Machine Learning
Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning
Liu Hung Ming
Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaining what the policy learned. We study whether independently trained policies can be represented and composed through auditable discrete behavioral rules. We define auditability as six separately testable predicates: trace integrity, lossless coding, rule coverage, behavioral agreement, composition quality, and value-model reliability. Our protocol uses a shared frozen symbolizer, passive rule extraction, an append-only hash-bound ledger, exact environment replay, and offline confidence-ranked arbitration with an explicit blind-spot fallback. The results place strict limits on this description layer. Rule-set overlap does not imply behavioral agreement: policies may share symbolic rules while choosing near-chance-matching actions on fresh states. The fused policy therefore selects among existing rules rather than generating a new skill. On a conflict-dominated task, an apparent fusion failure is traced to an induction/deployment mismatch: rules induced from sampled actions were evaluated under argmax actions, and deployment-consistent re-induction reverses the arbitration ordering. A fitted-Q generalized-policy-improvement diagnostic also fails in both environments, limiting claims that rule fusion is superior to value-based composition. One exploratory comparison favors rule fusion, but its comparator is post hoc, the task is partly saturated, and the fused policy remains below the strongest held-out actor. We contribute an evidence-bounded audit and composition protocol, not a claim of universal interpretability or autonomous skill generation. Future work must add temporally extended skills, cross-skill interfaces, composition search, and independent novelty audits.
Read the full abstract ▾
Computer Vision
Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification
Yimin Zhu, Mahmood Elahi and Lincoln Linlin Xu
Although hyperspectral images (HSIs) provide rich spectral-spatial information, accurate pixel-level classification remains challenging because of spectral-spatial heterogeneity and complex spatial structures. Existing
vision state space models (Mamba) typically construct sequences according to predefined spatial neighborhoods, without explicitly accounting for semantic similarity or spatial non-stationarity. To address this limitation, we propose
Token Clustering and Semantic Sequence Mamba (STMamba), which organizes sparse
tokens into semantically coherent sequences for hyperspectral image classification with the following features. First, at the macro level, a hierarchical encoder decoder progressively selects semantic
tokens with the
Token Clustering Module (TCM) and restores dense features using a parameter-free Cross-scale Neighborhood
Attention (CNA) Upsampler. Second, at the micro level, TCM first identifies representative cluster centers through density-aware clustering and estimates soft memberships based on feature similarity. A quadtree-based dynamic selection strategy then retains sparse and spatially distributed
tokens from each semantic cluster, forming coherent semantic-
token sequences while reducing redundant pixel-wise representations. Third, parallel Spatial and Spectral Semantic-wise Sequencing Mamba (SWSM) modules capture complementary long-range spatial and spectral dependencies within homogeneous semantic
token sequences while suppressing irrelevant interactions across heterogeneous regions. Experimental results on three large-scale
benchmark datasets demonstrate that STMamba outperforms the SOTA methods with respect to quantitative and qualitative results.
Read the full abstract ▾
Instrumentation and Methods for Astrophysics
AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research
N. Sahakyan, M. Khachatryan, A. Mahabal et al. (+13 more)
Modern astrophysical research requires the integration of rapidly expanding scientific literature, heterogeneous observational data, and increasingly complex physical models. We introduce AstroGenesis (https://astrogenai.com), a domain-specific multi-
agent AI framework that integrates literature
retrieval, multiwavelength data access and analysis, theoretical modeling, and research ideation within a unified research environment.The current implementation focuses on blazar research, with specialized
agents coordinated by a Supervisor
Agent and Planner/Replanner architecture. These
agents provide capabilities for retrieving and synthesizing literature, accessing and analyzing multiwavelength observations, performing physical modeling, and identifying research directions. A central component is the Theoretical Modeling
Agent, which uses pretrained neural-network surrogate models to enable efficient broadband and multimessenger modeling through natural-
language interaction. The framework provides natural-
language access to science-ready multiwavelength observational data and
retrieval-grounded literature through a multi-stage
retrieval and ranking pipeline. The literature-
retrieval system was evaluated using two
benchmarks: a single-paper
benchmark, in which each question targets one publication, and a multi-paper
benchmark, in which questions may require evidence from several publications. At least one relevant publication was retrieved among the top five results for 76.6% of the single-paper questions and 79.2% of the multi-paper questions. Representative workflows demonstrate how literature, observational data, physical modeling, and hypothesis generation can be combined within traceable analyses. The framework is extensible to additional astrophysical domains, with the goal of streamlining research workflows and enabling efficient, connected, and reproducible scientific investigations.
Read the full abstract ▾
All authors N. Sahakyan, M. Khachatryan, A. Mahabal, D. Pasham, A. Khachatryan, V. Markosyan, N. Unkovskii, V. Vardanyan, D. Bégué, P. Giommi, G. Harutyunyan, D. Israyelyan, A. Tramacere, A. Casotto, Y. Wang, D. Li
Machine Learning
Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning
Jack Zheng and Hao Wang
The increasing adoption of electric vehicles (EVs) and rooftop photovoltaic (PV) systems is reshaping residential electricity demand and creating new challenges for demand-side management (DSM), tariff design, and low-voltage network planning. Much of the existing literature examines EV charging or PV generation in isolation, leaving the behavioral dynamics of household co-adoption less understood. We develop an integrated, two-part workflow to analyze advanced metering infrastructure (AMI) data. A discovery component applies dynamic time warping (DTW) k-means with DTW barycenter averaging to cluster daily import or export profiles into interpretable behavioral archetypes, while a predictive component trains a bidirectional long short-term
memory (BiLSTM) model on 21-day windows and
benchmarks it against tabular baselines for PV/EV activity detection. The EV activity labels are inferred from charging-like load signatures because charger measurements are unavailable. Using half-hourly AusNet residential data from Victoria, Australia, the clustering uncovers distinct patterns across PV-only, EV-only, co-adoption, and neither cohorts; for co-adopters, a midday-centered weekday export archetype accounts for approximately 50% of days. At validation-tuned thresholds, both BiLSTM and XGBoost achieve strong discrimination. BiLSTM obtains 0.991 for the area under the receiver operating characteristic curve (AUROC), 0.906 for macro-F1, and the highest recall on the most difficult class (0.836 for EV-only recall). Tree-based baselines remain competitive. Performance remains stable across plausible labeling rules (macro-F1: 0.894–0.914) and strictly forward temporal splits (macro-F1: 0.894–0.906).
