Papers

Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding session - a function is renamed, an endpoint moves, a dependency is bumped - RAG retrieves both the old and new value with near-identical similarity and cannot tell which is current, so it serves the superseded value. Paper 1 showed, on synthetic single-value benchmarks, that a deterministic (subject, relation, object) supersession memory eliminates this failure. Here we validate it end-to-end on real software history. From 707 real GitHub issues (SWE-bench Lite + Verified) we extract 130 clean atomic state transitions, a fix that changes one identifiable value from a pre-fix to a post-fix form, and render each marker-free (the stale and current statements differ only in the value). On this set, MemStrata reaches 0.91 answer accuracy versus RAG's 0.57-0.59; and, the structural result, when forced to answer RAG serves the superseded value 36-38% of the time (an LLM reranker does not help) while MemStrata drives this to ~0, at RAG retrieval latency (~2.1 s vs ~18 s for the reranker). We are explicit about scope: only ~18% of real fixes are clean atomic transitions; Paper 2 isolates the memory mechanism on that class, and extraction coverage of the remaining fixes is the orthogonal problem we defer to follow-on work. A real product bug surfaced and was fixed during the study (a case/punctuation-insensitive value comparison), with the moat property (deterministic-supersession accuracy on clean code mutations) preserved and verified.

We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not possess a vector space structure) and continuous/discrete action spaces. The setup covers many well-known applications in operations such as multi-product dynamic pricing with capacitated resources (Gallego and van Ryzin 1997). To model the exploration-exploitation tradeoff, we formulate an entropy-regularized continuous-time control problem with stochastic policies. Recent continuous-time RL techniques such as $q$-learning for controlled diffusions in (Jia and Zhou 2023) focus on continuous state spaces $\mathbb{R}^d$ and rely heavily on semimartingale theory in $\mathbb{R}^d$ for their theoretical analysis. Consequently, their methods cannot be directly applied to CTJMDPs with general discrete state spaces, which may lack the algebraic addition and subtraction structures inherent to Euclidean spaces. To bridge this gap, we establish the theoretical foundations of $q$-learning for CTJMDPs and develop model-free $q$-learning algorithms. Compared to naïve time discretization and approximating CTJMDPs using discrete-time MDPs, our approach has several conceptual and empirical benefits. Numerical experiments in network dynamic pricing (Gallego and van Ryzin 1997) show that our proposed RL algorithm reliably learns near-optimal policies and consistently outperforms standard benchmark methods, demonstrating superior solution quality and effective scalability to large-scale network instances.

In recent years, a white-box neural network called ReduNet has been proposed, which employs the maximal coding rate reduction (MCR$^2$) principle to transform raw data into low-dimensional discriminative features via a forward layer-wise construction process. Unlike traditional deep networks that rely on backpropagation, ReduNet explicitly derives the parameters of each layer from the features of its preceding layer, offering a mathematically interpretable paradigm. However, this layer-wise construction often requires a large number of layers for the MCR$^2$ objective to reach a stable value, which increases the parameter storage of the unfolded module. To address this issue, we propose LA-ReduNet, a lightweight adaptive architecture that refines the layer-wise update rule and enables discriminative feature representations to be obtained with substantially fewer unfolded layers. Specifically, LA-ReduNet employs hyperspherical manifold learning and adaptive step sizes, thereby reducing by an order of magnitude the number of layers required for the MCR$^2$ objective to reach a stable value. Simulation results demonstrate that, while maintaining comparable classification accuracy, LA-ReduNet requires significantly fewer layers for the MCR$^2$ objective to reach a stable value. Remarkably, under the considered experimental settings, LA-ReduNet requires only approximately $1/29$ of the parameter storage of the unfolded ReduNet module for the MCR$^2$ objective to reach a stable value.

