular data by constructing informative abstractions from raw features. Recent generative approaches encode transformation knowledge into continuous embedding spaces for efficient exploration of candidate strategies, but face three key limitations: (1) overlooking hierarchical relationships between low-level features, operations, and high-level abstractions; (2) enforcing order-sensitive embeddings on inherently permutation-invariant transformation sequences, thereby introducing systematic bias; and (3) relying on gradient-based search, which is ill-suited to non-convex transformation spaces. We propose a framework with two complementary components. First, a permutation-invariant hierarchical module captures interactions across features, operations, and abstraction levels, with a self-attention pooling mechanism that maps semantically equivalent structures to consistent embeddings aligned with downstream performance. Second, a policy-guided multi-objective reinforcement learning strategy initializes the search from empirically strong seeds and jointly optimizes predictive accuracy and transformation efficiency. Extensive experiments on diverse tabular benchmarks demonstrate the effectiveness and robustness of our framework against strong baselines. Our code and data are publicly available at: https://github.com/RayLiu1103/PHER.

Abstract: Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions. Search generally helps, but all four diagnostic models perform worse than an exact-count exponentially weighted moving average (EWMA) baseline in compositional accuracy. We identify two linked bottlenecks. Under cumulative-history access, State carry-forward outperforms direct Forecast for all four diagnostic models; frozen-evidence replay links a shared component of this reversal to Forecast-oriented policies retrieving a smaller share of recent evidence. Even with exact historical activity, future-specific updating remains limited, with only GPT-5.5 plus reopened Search slightly surpassing EWMA. Fine-tuning on realised outcomes improves Qwen3-4B's forecast Spearman correlation by 0.105 on held-out fields at later origins, with gains also on change-rich episodes.

Abstract: Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing benchmarks primarily emphasize structural evolution via temporal link prediction (TLP), while support for semantic evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture realistic semantic drift. Moreover, commonly used datasets exhibit high link repetition, leading to inflated performance estimates and obscuring true model capability. To address these limitations, we introduce \textbf{TTGBench}, a new benchmark that jointly evaluates structural and semantic evolution. TTGBench comprises six real-world, text-rich datasets characterized by \emph{Dual Volatility}, enabling rigorous and fair evaluation of existing models. Notably, it is the first benchmark to support both multi-class and multi-label TNC, filling a critical gap in evaluating temporal semantic drift. We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms. The results reveal a clear \emph{capability divide} between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictors show the opposite trend. Through in-depth analysis, we uncover their fundamental limitations and provide insights for developing more comprehensive temporal graph models.

Abstract: This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a research question through experimental design, code implementation, actual execution, result analysis, and report delivery. Qiushi Engine is model-configurable; this evaluation selected DeepSeek deepseek-v4pro-preview as the model backend. The official AstaBench leaderboard records a score of 0.816 and an average benchmark cost of USD 15.209 per task, while the full-precision local recomputation is $81.59 \pm 1.87$. Four tasks satisfied every rubric item, yielding a full-task completion rate of 4/40 = 10% -- 7 percentage points above, and about 3.3 times, the approximately 3% best rate reported for AstaBench's official agents. Across 507 required rubric items, 416 were satisfied (82.1%). Official scoring archives and 40 Meta-Trace records show sustained production and verification of reports, code, and experimental artifacts; the principal gaps lie in repeated runs, external dependencies, specified metrics, and ablation studies. The report explains the benchmark, system workflow, aggregate results, representative cases, and limits of interpretation.