Read the full abstract ▾
Sound
ASR ensembling for phoneme intelligibility evaluation of speech anonymizers
Victor Ménestrel, Sebastian Möller, Slim Ouni et al. (+1 more)
We present the first phoneme-level intelligibility evaluation of
speech anonymizers, assessing the performance of ASR-ensemble-based metrics against measured intelligibility from a crowdsourced listening test. Our results show that simple hard-voting ASR metric reaches correlations above 0.9 with human ratings when aggregated by feature, test-type, or condition, provided that multiple ASR models are combined; evaluating stimuli with and without a carrier sentence further improves the correlation at the stimulus level. However, posterior-probability-based confidence metrics bring no gain, which can be traced back to the insufficient calibration of the state-of-the-art open ASR models that were utilized here. All data, code, and evaluation tools are released as open source.
Read the full abstract ▾
All authors Victor Ménestrel, Sebastian Möller, Slim Ouni, Dorothea Kolossa
Machine Learning
Time-Series Foundation Models That Understand Data Revisions
Taimoor Ahmad
Historical observations are not always fixed: statistical agencies revise previously published values as new evidence arrives.
Forecasting from a contemporary download can therefore expose a model to information unavailable at the date it purportedly made a prediction. We propose VINTAGE-TS, a revision-aware adaptation of a time-series foundation model that distinguishes observation time from information-availability time. Its targets are the next period's first-published value and the value available a fixed number of days after that publication; neither is declared final truth. A joint predictive distribution preserves dependence between these targets and exposes uncertainty about their difference. We specify an ALFRED-based rolling evaluation, a matched Chronos-2 comparison, conventional and revision-aware baselines, and a separate audit of pretraining overlap. The accompanying software implements validity-interval reconstruction, delayed-label filtering, a frozen-backbone adapter interface, and reproducible diagnostics. An executed synthetic demonstration and a 25-configuration sensitivity suite verify the workflow, expose variation across seeds and revision regimes, and illustrate how hindsight contamination changes measured performance. Thirty one automated tests check temporal and integration contracts. Real ALFRED and Chronos-2 experiments have not been executed; no empirical foundation-model advantage is claimed.
Read the full abstract ▾
Artificial Intelligence
TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
Subrat Panda
Long-conversation
memory benchmarks increasingly test recall and prompted knowledge updates, and recent work studies evolving user beliefs and
memory state. TWIST is a proposed
benchmark suite for a complementary, unmeasured property: intervention quality – whether a deployed
memory system, exercised through its own ingest/recall/vet surface, acts correctly at belief change points. Four tracks cover unprompted tension detection, vetting outgoing drafts against the record, answering with current beliefs while preserving supersession history, and governing sensitive recall. The suite extends LoCoMo's corpora and harness, pairing every detect/block metric with a matched do-not-over-detect control: surface-matched hard negatives price false intervention, so no track can be gamed by flagging everything. The
benchmark itself is validated first: independent, gold-blind double annotation with adjudication, judge decoy calibration, and a separability audit. On the human-validated Track B v1.0 key (161 items, post-adjudication kappa = 0.85), no tested configuration simultaneously achieves high contradiction recall, high hard-negative specificity, and high attribution: flat-RAG baselines detect 0.76-0.97 of true contradictions but falsely flag 16-43% of surface-matched safe drafts depending on backend, while a deployed coherence-oriented system almost never over-flags (0.98-1.00 specificity) yet catches 42% of true contradictions – a trade-off no recall-only score can see. A 13-configuration baseline ladder localizes causes: every gold contradiction is detectable from its evidence alone (recall 1.000), calibrated models nearly solve the track given the full transcript – consistent with substantial
retrieval-coverage gaps – and draft-only floors reveal model-dependent style priors. A system's TWIST profile, beside its recall score, measures whether
memory knows when to intervene and when not to.
Read the full abstract ▾
Cryptography and Security
Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia et al. (+2 more)
Multi-stage LLM-based cyber
agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution evidence. Success rates alone obscure inefficiency, adaptation through retries, and recognition of success or failure. We present an end-to-end diagnostic study of an Autonomous Adversary system with orchestrator, executor, and validator LLMs in enterprise-like lateral-movement scenarios. Six frontier models are evaluated across two scenarios and three modes: expert-defined, self-scaffolded, and fully autonomous. We assess validator consistency and evidence grounding; introduce a subtask-conditioned, cost-aware score for abnormal
token use, retries, and runtime; and use comparative LLM-as-a-Judge analysis to identify planning deficiencies, including tool misalignment, plan similarity, over-specification, inadequate probing, and weak recovery. Validators are generally relevant and evidence-grounded but often nonspecific and overly optimistic. Bottlenecks cluster in credential and lateral-movement tasks, spread with scenario complexity, and vary more under full autonomy. Reliable evaluation must assess outcomes, evidence interpretation, resource use, and adaptation after failure.