Pseudo-label-based semi-supervised learning has achieved strong performance due to its simplicity and scalability. However, it is typically developed under a closed-world assumption that unlabeled data are drawn from the same distribution as labeled data. In practical deployment, unlabeled data are often collected from open environments and may contain OOD samples. Under such contamination, OOD samples may still receive high-confidence predictions and be incorporated into training as if they were valid target examples. This creates an important evaluation problem: clean in-distribution test accuracy may appear stable even when the internal learning dynamics of SSL have already deteriorated. To address this issue, we study hidden collapse in pseudo-label-based SSL under open-world unlabeled contamination from a diagnostic evaluation perspective. We present C-Score, a compact framework that evaluates training behavior in three complementary spaces: prediction, feature representation, and optimization. C-Score includes PLE and CCI for unlabeled prediction behavior, Sem-Drift for deviation from labeled semantic anchors, and Grad-Align for the compatibility between labeled and unlabeled optimization. Experiments on CIFAR-10 and CIFAR-100 with multiple OOD sources, varying contamination ratios, and four pseudo-label-based SSL algorithms show that C-Score metrics reveal hidden degradation that clean accuracy alone fails to detect: under SVHN contamination, CCI rises over 280% while best-accuracy remains within 3% of the uncontaminated baseline; near-OOD sources (CIFAR-100, STL-10) cause up to 14.9% accuracy collapse (FlexMatch, r=0.5). The results suggest that clean accuracy alone is insufficient for evaluating SSL robustness in open-world environments, and that internal diagnostic signals are necessary for more reliable robustness assessment under unlabeled contamination.

While Digital sky surveys provide excellent throughput of image data and can cover a large footprint, their imaging power is normally inferior to that of space-based telescopes. Space-based telescopes, on the other hand, provide excellent imaging power and can image the deep Universe, but cannot provide the same throughput as advanced ground-based sky surveys. Here, we utilize generative AI to elevate the quality of galaxy images taken by ground-based telescopes to the level of details enabled by space telescopes. The solution is based on the nature of galaxy shapes, allowing generative AI trained on space-based images to convert weak signal into detailed and clear galaxy images. The method allows for combining the high throughput of ground-based sky surveys with the image quality of space-based telescopes. The source code for the method is available, as well as paired training data and a catalog of 63,202 galaxy images enhanced by the proposed method. We also provide a software tool that encapsulates the entire pipeline and the custom generative AI model to generate galaxy images with enhanced quality.

Simulating a continuous-time quantum walk (CTQW) on a graph in the circuit model of quantum computing requires decomposing its Hamiltonian into terms that can be Trotterized into hardware-native gates. We consider two such decompositions: the standard Pauli decomposition and the recently introduced matching decomposition. Prior work suggests that the matching decomposition uses fewer CX gates on sparse graphs, while the Pauli decomposition uses fewer on denser graphs. Since CX gates dominate error and runtime on current hardware, we train machine learning models to predict, for a given graph, which of the two decompositions produces the smaller CX gate count. We train and evaluate on the complete population of all 11,117 connected eight-vertex graphs from Brendan McKay's database, so the class balance and overlap are measured directly rather than estimated. We use twelve features: ten topological properties of the graph and two that count the terms the Pauli and matching decompositions produce (n_Pauli and n_match), both computable without transpiling the simulation circuit. Standard topological properties alone provide little predictive power. Instead, the dominant signal comes from n_Pauli, a property of the Hamiltonian decomposition rather than an intrinsic property of the graph; degree variance is the only other feature that carries signal. Across a range of models the Matthews correlation coefficient (MCC) falls in a narrow band, from 0.569 untuned to 0.593 after tuning, so no single architecture stands out. We adopt a single-hidden-layer neural network at MCC 0.593. Applied frozen to a held-out, class-balanced test set of larger graphs (up to 256 vertices) from structured and Erdos-Renyi families, the model transfers, with MCC rising from 0.785 at N=8 to 1 at N>=64.

Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting benchmarks and models rarely exploit all three raw measurements reliably. Although speed and occupancy provide sensor-native traffic-state information beyond flow alone, existing releases often omit these variables, replace them with proxies, or contain logically inconsistent records. Moreover, direct empirical risk minimization over three-variable inputs may exploit regime-dependent shortcuts, as the relationships among flow, speed, and occupancy vary substantially between free-flow and congested states. We introduce PEMSB-3V, a public benchmark suite that preserves raw flow, speed, and occupancy measurements from PeMS detectors for flow prediction. We also propose RiskTraf, a model-agnostic risk-extrapolated residual plug-in. For each trained spatio-temporal backbone, RiskTraf freezes the selected checkpoint and learns a lightweight zero-start residual head from historical speed and occupancy. The residual head constructs ordered traffic-risk environments and optimizes horizon-wise flow corrections with a risk extrapolation objective, thereby mitigating regime-specific shortcut correlations without modifying the backbone. Extensive experiments demonstrate that RiskTraf consistently improves diverse forecasting backbones and outperforms debiasing and distribution-shift adaptation methods. Our code and benchmark are available at https://github.com/Guangyu4/RiskTraf.