Abstract: We characterize the sharp structure-agnostic minimax risk for coefficient estimation in the partial linear model when the outcome and treatment nuisances are learned by two distinct black-box learners, which resolves the open problem in double machine learning posed by Gu (2025). For each nuisance \(q\in\{μ,π\}\), we characterize the available learner by an approximation-error budget \(a_q\) and a stochastic-error budget \(s_q\), with the latter controlled through localized Rademacher complexity. Writing \(\mathcal E_n\) for the minimax mean-squared error, we show that \[\mathcal E_n\asymp1\wedge\left\{\frac1n+\left(a_μa_π+\min\left\{a_πs_μ+s_π^2,\,a_μs_π+s_μ^2\right\}\right)^2\right\}.\] The main new ingredient is a novel lower bound for the general two-learner problem. Our proof constructs four finite-mixture testing experiments using orthogonal code functions. Across these experiments, the hidden perturbations are placed outside both learner classes, outside only the treatment learner class, outside only the outcome learner class, or inside both learner classes. These four configurations capture, respectively, the interaction between the two approximation errors, the two asymmetric interactions between one learner's approximation error and the other learner's learning error, and the joint estimation difficulty of learning both nuisances. Combining the four resulting lower bounds yields the displayed rate, which matches the latest upper bound in Gu (2026). Our result shows that standard double machine learning can overstate the intrinsic difficulty of target estimation and provides a target-specific principle for learner selection: approximation error and stochastic complexity must be jointly balanced across the two nuisance learners rather than optimized separately.

Abstract: Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. However, current graph modeling methods rely on traditional Graph Neural Networks and pre-training approaches to implicitly learn the underlying relational structure of graph data. Thus, these prior methods cannot capture the complex graph structure and correlations among inputs. In this paper, we introduce a novel Attention-based Normalizing Flow-based Approach\footnote{Our implementation and models will be released publicly for research reproducibility.} (ANFA or $α$) that provides an explicit, interpretable, and tractable Graph Modeling ($α$-Graph). In particular, we propose a new Unconditional Graph Normalizing Flow with an Invertible Attention Mechanism to capture the complex relational structure of graph data. To further enhance the expressiveness of the model, we introduce Conditional Graph Normalizing Flow with Learnable Queries that enables efficient modeling of correlations in graph-structured data. We show that our Conditional Graph Normalizing Flows behave similarly to Unconditional Graph Normalizing Flows, enhancing expressiveness while maintaining training stability and efficiency. Our experimental results on three benchmarks will illustrate the effectiveness and the state-of-the-art (SoTA) performance of the proposed $α$-Graph method.

Abstract: Counterfactual explanations formalize "what-if" scenarios by identifying modifications to an input instance that obtain a desired alternative prediction. Traditionally, whether generated via instance-specific optimization or amortized single pass models, these approaches rely on a single, deterministic point-estimate predictor. However, this ignores predictive uncertainty and hypothesis variability, leading to brittle explanations that frequently become invalid if the underlying model is retrained or updated. To address this fragility, we propose the Amortized Variational Counterfactual Generator (AVCG), a generalized optimization framework that formulates counterfactual generation as optimization over an arbitrary distribution of plausible predictive hypotheses rather than a single deterministic predictor. This formulation naturally accommodates Bayesian posteriors, Rashomon-restricted hypothesis spaces, and other uncertainty representations within a unified optimization framework. Evaluation across multiple benchmark datasets demonstrates that the AVCG framework produces counterfactual explanations that remain highly valid under predictive uncertainty and model changes, while maintaining competitive plausibility and single-pass runtime performance.

Abstract: Time series data is very common in many real-world applications and in numerous domains, with increasing interest for automated information extraction using machine learning. One of these subfields is time series clustering, which consists in identifying clusters among a set of time series in an unsupervised fashion. Most time series clustering algorithms suffer from the same balancing act: they trade clustering performance for faster runtimes or vice versa. We present a novel time series clustering algorithm that we call CLUES-WEASEL, which stands for CLustering with the UnsupervisEd Second version of Word ExtrAction for time SEries cLassification. CLUES-WEASEL extracts features using the unsupervised version of the transformation step of WEASEL 2.0, which is a time series classification algorithm, then reduces these features using principal component analysis, and finally performs clustering with the $k$-means algorithm using these reduced extracted features. Through extensive experiments, we prove that CLUES-WEASEL is significantly better than any other existing time series clustering algorithm while being (much) faster than any state-of-the-art one. We also show that the architecture of CLUES-WEASEL can work well with other time series feature extraction algorithms. Our findings highlight the relevance of CLUES-WEASEL for time series clustering.