Read the full abstract ▾
All authors Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia, Scott Buffett, Sherif Saad
Analysis of PDEs
Ornstein-Uhlenbeck semigroup maximal operator on weighted $L^p$ space
Christoph Kriegler and Jérémie Moukambi
Let $(\mathcal{H}\_t)_{t \geq 0}$ denote the standard Ornstein-Uhlenbeck
semigroup over ambient space $\mathbb R^d$ equipped with Gaussian measure $d\gamma(x) = e^{-|x|^2} dx$. Further let $\mathcal{H}^*(f)(x) = \sup_{t > 0} \mathcal{H}_t(|f|)(x)$ denote the associated maximal operator. Since $(\mathcal{H}_t)_{t \geq 0}$ is a Markovian
semigroup over $(\mathbb R^d,d\gamma(x))$, it is well known that $\mathcal{H}^*$ is bounded on $L^p(\mathbb R^d,d\gamma(x))$ for all $1 < p \leq \infty$. We show that $\mathcal{H}^*$ is also bounded on the weighted space $L^p(\mathbb{R}^d,\omega(x)e^{-\frac{p}{2}|x|^2}dx)$ for $1 < p <\infty$, for weights $\omega\,: \mathbb R^d \to (0,\infty)$ belonging to a certain Muckenhoupt type class $A^\alpha_p$, where $\alpha \in [0,1)$. Essentially, a weight $\omega$ belongs to $A^\alpha_p$ if and only if $\omega(Q) \omega^{-\frac{1}{p-1}}(Q)^{p-1} \leq C |Q|^p$ for all cubes $Q$ contained in any reference cube $N_\alpha(R_x) \subseteq \mathbb R^d$, where the well chosen family $(N_\alpha(R_x))_{x \in \mathbb R^d}$ covers $\mathbb R^d$, $N_\alpha(R_x)$ contains $x$ and the side length of $N_\alpha(R_x)$ is comparable to $1/\max(1,|x|)^\alpha$, with constants depending only on $d$. The class $A^\alpha_p$ contains the usual Muckenhoupt class. We also use the weight class $A_p^{loc}$ from \cite[Definition 2.2]{B} defined in a similar way as $A^\alpha_p$ but with dyadic subcubes contained in some $N(R)$ built over the Gaussian dyadic grid (see below), and we show that the local part $\sup_{t >0}\mathcal{H}_t(|f|\chi_{N(R_x)})(x)$ is bounded on $L^p(\mathbb{R}^d,\omega(x)e^{-\frac{p}{2}|x|^2}dx)$ if and only if $\omega \in A^{loc}_p$.
Read the full abstract ▾
Artificial Intelligence
DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs
Yingxuan Zhuang, Miao Pan, Wangjie Gan et al. (+6 more)
Reinforcement learning (RL) is widely used to sharpen
reasoning in
multimodal large
language models (MLLMs), yet its effect on
hallucination is uneven. We trace this to two weak points in the correction chain from reward to parameter update. At the rollout level, hard queries—those with high semantic
entropy—frequently produce unanimously wrong sample groups, collapsing the group-relative advantage to zero exactly where
hallucination risk is highest. At the optimization level, confident-but-wrong
tokens are gradient-invisible: a categorical policy's expected score-gradient norm vanishes as its distribution sharpens, so the predictions that most need correction receive the weakest updates. We propose Dual-
Entropy Enhanced Policy Optimization (DEEPO), a dual-stage enhancement combining signal variance regularization with gradient preconditioning: semantic-
entropy-triggered expert prefixes inject grounded continuations on high-uncertainty queries, providing direct supervision and restoring advantage variance, while advantage-sign-aware Renyi preconditioning counteracts logit-level saturation so correction reaches confident errors in the operational confidence regime. Both branches improve over GRPO individually; their interaction is statistically significant on VideoMMMU—the most complex long-horizon task in our evaluation suite (+4.0$, 95% CI [1.1, 6.9])—and additive elsewhere. DEEPO reduces
hallucination while preserving accuracy and training stability.
Read the full abstract ▾
All authors Yingxuan Zhuang, Miao Pan, Wangjie Gan, Jingxiao Yang, Fan Wang, Weiming Liu, Cheng Tan, Xuhong Zhang, Jintao Chen
Functional Analysis
Erratum and a counterexample to: Stability of diametral diameter two properties
Johann Langemets
In Proposition 3.5 of our paper [J. Langemets and K. Pirk, Stability of diametral diameter two properties, RACSAM (2021)], we claimed that the convex DLD2P lifts from an $M$-ideal to its superspace. The proof contains a quantifier error. We show that its valid part yields the following replacement: for every $\varepsilon>0$, every slice of the unit ball of the superspace contains a $(2-\varepsilon)$ $\Delta$-point of norm arbitrarily close to one. In particular, the unit ball is the closed convex hull of these points at each fixed scale, and the superspace has the local diameter two property. Finally, we prove that the original claim was false, we construct
Banach spaces $Y$ and $X$ such that $Y$ has the convex DLD2P, $Y$ is an $M$-ideal in $X$, yet $X$ fails the convex DLD2P.