Clustering methods have been used to identify distinct groups of milk samples, cows, or herds. Fourier-transform infrared (FTIR) spectroscopy, particularly mid-infrared (MIR) spectroscopy, has been applied to individual cow milk samples to predict various milk traits. Applying clustering directly to MIR spectral data may reveal latent groups of cows associated with milk traits or health disorders and can help prevent these conditions or monitor at-risk animals. This study aimed to identify groups of individual dairy cows in early lactation directly from milk MIR spectra and to analyze their associations with milk traits. Using a dataset of 407,632 individual milk MIR records from 3,408 commercial farms, we combined (i) spectral filtering that selects informative wavenumbers, (ii) two dimensionality-reduction methods: principal component analysis (PCA) and an autoencoder, and (iii) two clustering algorithms: k-means and spectral clustering to yield eight different clustering approaches. We regrouped the assigned clusters into meta-clusters that encompassed the most similar ones identified by the eight approaches. Our results revealed five distinct meta-clusters of early-lactation individual dairy cows significantly associated with milk traits. Despite substantial differences, the eight approaches converged on the same five meta-clusters, and the classic, computationally efficient PCA-based k-means approach using the full spectrum recaptured clusters identified by more sophisticated, computationally intensive approaches. The five meta-clusters were strongly associated with DIM and appeared to reflect a gradient of negative energy balance (NEB) severity: severe, moderate, and possibly mild, while the remaining two likely represented cows recovering from NEB, one with rapid restoration of energy balance and one in early recovery.

The edge-of-stability (EoS) phenomenon of full-batch Adam has been widely observed, yet its underlying dynamical mechanism remains poorly understood. In this paper, we identify Adam's second-moment adaptation as a negative-feedback mechanism that drives the dynamics toward the stability boundary. We characterize this mechanism through the *active curvature*, namely, the preconditioned curvature along the preconditioned gradient direction, and establish rigorous characterizations in progressively richer settings: rank-one quadratics with momentum, diagonal quadratics, on which the active curvature separates from the sharpness, and general objectives. Importantly, the mechanism predicts *gradient reversal* of full-batch Adam near the edge: consecutive gradients repeatedly point in nearly opposite directions, as we observe across fully connected networks, ResNets, ViTs, LSTMs, GPT-2 medium, and Adam-family optimizers. Consistent with this picture, averaging iterates suppresses these fast oscillations and produces smoother and lower loss curves. Together, these results provide an important first step towards fully understanding the dynamical behavior of Adam's EoS through active curvature and gradient reversal.

Many text classification decisions are viable based on constituent excerpts alone. Taking inspiration from the field of multiple instance learning, we present an algorithm for training a neural network to classify text by selecting such excerpts. We show that our approach is also scalable with demonstrated learning against samples with nearly 1M tokens. We evaluate our methods on 7 datasets with emphasis on long-textual collections that far exceed the encoding limit of our base model. We present state-of-the-art results with this algorithm on 3 datasets: identification of political bias in news outlets, trigger warnings in long stories, and demographic characteristics of authors in tweet collections. Furthermore, the model trained on weakly-labeled collections of text (bags) generalizes to accurately classify constituent, smaller instances. Besides a new state-of-the-art for these problems, this approach is one of the few neural methods to excel in these datasets.

Discrete diffusion models have demonstrated strong performance across a range of datasets, including natural language data and graph-structured data. Among many variants, score-entropy discrete diffusion (SEDD) has achieved particularly strong empirical results. In SEDD, new samples are generated by iteratively evaluating a sequence of concrete score functions, which are learned by minimizing a score-entropy loss. While much of the prior theoretical literature on discrete diffusion has focused on the sampling efficiency of SEDD under the assumption of small score estimation error, recent work has begun to investigate the finite-sample properties of score estimation itself. In this work, we take a different route by investigating the fundamental statistical limits of concrete score estimation. We focus on uniform and masking discrete diffusions, two of the most widely adopted discrete diffusion models. We establish a minimax lower bound under the score-entropy loss, and propose an MLE-based thresholding estimator that matches this lower bound up to constant and polylogarithmic factors that depend on neighboring density ratios. We further show that, for any target distribution, this density ratio is naturally controlled under both uniform and masking discrete diffusion models, yielding nearly matching minimax lower and upper bounds for the aggregated score estimation error. Our results imply that, with appropriate initialization and discretization, SEDD can achieve nearly optimal minimax sample complexity, as measured by the KL divergence between the target and generated distributions.