Read the full abstract ▾
Software Engineering
Pretraining and adapting a language model on a dependency-free stack: GPT-2 124M from random weights, reproduced against llm.c, and a clinical adapter for Qwen3-0.6B
Thang Tran and Lan Dang
Almost every
language model in service was trained by one family of software. That concentration makes a question hard to settle: how much of what is known about training a
language model describes
language models, and how much describes that software? Settling it needs a second implementation able to carry a model through a whole lifecycle rather than reproduce one operator. We report such a lifecycle. Using numbat, a machine-learning stack written in Zig with no third-party runtime dependencies, we pretrain a 124.4 M-parameter GPT-2 from random initialisation over 9.91 B
tokens of web text, then adapt a separate small model to clinical question answering. A reference implementation runs on identical hardware at both stages, and a sidecar with authority to halt a run supervises each. Agreement is close. Held-out cross-
entropy finishes at 3.2588 against a published 3.29, and HellaSwag at 0.3053 against 0.299; across 8 paired evaluations it sits below a same-machine reference at every point, by 0.0608 on average. Re-running that reference on different hardware moves it 0.0035, which bounds how much of any gap is method rather than framework. Throughput does not pay for agreement: measured in one session at a production configuration, numbat reaches 43,374
tokens per second against PyTorch's 41,202, scaling 2.769x over three cards. Clinical adaptation ends at 2.1899 held-out loss against 2.1941. Neither model is a medical device, and neither is validated for clinical use.
Read the full abstract ▾
Machine Learning
Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs
Muhammad Awais, Muhammad Yaseen, Abdul Shakoor et al. (+3 more)
Scanning electron microscopy (SEM) is routinely used to characterize the microstructural changes caused by hydrogen embrittlement (HE) in structural steels. Machine learning can automate this characterization, but models are often evaluated using image-level splits. When several images come from the same specimen region, such splits leak information between the training and test sets. Here, we propose a region-held-out protocol for classifying as-received (AR) and hydrogen-charged (H2) SEM micrographs of 316L stainless steel, based on Leave-One-Region-Out (LORO) cross-validation over 14 spatial regions (8 AR, 6 H2; 31 images). We compared six feature-classifier combinations built on local binary patterns (LBP), grey-level co-occurrence
matrices (GLCM), self-supervised convolutional
embeddings pretrained on 143 unlabeled SEM images, and a convolutional neural network (CNN). The simplest texture approach, LBP with a support vector machine (LBP+SVM), performed best, achieving a balanced accuracy of 0.79, H2 recall of 0.69, and H2 precision of 0.82, outperforming every deep-learning and combined-feature model. A group-level permutation test (500 permutations sampled from the 3,003 possible region-to-label assignments) yielded p = 0.008, indicating that the result cannot be explained by a chance
alignment of the region structure. Grad-CAM maps from a CNN trained on the full
dataset tended to concentrate on localized surface and grain-boundary features, where hydrogen-induced morphological changes are known to occur. Under a leakage-safe, statistically validated protocol, texture descriptors recover a hydrogen-charging signature from SEM micrographs even with few samples, and the same protocol can be extended to larger HE detection studies in other
alloy systems.
Read the full abstract ▾
All authors Muhammad Awais, Muhammad Yaseen, Abdul Shakoor, Niaz Ahmed Niaz, Huria Zia, Muhammad Zain Shakoor
General Mathematics
Primitive norm extraction and a signed descent for the cubic Fermat equation
R. Laniewski
We give a self-contained proof of the cubic case of Fermat's
theorem through a signed form of Euler's descent, with the required extraction step proved directly in $\mathbb{Z}[\sqrt{-3}]$. A pigeonhole argument of Thue represents the relevant
primes by $X^2+3Y^2$, and explicit division in $\mathbb{Z}[\sqrt{-3}]$ lifts primitive odd-power norms to powers in that order. For cubes, the resulting coordinate identities transform $2K(K^2+3M^2)=C^3$ into another equation of the same signed form with a strictly smaller non-zero integer height. The construction gives $|C'|\le |C|/39$. Half-sums and half-differences of the two odd entries place the sum and difference parity configurations in this single descent.
Read the full abstract ▾
Machine Learning
When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages
Rameesha Zia and Muhammad Shahid Iqbal Malik
Post hoc explanation methods such as SHAP and LIME are widely used to interpret text classifiers, but their visualizations are mainly designed for left-to-right
languages. When applied to right-to-left (RTL)
languages such as Urdu, Arabic, Persian, and Hebrew, the attribution values remain mathematically valid, while their visual presentation fails.
Tokens appear out of sequence, connected letterforms break apart, and plot layouts do not follow the natural reading direction. This study addresses this gap as a visualization problem rather than a limitation of the explanation methods themselves. We present SHAP-RTL, a rendering layer that corrects reading direction and script shaping in SHAP and LIME visualizations, with per-
language font selection, while preserving the original attribution values, feature ordering, and model outputs. The approach is evaluated on Urdu, Arabic, Hebrew, and Persian hate and offensive-
language datasets using TF-IDF and logistic regression classifiers. Rendering correctness is measured by an OCR round trip over 200 feature words per
language. Default rendering yields character error rates of 0.820 to 0.979, meaning the label no longer carries its
token; the common reshape-and-reorder workaround fails for Urdu at 0.998, worse than no correction; and the Matplotlib 3.11.0 text rewrite inverts that workaround, while SHAP-RTL remains correct under both versions. The framework also verbalizes the same attributions as short contextual explanations in the reader's
language, constrained to the identified features. Evaluation in this paper concerns rendering correctness; assessment of the generated explanations is left to future work. The study highlights the importance of
language-aware visualization in making post hoc explainability more accessible across different writing systems.