Understanding the features captured by the hidden layers of neural networks is a fundamental challenge in machine learning, despite their widespread success across various classification problems. In this work, we propose an algebraic framework for examining neural networks that model classification problems. Certain results, such as the correspondence between the neural network and neural ideals, algorithms for computing the neural ideals, and a stabilization theorem that enables approximation of the neural ideals, are first established. As an application to the framework, we present algorithms to identify and interpret the features captured by each hidden-layer neuron. Along with these theoretical developments, the practical performance has been demonstrated on the MNIST digit dataset, and the results highlight the pivotal role of neural ideals as a mathematical and computational tool for analyzing the features captured by neural networks. Further, we develop an interactive software that builds on the presented framework to visualize the features captured by each neuron. This tool is available at https://github.com/yvs1967/neural-network-representation-explorer

Closed-loop discovery systems increasingly execute experiments and update decisions autonomously, turning record integrity into part of the experimental apparatus. We show that false-science induction arises when legitimate physical objects and measurements are paired incorrectly, driving neural surrogates to faithfully learn record-induced associations that do not correspond to the true object-outcome relationship while marginal data distributions remain unchanged. Across green fluorescent protein fitness and materials band-gap prediction loops, coherent paired misbinding systematically redirects experimental budgets toward low-performing basins, whereas same-volume random swaps have negligible effects. These observations identify error coherence, rather than raw error frequency, as the primary variable controlling this budget misallocation in the tested loops. The resulting binding identifiability boundary supports monitored-axis quarantines and feedback-conflict triage, which intercept over-concentrated proposals before execution and isolate the corrupted hypothesis axis.

Extreme events (EEs) in chaotic dynamics are rare broad excursions whose forecastability can be altered by dynamical noise. We investigate how noise changes EE occurrence and prediction skill across forecast horizons in a third-order autonomous chaotic flow. A single clean-data threshold is frozen for all realizations, broad events are defined by one maximum per excursion, and a future window W=15 is predicted from a 15-time-unit history using HistGradientBoosting with chronological data separation. As the forecast gap G between the observed history and the future event window increases, the clean Matthews correlation coefficient (MCC) decreases from 0.641 at G=0 to 0.165 at G=15. Noise dependence is evaluated with ten paired realizations at eight amplitudes. The mean short-horizon score increases from 0.456 in clean data to 0.546 at sigma=0.007; the paired gain is 0.0895 (95% CI 0.0494-0.1295; Holm-adjusted p=0.0234). Noise strongly increases EE occurrence while event amplitude and width remain comparatively stable. Equalizing positive training counts across noise levels substantially attenuates the short-horizon gain, whereas strong noise reduces intermediate-horizon skill. We term this horizon-dependent, nonuniform change in forecast skill noise-induced predictability redistribution (NIPR).

A forecasting benchmark reports which method won. We show that the answer is set by the evaluator's choices before any model is fitted. We benchmark 24 forecasting methods and one textbook reference, including six 2025-era time series foundation models, on a production marketplace panel of 1,887 business customers over 67 months. We hold the data, the horizon and the period fixed, and vary only the evaluation design. Three choices each reverse or dissolve a headline conclusion. Changing the unit of analysis from the market total to the individual customer moves our production baseline from second of nineteen, beaten by nothing, to twenty-third of twenty-five. Nineteen of its twenty-four challengers beat it there. Changing how much error is pooled decides whether a Diebold-Mariano test finds anything at all. Scoring prediction intervals rather than point forecasts reorders the field almost completely, with a rank correlation of 0.02 on intermittent demand. We then measure what the deployed system gets from this. Its selection rule captures 55% of the distance between doing nothing and choosing with hindsight. The reversal is not a quirk of our data. We ran the released protocol, unchanged, on the public M5 retail panel. The same baseline shape places first at the market total and last per series, beaten by everything, and a replayed selection rule closes 64.7% of the same floor-to-ceiling distance there. Adding five zero-shot foundation models to that roster changes who wins at the total, not the shape. The bands' blind spot travels too: conformal bands under-cover most on the spikiest items. Splitting our own panel into ever smaller groups turns the contrast into a curve: the baseline's rank worsens at every level of disaggregation. We release the evaluation protocol and report an error of our own that inverted a result before we caught it.

Sharing a deep encoder does not, by itself, fix the central confound of task-comparison scores. We show that cross-evaluated heads on a frozen shared representation inherit the extrapolation confound of shallow exchange scores: pure input rotations with fixed labels inflate a deep exchange score from about 0 to 0.80, while representation-novelty scores are blind in the complementary direction (flat under label permutations that change the task completely). Transplanting a conditional two-discriminator discrepancy into the embedding space resolves both blind spots: the functional axis stays within +-0.001 under rotations and tracks label-permutation drift mass monotonically. Built into a mixture-of-heads lifecycle, the two-axis gate attains better decision quality with fewer heads than exchange or novelty triggers at a matched training budget. On generalized category discovery, the same chunk-level functional axis separates semantic novelty from photometric shift with AUROC 0.98-0.99 where per-input OOD scores (MSP, Energy, Mahalanobis, KNN) sit near chance for that distinction. All findings replicate across frozen ImageNet-21k ViT-B/16 and self-supervised DINOv2 backbones on CIFAR-100, and extend to residual adapter pools with recurrence, where a null-calibrated novelty trigger never fires on mechanism changes while the two-axis gate handles them with full recurrence reuse. We state explicitly the common-factoring condition under which embedding-space conclusions transfer to the original mechanism.

A pointwise-unbiased one-bit compressor reconstructs every real input in expectation while transmitting one bit. For a scalar source $P$ with CDF $F$, mean $m$, and $\mathcal J(P)=\int_{\mathbb R}\sqrt{F(r)(1-F(r))}\,dr$, we prove that the infimum of the source-averaged reconstruction second moment over all public-coin one-bit codes unbiased on $\mathbb R$ is $m^2+\mathcal J(P)^2$. For regular full-support sources, a distribution-centered random-threshold code attains this value; a converse over arbitrary randomized binary encoders and an equality analysis characterize every attaining code up to null sets, bit relabeling, and public-seed refinement. For the Gaussian location family $\mathcal N(\mu,\sigma^2)$ with $|\mu|\le c\sigma$, the equal prior on the endpoint means is least favorable and the minimax value is $\sigma^2\Lambda_c^2$. Exact Gaussian minimax optimality forces a critical heavy tail: at the endpoint means, absolute moments are finite exactly for $p<3$, and $\Pr(W>t)=\Theta(t^{-3}/\sqrt{\log t})$. A Cauchy-mixture robustification inflates the second moment by at most $1/(1-\eta)$ while making every positive-order absolute moment finite. Finite-support public randomness with finite decoder means cannot achieve exact unbiasedness on $\mathbb R$, but a bounded-output approximation using exactly $R$ shared random bits has explicit bias and second-moment bounds converging to the minimax constant. Finally, coordinate allocation communicates exactly $B$ bits per Gaussian-gradient query. On Kim's continuous quadratic hard family, the expected optimization guarantee matches the lower bound in its dependence on $(\sigma,d,B,\varepsilon)$, and a finite-variance high-probability bound incurs only a logarithmic confidence factor.

Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introduce ChronosAttack, a delay-only scheduling attack that changes when authentic tool responses arrive without modifying, adding, removing, or accelerating them. Bounded delays can change the order of the same evidence and alter the final decision. We evaluate ChronosAttack on GPT-5.6 Sol, Gemini 3.6 Flash, DeepSeek V4 Flash, and Claude Sonnet 4.6. GPT-5.6 Sol and Claude show strong targeted shifts in vulnerable settings, Gemini shows large shifts in the opposite direction, and DeepSeek is more stable under the tested schedules. We also find that sequential agent state is not always required and that a single scheduling inversion can cause a large decision change. Synchronization and order-consistency defenses reduce attacker control over observation order. These results show that tool-response timing can itself form an attack surface in asynchronous LLM agents.

Many computations admit several valid execution orders because independent subgoals or disjoint state updates can commute. Reinforcement learning with verifiable rewards usually treats each successful trace as a separate token sequence, so serialization choices can be mistaken for logical dependencies. We introduce Verifier-Certified Rule Transport (VCRT), which replays adjacent operation pairs with native verifiers. Pairs whose two orders are accepted and reach the same canonical state provide commutation certificates; rejected or state-changing reversals provide anti-diamonds. VCRT uses anti-diamonds to preserve genuine prerequisites and assigns policy credit to the total probability mass of each certified orbit. It also constrains post-swap consistency, source retention, and policy drift. We evaluate leave-one-environment-out transfer across ProofWriter, CLRS, and Lean through a shared anonymized relation-graph interface. All training and checkpoint decisions are frozen before held-out evaluation, which uses one greedy trajectory per item without search or verifier feedback. VCRT obtains a 77.60% macro pass rate versus 64.53% for the strongest matched baseline, a paired gain of 13.06 points (95% bootstrap CI [12.58, 13.54]). Lean accounts for most of this gain at 33.49 points, while ProofWriter and CLRS improve by 2.85 points on average. Mechanism tests consistently favor anti-diamond supervision, whereas No-Orbit is statistically indistinguishable from full VCRT. The evidence does not establish a general benefit from exact orbit aggregation.