Read the full abstract ▾
Cryptography and Security
Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents
Jian Xu
Agentic
video-generation systems close a loop between a generator and a verifier: an LLM plans shots, calls a text-to-
video model, and a
multimodal judge decides whether the result satisfies the request. To diagnose where a long workflow fails, recent harnesses deliberately show the judge more than the
video-the
agent's execution trace, its plan, the narration it synthesized. We ask whether this auxiliary text moves the judge's verdict on purely visual requirements, holding the frames fixed. On a
benchmark of 109 generated two-event clips with manual labels, in which the requested event is either visibly completed or visibly missing, a trace that reports a successful tool call makes three open-weight Qwen-VL judges (7B, 8B, 32B) accept $78$–$90\%$ of the failures, up from $7$–$19\%$ without text, and a contradicting trace makes them reject up to $100\%$ of correct clips; an instruction to “use only the frames” does not remove the effect. Frontier closed judges are essentially unmoved on the same clips, showing that the vulnerability is a property of the judge's learned trust in tool logs rather than of the task. Plan-derived text carries no clip-specific information, so it can only shift a judge's operating point, and in a repair loop that shift becomes a cap on the true pass rate that no repair policy can exceed; the cap matches simulation to two decimals. In the loop, contamination is exploited without any
adversarial agent: an honest LLM planner that always regenerates ends with a judge pass rate of $1.00$ and a human-labelled pass rate of $0.28$, and a pipeline in which a cheap checker writes its verdict into the trace launders that checker's errors into a stronger final judge ($0.69$ false accepts).
Read the full abstract ▾
Machine Learning
SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference
Shiting Ruan, Xitong Ling, Qiming He et al. (+6 more)
Spatial transcriptomics (ST) profiles gene expression within tissue architecture, but its cost and experimental complexity limit routine use. Predicting spatial expression from routinely available hematoxylin and eosin (HE) images therefore offers a scalable alternative. However, conventional methods often fit high-dimensional gene outputs as independent targets, overlooking the biological coordination among genes while remaining vulnerable to high-dimensional noise and overfitting. Existing attempts to address this limitation often rely on computationally heavy graph networks or complex auxiliary supervision. We therefore introduce SpaFactor, a lightweight and efficient low-rank morphology-program-gene factorization framework. At the input, SpaFactor efficiently fuses the visual representation of the central spot with multiscale local and regional neighborhood context, yielding a histologic representation that captures cellular morphology and microenvironmental heterogeneity. For modeling, a residual MLP stably learns a nonlinear mapping from the tissue microenvironment to low-dimensional latent gene programs. These activities are decoded through shared gene loadings into coordinated multi-gene expression predictions. Across five public cohorts, SpaFactor achieves the best aggregate performance, with particularly clear improvements for spatially variable genes, and more faithfully recovers biologically organized spatial patterns. These results demonstrate that lightweight joint modeling of tissue context and gene programs can improve both predictive accuracy and biological fidelity.
Read the full abstract ▾
All authors Shiting Ruan, Xitong Ling, Qiming He, Ziyou Yan, Huaitian Yuan, Tian Guan, Ying Xiao, Xu Guan, Yonghong He
Machine Learning (Statistics)
Matrix Aggregation Operators
Inmaculada Gutiérrez, Asier Urio-Larrea, J.Tinguaro Rodríguez et al. (+3 more)
Aggregation theory has traditionally focused on operators defined over vectors. However, many applications-including Multi-Criteria Decision Making, Group Decision Making, Fuzzy Rule-Based Classification Systems, and overlap/grouping indices-require aggregating information naturally structured as a
matrix of membership degrees (e.g., where a set of objects interacts with a family of fuzzy sets). Despite this, no formal framework has been proposed for this class of operators, partly due to the common practice of flattening
matrices into vectors (which discards structural information) and partly due to a reliance on decomposable operators that aggregate rows and columns sequentially. This paper addresses this gap by formalizing the notion of a
matrix aggregation operator (MAO). We analyze the decomposability and
symmetry properties of MAOs, showing that certain operators cannot be expressed in decomposable form and examining several notions of
symmetry. Finally, we introduce a family of MAOs termed maximum
entropy global coverage indices (MEGCIs), provide a construction method for them based on combining grouping functions and MEOWA operators, and illustrate their usefulness in cluster quality assessment through an extensive computational study.
Read the full abstract ▾
All authors Inmaculada Gutiérrez, Asier Urio-Larrea, J.Tinguaro Rodríguez, Daniel Gómez, Javier Montero, Humberto Bustince
Machine Learning
CARE: Condition-Aware Representation Regularization for Diffusion Models
Fengjia Guo, Zhuoyi Yang and Jie Tang
Recent advances in
diffusion models highlight the importance of representation regularization for improving sample quality and training efficiency. However, commonly used regularization methods often overlook the built-in conditions (such as labels or texts) which directly determine the generation target. In this work, we demonstrate how conditioning signals affect the feature distribution and introduce the CARE (Condition-Aware REpresentation regularization). CARE is a lightweight plug-and-play regularization framework that dynamically modulates feature distribution based on condition similarity. CARE leverages built-in conditioning signals to judiciously guide the representation space, promoting tighter feature clusters for similar conditions without relying on explicit
alignment losses or external supervision. Empirically, CARE consistently improves both visual fidelity and convergence stability across both class-to-image and text-to-image tasks. On ImageNet, CARE achieves a 19.08% reduction in FID in 400k training steps, leading to a 3.5$\times$ speed-up. When applied to text-to-image generation, CARE lowers FID by 16.61% in 200k iterations and improves semantic
alignment between generated samples and text
prompts. Moreover, CARE can be seamlessly integrated with existing regularization methods, yielding additional performance gains.