Neural samplers are trained against an unnormalised target $\tilde\pi=e^{-E}$ with no samples from $\pi$, which leaves the practitioner with no way to tell whether an expensive training run has silently dropped part of the target. The diagnostics in common use are computed from the model's own draws and are therefore confined to the model's support: we exhibit a sampler whose self-normalised effective sample size is $0.99$ while it misses $87\%$ of the target mass. We argue that detecting missing mass is a strictly easier problem than sampling it: detection needs one point per missed basin plus a local curvature estimate, whereas correction needs the sampler retrained. We turn this into a pre-flight check that consumes a few percent of the sampler's own training budget and uses only $E$, $\nabla E$ and $\nabla^2 E$. On Gaussian-mixture, Many-Well and rotated anisotropic Many-Well targets with exactly computable ground truth, the check estimates the missing mass to within $10^{-3}$ at $2.7\%$ of training cost, where a tuned annealed SMC reference needs $70$–$280\%$ of training cost to do worse. It also applies unchanged to a controlled-SDE sampler that has no tractable density, where ESS and the ELBO cannot be formed at all. The estimator carries a self-diagnostic that, without ground truth, is conservative in the safe direction: across $60$ configurations it clears $16$, of which $15$ are accurate to $10^{-2}$ or better. We are explicit about what this does and does not license: the check cheaply produces evidence of missing mass, and sometimes evidence that the search has stabilised, but it cannot certify a run, and its thresholds are heuristic. We then map the boundary of the method on a real physical landscape, LJ-13, and report where it fails and why.

Fixed-budget robustness evaluation can select the wrong frozen vision encoder. An encoder that survives a shallow attack may lose most of that robustness when the same evaluation is strengthened. We ask whether the shallow evaluation contains enough information to identify this budget fragility. For each clean-correct sample, the evaluation records the clean pairwise margin, the first-order linearized margin-drop scale, the margin drop from a clean-start one-step attack, and the drop reached by an iterative attack. Normalizing by that scale gives three margin-drop coordinates capturing clean margin slack, one-step shortfall, and drift, where drift is the additional normalized margin drop the iterative attack reaches beyond the one-step perturbation. Together, they reconstruct the normalized post-attack margin and therefore the pass-or-fail outcome. Across 42 pretrained frozen vision encoders, the shallow survival rate carries essentially no rank information about subsequent PGD-10 to PGD-200 collapse, at Spearman -0.006, while the median shallow drift coordinate ranks the same collapse at +0.811. The result persists in a held-out encoder pool and under an $\ell_\infty$ evaluation. With deep evaluation limited to 11 encoders, ranking by shallow drift recovers 11 of the 17 high-collapse encoders, compared with 5 under survival-rate ranking. The full coordinate decomposition further distinguishes cases that share the same fixed-budget residual but diverge at deeper budgets, and separates margin repair from drift repair under interventions, revealing distinct repair paths that endpoint robustness alone does not identify.

Multi-station multivariate weather forecasting aims to forecast future weather variables at multiple weather stations from historical surface observations. Existing station forecasting models learn statistical dependencies among discrete stations, but lack explicit physical evolution. Meanwhile, PDE-based weather models provide interpretable physical dynamics, yet require continuous fields and upper-air variables unavailable in surface station data. To bridge this gap, we propose StationPDE, a station-oriented surface PDE learning model. StationPDE constructs a terrain-aware continuous surface field from discrete station observations and decomposes its physical evolution into surface wind transport and upper-air inference. Surface wind transport explicitly evolves observable weather variables, while upper-air inference uses learnable horizontal diffusion to approximate the missing influence of unavailable upper-air variables. A parallel data-driven diffusion branch captures complementary motion patterns, and an adaptive router integrates the two forecasts for station-level multivariate forecasting. Experiments on Weather2K and MeteoNet show that StationPDE consistently outperforms state-of-the-art baselines, reducing MSE by about $9.6\%$ on average compared with the strongest baseline.

Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selection. We stress-test this assumption for joint latency-energy feasibility across two public architecture families. On NAS-Bench-201, cross-device rank correlations are moderate, while target-comparable feasible-set overlap remains incomplete. A faithful AdaProxy diagnostic substantially improves latency ranking, showing that the observed boundary failures are not simply due to weak adaptation. Exact finite-sample split-conformal analysis also exposes an evidence bottleneck: a finite one-sided 90% threshold requires at least nine calibration observations. We then replicate the phenomenon on 10,000 GPT architectures across 13 HW-GPT-Bench devices. Relative to an RTX3080 proxy, target latency SRCC ranges from 0.951 to 0.996, yet proxy-reuse violation risk ranges from 33.3% to 100% under matched joint constraints. These results show that rank portability, feasibility portability, and target-specific decision support are distinct evaluation objects. Cross-device evaluations should therefore report which target environments actually support the operating point being claimed.

Passively collected mobile phone location data provide large-scale, longitudinal observations of human mobility but do not directly reveal activity purposes. The functional characteristics of visited locations offer useful contextual information, yet their relationship with activity purpose remains uncertain, particularly in mixed-use urban environments. We conceptualise activity pattern mining as an integrated process of representation, clustering, and interpretation, and propose the Activity Chain Encoder (ACE) for the representation stage. ACE is a self-supervised model that combines pre-trained urban embeddings with visit timing and duration and uses a Transformer to model the sequential organisation of stays. It is trained using masked activity modelling and identity-guided contrastive learning without requiring deterministic activity purpose labels. Learned daily representations are aggregated into user-level profiles, clustered, and interpreted through temporal-functional patterns and Census-derived demographic context. Applied to mobile phone app location data from London and compared with three representative methods, ACE supports the identification of six differentiated weekday activity-pattern groups characterised by distinct daily rhythms, urban functional contexts, and demographic associations. These complementary forms of evidence further support the development of empirically grounded activity-pattern personas, establishing a holistic route for deriving behaviourally meaningful population patterns from unlabelled mobile phone location data. The source code for the entire analytical pipeline developed in this study is publicly available at https://github.com/xlwang233/ACE.

Test-time self-evolving agents improve by reusing past experience, yet sparse-reward trajectories contain failures, loops, and detours, while summaries often omit the state conditions and action dependencies needed for execution. We study executable Walkthrough induction from sparse-reward trajectories: extracting compact, state-conditioned, and verifiable procedures. Our key observation is that delayed credit identifies actions associated with progress but cannot determine whether they produce facts required by later actions. We propose Trace, a credit-guided, dependency-grounded framework that compiles noisy trajectories into executable Walkthrough Memory. It detects progress anchors from rewards and persistent state changes, propagates credit to identify valuable transitions, and estimates action prerequisites from cross-episode success and failure evidence. Backward dependency slicing then traces required facts to their producers, extracting dependency-consistent action chains while removing irrelevant loops and detours. The resulting Walkthroughs encode entry conditions, ordered state–action–effect steps, and completion and failure predicates, supporting reuse, intermediate-state resumption, and programmatic verification. Experiments on J-TTL, WebShop, and ScienceWorld with three open-source LLMs show that Trace consistently outperforms eight test-time learning and memory baselines. Compared with the strongest baseline, it improves average AUC and Final-$3$ by $30.0%$ and $40.5%$, respectively, while using fewer inference tokens. These results show that long-horizon interaction benefits more from state-conditioned executable procedures than from complete trajectories or abstract summaries.

Evaluation awareness poses an unprecedented threat to model evaluation, but the mechanisms by which models detect it remain unknown. This study focuses on determining this and identifying contrasting mechanisms between smaller and larger models. While smaller models use the prompt's format sensitivity to detect evaluation, larger models often rely on higher-order reasoning to detect it. We evaluated Gemma 3 (1B, 4B, and 12B), Phi-3 (Mini and Medium), and Llama-3 8B using Chain-of-Thought analysis, representation probing, and Integrated Gradients attribution. Motivated by these findings, we propose a dual-pathway intervention that combines prompt sanitization with activation counter-steering to suppress both external evaluation triggers and their internal representations. Across 200 highly evaluation-aware prompts, our method achieves an average behavioral flip rate of 70.58%, consistently outperforming either intervention alone. These results provide new insights into how evaluation awareness develops in compact language models and suggest that effective mitigation requires jointly addressing both prompt-level and representation-level signals.Datasets and codebase can be found in this \href{https://github.com/chahal-navi/Evaluation-Awareness-Compact-LLMs/tree/main}{Github Repository.}