Read the full abstract ▾
Machine Learning (Statistics)
Speculative Evaluation of Stochastic LLMs
Qianli Shen, Xiang Li, Ruomeng Ding et al. (+3 more)
Evaluating a
stochastic large
language model is costly:
benchmark scores estimate expected performance from randomized rollouts, yet uniform repetition ignores sharp differences in task-level rollout variance. We ask how to minimize the variance of a fixed-
benchmark mean under an exact rollout budget. We develop Speculative Evaluation with a Hierarchical
Bayesian Neyman (HBN) policy with pilot size and stage weight jointly chosen ex ante. It runs a short uniform pilot, pools per-task success counts with a hierarchical
Bayesian model, and uses posterior expectations of task-level sampling variances for exact positive-integer Neyman allocation. To mitigate the pilot synchronization barrier, HBN-async speculatively executes continuations from partial pilot feedback and retains those selected by the final allocation. Across six checkpoints and 18
benchmark groups, we evaluate 107 nondegenerate
benchmark-checkpoint profiles. For rollout budgets of 8-64 per task, Speculative Evaluation reduces variance relative to Uniform by 12.8%-33.6% on average across profiles, outperforming hindsight-tuned empirical and independent
Bayesian baselines. Real-generation experiments that account for the pilot synchronization barrier show that HBN-async mitigates its overhead, helping translate statistical efficiency into practical evaluation benefits.
Read the full abstract ▾
All authors Qianli Shen, Xiang Li, Ruomeng Ding, Yanxi Chen, Daoyuan Chen, Yaliang Li
Cryptography and Security
Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
Chuyi Wang, Xiaohui Xie, Tongze Wang et al. (+2 more)
LLMs increasingly operate through coding-
agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an
agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures. Existing LLM fingerprints largely infer identity from direct text or
token distributions. In coding
agents, these signals are mediated by system instructions, controller logic, tools, and execution feedback, limiting their transfer. We present
LIDAR (LLM Identification from Decisions and Actions at Runtime), an active black-box fingerprinting method for coding-
agent execution. Three coding probe pairs expose post-edit verification, transient-failure recovery, and specification–test conflict resolution under controlled changes.
LIDAR represents the resulting trajectories with complementary instance-level and distribution-level features and compares them with clean references using a lightweight probabilistic identifier. It requires no access to model weights, logits, or provider internals. Across 36 models from seven families and two
agent harnesses,
LIDAR achieves high Top-1 accuracy and MRR and outperforms four existing fingerprinting and API-
auditing baselines. Ablations confirm that the two feature levels, all probe pairs, and their controlled variants contribute. These results show that
agent execution behavior provides model-identity evidence beyond final outputs.
Read the full abstract ▾
All authors Chuyi Wang, Xiaohui Xie, Tongze Wang, Fangchen Luo, Yong Cui
Machine Learning
CFD Correction of Open Tip Clearance Flow in a Compressor Cascade Using VAE Latent Space Adaptation
Xiang Zuo, Hefang Deng, Caiyan Chen et al. (+4 more)
CFD predictions of open tip clearance flow in compressor cascades are subject to discrepancies relative to experiments, while experimental observations are sparse and high-resolution experimental ground truth is unavailable. This study proposes a non-intrusive correction method based on a variational autoencoder (VAE) and latent-space adaptation. A VAE is first trained using a
dataset of 166 parametrically sampled CFD total pressure loss fields to learn a low-dimensional statistical representation of these fields. The VAE is then frozen, and a low-rank latent-space adapter is trained using only 12 paired CFD–experiment operating conditions. An observation operator maps the corrected high-resolution fields to the experimental observation space, allowing supervision to be applied only at the available measurement locations and within the measured pitchwise windows. In the current 12-fold cross-validation, the mean absolute error decreases from 0.1335 to 0.0473, the root mean square error from 0.1717 to 0.0621, and the relative $L_2$ error from 0.5108 to 0.1871. These results indicate that the method improves agreement between CFD predictions and sparse experimental observations of open tip clearance flow without modifying the RANS solver or constructing artificial high-resolution experimental labels.
Read the full abstract ▾
All authors Xiang Zuo, Hefang Deng, Caiyan Chen, Honglin He, Mingmin Zhu, Songan Zhang, Jinfang Teng
Artificial Intelligence
BaseCamp — An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
Eranga Bandara, Xueping Liang, Asanga Gunaratna et al. (+19 more)
DNA sequencing pipelines, spanning quality control,
alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate established bioinformatics tools at scale. What remains manual is the decision layer surrounding that execution: selecting quality thresholds appropriate to a sample and platform, adjudicating borderline variant calls, diagnosing anomalies, and determining which findings warrant expert review. These decisions are repetitive, judgment-intensive, inconsistent across operators, and frequently undocumented. This paper introduces BaseCamp, a novel agentic AI framework for automating the decision layer of DNA sequencing pipelines. The framework decomposes the pipeline into six specialized AI
agents, covering sample intake and quality control,
alignment, variant calling, annotation, cross-stage monitoring, and reporting. Critically, BaseCamp
agents do not perform sequence analysis: established tools execute
alignment, calling, and annotation, while the
agents select among them, configure them, interpret their output, and decide what follows. This confines
language model
reasoning to the judgment layer where it is reliable and preserves the reproducibility existing tooling guarantees.
Agent reasoning is powered by a consortium of fine-tuned, domain-specialized large
language models coordinated by a central
reasoning LLM, executing locally so no sequencing data leaves the operating environment, under human-in-the-loop orchestration. Evaluation shows
agent-generated configurations are concordant with expert practice, that an explicit filtering ledger renders inspectable what filtering otherwise removes without trace, and that cross-stage anomaly detection surfaces conditions execution monitoring misses. BaseCamp offers a generalizable blueprint for agentic automation of scientific data pipelines.
Read the full abstract ▾
All authors Eranga Bandara, Xueping Liang, Asanga Gunaratna, Tharaka Hewa, Abdul Rahman, Peter Foytik, Safdar H. Bouk, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Chalani Rajapakse, Ng Wee Keong, Kasun De Zoysa, Amin Hass, Wathsala Herath, Ross Gore, Ravi Mukkamala, Nihal Siriwardanagea, Gihan Siriwardanagea, Aruna Withanage, Nilaan Loganathan, Sachin Shetty
Combinatorics
Spectral extremal graphs for $W_5$-free graphs with odd size
Jing Gao, Xianya Geng and Shuchao Li
For a fixed integer $k\ge 2$, let $W_{2k+1}=K_1\vee C_{2k}$ be an odd wheel graph. The fixed-size spectral extremal problem aims to determine \[ \operatorname{spex}(m,W_{2k+1}):=\max\{\rho(G): e(G)=m,\ G \text{ is } W_{2k+1}\text{-free}\}, \] where $\rho(G)$ denotes the adjacency spectral radius. Based on this problem, Yu, Li, and Peng [12] proposed the following
conjecture: When $m-\binom{k}{2}$ is divisible by $k$ and $m$ is large, every $W_{2k+1}$-free graph of size $m$ satisfies \( \rho(G)^2-(k-1)\rho(G)\le m-\binom{k}{2} \) with equality precisely for $K_k\vee qK_1$. For nonzero residue class, Yu, Zhang, and Zhang [13] proposed the following
conjecture: Let $r$ be a nonzero remainder when $m-\binom{k}{2}$ is divided by $k$ and $m$ is large. Then $S_{k,m}$ is the unique graph among $W_{2k+1}$-free graphs of size $m$ having maximum spectral radius, where $S_{k,m}$ is obtained from $K_k\vee qK_1$ by adding a vertex $z$ and joining it to exactly $r$ vertices of the $K_k$. Very recently, Fang, Zhai and Zhang [4] confirmed the Yu–Li–Peng
conjecture for $k\ge 2$. Chen, Gao and Li [2] confirmed Yu-Zhang-Zhang
conjecture for $k\ge 3$. When $k=2$, then $W_5=K_1\vee C_4$. For large odd $m$, determining $\operatorname{spex}(m,W_5)$ is still open. In this paper we address the odd-size problem. Our result disproved Yu-Zhang-Zhang
conjecture for $k= 2$. In our proof, a universal defect bound shows that only $O(1)$ edges can lie outside the dense core. Perron localization then reduces this to at most one edge. A discrete defect inequality forces the complete bipartite crossing and quantizes the two matching deficiencies. Exact quotient-
polynomial comparisons eliminate the remaining cross-edge and odd–odd candidates.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Finite-Temperature Axion-Admixed Neutron Stars in a Quarkyonic Crossover Framework
S. K. Patra, D. Dey, Jeet Amrit Pattnaik et al. (+1 more)
We analyze the effect of
axion contribution on the mass, radius and dimensionless deformability of a
neutron star (NS) at finite temperature. Although the cooling of an NS is mainly due to the emission of
neutrinos, additional cooling cannot be ruled out due to the emission of
axions. The existence of an
axion is needed for addressing the strong CP problem within the standard model. The Peccei-Quinn (PQ)
symmetry breaking mechanism generates
axions. They are pseudo-Nambu-Goldstone
bosons. Their mass is extremely small but non-zero. This naturally resolves the fine-tuning problem of the strong CP-violating parameter ${\theta} \lesssim 10^{-10}$. We propose that a finite temperature NS feature a
quark core surrounded by a baryonic medium admixed with the
axions, which are pseudo scalar Goldstone
bosons and are considered as strong candidates for the dark matter (DM). Unlike the original quarkyonic model, we formulate a quarkyonic-inspired smooth crossover equation of state (EoS) at finite temperatures. This smooth crossover avoids thermodynamic instabilities found in sharp first-order constructions. We add the axionic EoS to the finite temperature quarkyonic one and solve the Tolman-Oppenheimer-Volkoff equations to estimate the properties of the NS both with and without taking the
axion into account at different temperatures. We find that the production of
axions is maximum within a radius of $5-11$ km in the
star's interior; however, the impact on the mass is significant, i.e., $\sim 60\%$ of
axion mass concentrated in the central region of the
star. We also find that the effect of temperature on the mass of NS is marginal unlike the radius. In general, the influence of
axions is significant for the observational properties of NS. These results highlight the pivotal role of
axion physics in
neutron star phenomenology.