As the music industry becomes an increasingly collaborative effort, understanding the underlying structures of the artist network has become a focal point in cultural data analytics. This study expands on the previous analyses of the Italian and Danish networks by introducing a novel dataset of the Polish music scene. By utilizing methodologies used in the prior studies, this work enables a direct comparison between three distinct European music landscapes and allows to merged the created networks into one. Furthermore, this research introduces a framework to test the efficacy of Graph Neural Networks (GNNs) for artist popularity predictions based on the metadata and the position in the network. The statistical analysis revealed that the Polish and tri-national network exhibit similar properties and clustering behaviours, consistent with prior models. An evaluation of the predictive architectures reveals that while GNN models achieve a comparable F1-macro scores to the Multilayer Perceptron (MLP) in specific cases however the MLP remains a superior model regarding the success metric. The results suggest that internal node features - such as genre and label affiliation might carry more predictive capabilities than the topology of the network. The higher performance of the GNN models in the tri-national network might also suggests that the relational features become more informative when the network spans multiple linguistic and geographic boundaries, with the GNNs potentially capturing complex 'bridge' structures between the merged networks.

The study employed an Artificial Neural Network in combination with the optimized Adaptive Moment Estimation (Adam) algorithm, currently the only AQI forecasting model available in the Philippines. The modified QHAdamW - Quasi-Hyperbolic Momentum (QHAdam) and Adam with decoupled weight decay (AdamW) were both extensions of the Adam optimizer, and both offer unique advantages for training ANN. The proposed QHAdamW optimizer addresses the issues on convergence, generalization, and forecasting performance of Adam. Hyperparameter tuning results revealed that 0.01 and 0.001 were the most effective optimal values for the generalization performance of QHAdamW. The comparative analysis results using seven evaluation metrics revealed that the error value range is lower, and the regression coefficient, having a value approximately equal to 1, improved the model accuracy performance. Likewise, the model converges to a satisfactory level of performance with the convergence performance results of lower loss values as obtained from training and validation losses. Based on data from a real-time air quality tracking station in Manila, a feed-forward neural network is used to predict the AQI of PM2.5 and PM10 separately. This model can be used to forecast Particulate Matter (PM), to help the Department of Environment and Natural Resources-Environmental Monitoring Bureau (DENR-EMB) implement a comprehensive air quality management.

Due to the selection of their training data, large language models (LLMs) perform best on standard-language inputs from languages using the Latin alphabet with large speaker populations, while disadvantaging other language varieties. Nevertheless, they can also be a versatile tool for preserving precisely such endangered languages. But do they also possess the necessary creativity and capacity for abstraction to decode phonetically encoded language the same way humans do?

Multi-agent LLM systems split work across models, so answering often requires knowledge that sits in another agent's context: a Sharer has encoded information that a Receiver needs to complete its task. They usually communicate by exchanging text, which puts autoregressive decoding on the critical path and reduces the exchange to a discrete message written without sight of the receiver's state. Recent latent protocols instead translate the sharer's key-value (KV) cache into the receiver's: C2C supports heterogeneous models but requires both to read the same input, while LCF-X removes this shared-context requirement through position-free sharer-cache pooling. Three restrictions remain: LCF-X compresses the sharer alone, supplies the same layer-local summary to every receiver position with no joint cross-layer memory to retrieve from, and assumes matched layer count and KV geometry. We introduce XKV, which lifts all three: learned-query attention pools both caches; self-attention over receiver-aligned layer tokens, with a learned layer map reconciling different depths, mixes the pooled summaries into a compact joint memory; and a shared position decoder lets every raw receiver cache position retrieve its own per-head-gated residual in the receiver's native KV geometry. Both models stay frozen and may differ in family, depth, KV-head count, head dimension, and tokenizer; only the translator is trained. Across 45 dataset-model-pair settings (six heterogeneous and three same-model ordered pairings, five datasets), XKV attains the highest macro score and best average rank, improving on LCF-X on every dataset (by 4.6 exact-match and 4.2 F1 points on ROPES) and surpassing text communication on four of the five, while training 76% fewer parameters and translating a cache pair 10.3x faster (5.8 vs. 59.9 ms); end to end, XKV is 26% faster than LCF-X and 6.8x faster than text communication.