Read the full abstract ▾
All authors S. K. Patra, D. Dey, Jeet Amrit Pattnaik, R. N. Panda
Artificial Intelligence
Pistis Technical Report
Heyun Chen, Xiaohan Lan, Jiaxi Li et al. (+17 more)
We introduce the Pistis model family, comprising 27B- and 9B-parameter
multimodal large
language models built on Qwen3.6 and Qwen3.5, respectively, and developed through a general and scalable post-training framework. The framework first establishes a strong foundation through large-scale
multimodal supervised fine-tuning (SFT). Building on this SFT foundation, we propose Interleaved
Distillation and Reinforcement Learning (IDRL), a novel post-training paradigm that tightly integrates on-policy
distillation and reinforcement learning within a single training loop. By alternating between the two objectives, rather than optimizing either in isolation or combining them in a static joint loss, IDRL enables more effective knowledge transfer, greater optimization stability, and more precise credit assignment for long-horizon agentic trajectories, leading to stronger performance while mitigating common capability trade-offs. At both model scales, the framework produces two specialized variants: Pistis-Thinking, designed to strengthen deep
multimodal reasoning, and Pistis-Agentic, which additionally incorporates agentic trajectory data to support long-horizon planning, iterative
reasoning, and tool use. Pistis-Agentic is particularly strong in
multimodal search. Both scales outperform their corresponding base models. Beyond model-parameter optimization, we further introduce Pistis-Auto-Harnessing (PAH), a system-level method that automatically improves the
agent's inference harness through iterative optimization. Experiments demonstrate that PAH enhances the model performance without updating the model parameters or increasing the interaction budget.
Read the full abstract ▾
All authors Heyun Chen, Xiaohan Lan, Jiaxi Li, Zhilin Lu, Qi She, Weiwen Xu, Fei Yu, Yujie Zhong, Jinghuan Chen, Zijian Feng, Siyu Jiao, Yiheng Lin, Xinhao Wang, Sihan Yang, Jieyu You, Changbin Zhang, Hengyu Zhang, Xudong Zhang, Yunqing Zhao, Shuai Zheng
Machine Learning
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
Quang Minh Nguyen, Thuy Quynh Nguyen, Duc Minh Le et al. (+3 more)
Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generalization, and the clinical need for interpretable predictions. Single-modality approaches-SMILES
Transformers or graph neural networks capture complementary aspects of molecular structure, while sequence-only models cannot directly provide graph-attributed explanations. We present SMILESGNN, a
multimodal architecture that fuses a SMILES
Transformer encoder and a GATv2 graph encoder via cross-
attention, and SMILESGNN-PT, a variant using a ChemBERTa-2 pretrained backbone. The design retains an explicit graph branch within the predictive pipeline, supporting GNNExplainer-based analysis of substructures associated with toxic predictions. On ClinTox, SMILESGNN achieves AUC-ROC 0.987 and F1 0.906 with only 0.4M parameters, performing competitively with a strong SMILESTransformer and a larger ChemBERTa-2/GATv2 concat-fusion baseline. On Tox21 (12 tasks), SMILESGNN-PT obtains mean AUC-ROC 0.750, comparable to ChemBERTa-2 alone and the same-backbone concat-fusion baseline. Overall, the results suggest that cross-
attention is a practical fusion alternative that preserves competitive predictive performance while enabling graph-based interpretability support.
Read the full abstract ▾
All authors Quang Minh Nguyen, Thuy Quynh Nguyen, Duc Minh Le, Ho Nhat Minh Nguyen, Thanh Long Dai Doan, Trong Nghia Nguyen
History and Overview of Mathematics
Percolation on Finite Graphs
Michael Krivelevich
Lecture notes from a graduate course given by Michael Krivelevich at the School of Mathematical Sciences of Tel Aviv University in the spring semester of 2026. Topics covered include: phase transition and the
giant component in $G(n,p)$; long paths and cycles in supercritical and sparse random graphs; thresholds for connectedness and perfect matching; general model of a random subgraph of a finite graph; phase transition and the
giant component in the random hypercube;
polynomial diameter of the
giant component; perfect matchings in the random hypercube.
Read the full abstract ▾
Machine Learning (Statistics)
An Order-Theoretic Characterization of Consistent Inductive Inference
Zhou Lu
When can a learner make only finitely many prediction errors along every infinite sequence labeled by a fixed, unknown hypothesis? We characterize this form of consistency for arbitrary binary hypothesis classes in ZFC, without requiring a uniform mistake bound. The characterization uses a single linear order on finite realizable traces. Each trace selects its least subtrace, and the order must satisfy two conditions: conflicting traces select different subtraces, and the order is well-founded on the traces of each fixed target. These conditions induce a learner whose selected evidence decreases on every mistake. Conversely, a consistent learner yields such an order through canonical mistake transcripts and the Kleene–Brouwer ordering. The result provides a representation of consistent prediction by finite evidence, answering a question of Lu (2024).
Read the full abstract ▾
Group Theory
Graphical Discreteness, Coxeter Doublings and Generalized Polygons
Xing-Yu Hu
Graphical discreteness is not preserved under quasi-isometry in general. We prove that, for every finite thick generalized $m$-gon $\Gamma$ with $m\geq 3$, graphical discreteness is nevertheless constant on the class of finitely generated groups quasi-isometric to the right-angled Coxeter group $W_\Gamma$: such a group $\Lambda$ is graphically discrete if and only if $\Gamma$ is nonflexible, meaning that no nontrivial graph
automorphism of $\Gamma$ fixes a closed
star pointwise. The proof combines quasi-isometric
rigidity of Fuchsian buildings with a metric-strata argument that recovers the standard Coxeter Cayley graph from the building metric. For finite-rank Coxeter systems, we also show that the
automorphism group of the standard Cayley graph is compact-by-discrete if and only if it is discrete, equivalently, if and only if the defining diagram is nonflexible. We further obtain obstructions to graphical discreteness from one-vertex doublings, classify compact-by-discreteness for standard chamber graphs of graph products of finite groups, and derive applications to finite projective planes and to right-angled Coxeter groups with Menger curve boundary. Our methods do not settle whether nonflexible finite thick generalized polygons exist.
Read the full abstract ▾