Papers

Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesis pipelines now generate tasks, environments, and trajectories independently and at very different costs, turning data into a structured design space. This raises a question pretraining never had to answer: given a synthesis budget, which axis should be scaled? We address this question end-to-end with three tightly coupled contributions. First, we decompose agentic data into three cardinality axes (task, environment, trajectory), plus a reward-density control variable, and fit per-axis scaling relations on different large language models (LLMs) across math+code, SWE, web, and UI/tool application domains. Across all model sizes, model families, domains, and RL algorithms (PPO and GRPO) we measured, the scaling exponents order as environment $>$ task $>$ trajectory. When environment diversity is decomposed into world and environment-structure diversity, its advantage is mainly driven by the former, while the latter is just comparable to the task diversity. Second, we use the fitted laws as a common ruler to price synthesis methods, capturing each method's efficiency as a per-axis discount factor and identifying critical synthetic-to-real ratios at which collapse begins; these ratios differ by an order of magnitude across axes. Third, we cast budget allocation as a constrained optimization under our laws and discounts, deriving a Chinchilla-style compute-optimal recipe and validating it at held-out scale. The empirical results demonstrate that following the recipe yields up to $1.7\times$ compute efficiency over the dominant “scale-the-trajectories” practice.

The scarcity of domain-specific annotated images remains a major limitation for developing computer-vision systems for Hajj crowd analysis. Existing crowd-counting datasets and unconstrained generative models do not capture Hajj-specific visual conditions, including sacred-site geometry, white-clothed pilgrim crowds, and indoor/outdoor illumination variation. This study presents CrowdH-Edit, a reference-guided, instruction-based framework for synthetic Hajj crowd-image generation. Real Hajj images provide structural references, while textual instructions guide changes in crowd conditions and illumination and help preserve the main scene layout. Stable Diffusion 2.1 and Stable Diffusion XL 1.0 with low-rank adaptation were evaluated as comparative baselines. Qwen Image Edit was used without additional training within a ComfyUI workflow and selected for final dataset construction. The workflow produced CrowdH-Edit, a cleaned pool of 6,122 synthetic images, from which 387 images were selected and annotated to construct CrowdH-Edit-Ann-387. Among the evaluated generation pipelines, Qwen Image Edit achieved the highest semantic-alignment score and the lowest distributional and perceptual distances. Downstream evaluation across five crowd-counting models showed that adding the annotated synthetic subset to real training data reduced mean absolute error for three models and root mean squared error for two. These findings indicate that reference-guided synthetic Hajj imagery can support crowd-counting training, although its benefits depend on the model and evaluation metric.

Large language models make it cheap to run influence operations whose messages never repeat, yet real platforms offer almost no ground truth for testing whether coordination detectors can find them. The problem is sharpest on Telegram, which moderates little and spreads content through broadcast channels and forwarding rather than a follow graph. We introduce TeleTwin, an LLM-powered digital twin of a Telegram crisis-discourse ecosystem in which channels are agents, each instantiated from the history of a real channel, calibrated on 1.07 million messages from 195 public channels on the Israel-Gaza and Iran-Israel conflict (March-August 2025). On a held-out period containing the June 2025 Iran-Israel war, the twin tracks daily dynamics better than statistical baselines (correlation 0.86 against 0.64) and reacts to the war unprompted, but it over-focuses on the conflict, over-amplifies forwarding cascades, underestimates the shock and writes recognisably LLM-like text. We then inject LLM-written campaigns with known membership into the real data and into the twin. In real data, identical-text, co-URL and synchrony detectors fail once a campaign rewords, staggers or drops links; multilingual semantic similarity recovers loud campaigns, including cross-lingual ones, but not quiet ones, and its false positives fall unevenly across political perspectives. Inside the twin all detectors fail, because the simulated background is about 40 times more semantically homogeneous than the real one. Digital twins can supply ground truth for campaigns, but not, without calibrating their diversity, a realistic background for evaluating semantic detectors.

Motion planning in unstructured environments is a bottleneck for robot deployment. Current visuomotor policies predominantly rely on external cameras, introducing perceptual blind spots and fragility due to occlusions, clutter, and calibration constraints. To overcome these limitations, we propose ESCAPE, an online egocentric sensing framework for collision-free trajectory generation. ESCAPE aggregates sparse measurements from distributed depth sensors, converting them into a structured, obstacle-aware point cloud representation. Our policy leverages a flow matching-based generative framework, and trains on a high-quality dataset comprising over 100K safety-critical trajectories. With joint optimization of goal-reaching and collision objectives, it produces safe trajectories directly from these egocentric inputs. Crucially, ESCAPE is trained entirely in simulation and transfers zero-shot to physical hardware without any real-world fine-tuning. Extensive simulation and real-world evaluations demonstrate that ESCAPE achieves stable motion planning using only egocentric perception, outperforming external-view and voxelized-planning baselines across both simulation and real-world evaluations.

LLM agents accumulate valuable task-specific information through their actions, observations, and environmental feedback during multi-turn task execution. When effectively used, this information can help agents refine subsequent decisions and improve task performance. However, the learning value of an interaction depends on its context and subsequent feedback, making it challenging to extract reliable, actionable lessons and revise them as the task unfolds. In this paper, we introduce ReTTT, which enables experience-driven self-adaptation through test-time training on lessons constructed and continually revised within an episode. ReTTT lets the agent reflect on interaction feedback, maintain the resulting lessons in an explicit memory, and learn from them by updating an episode-local LoRA adapter while keeping the backbone frozen. The adapted model then performs both subsequent actions and reflection, coupling policy adaptation with the construction of future learning experience. We evaluate ReTTT on ALFWorld, ScienceWorld, and SWE-bench Lite using two model families. ReTTT outperforms trajectory-based test-time training across all six model–benchmark settings, improving task success by up to 12.14 percentage points. A frozen-reflection comparison further shows a 7.14-point benefit from adapting the reflection policy, while trajectory analysis illustrates how adapted reflection derives more task-specific guidance from failed attempts. These findings suggest that learning to reflect on its own behavior can boost agents' performance on long-horizon tasks.

Human Activity Recognition (HAR) using wearable or smartphone inertial sensors is commonly evaluated with both classical machine learning and deep learning methods. However, reported performance can be strongly affected by sensor modality, dataset characteristics, and data-splitting strategy. This study presents a controlled comparative evaluation of four classical machine learning models and four deep learning models on two public HAR datasets, UCI-HAR and KU-HAR. Three sensor modalities were considered: accelerometer (ACC), gyroscope (GYRO), and their combination (ACC+GYRO). Classical machine learning models used handcrafted statistical features, while deep learning models operated directly on raw sensor sequences. The primary evaluation employed five-fold StratifiedGroupKFold cross-validation, with subject- or participant-level grouping to prevent group overlap between training and test folds. Macro-F1 was used as the primary performance metric. The results show that deep learning did not consistently outperform classical machine learning. On UCI-HAR, the evaluated deep learning models achieved slightly higher macro-F1 values, whereas on KU-HAR, LightGBM achieved 0.857 compared with 0.828 for the highest-performing evaluated deep learning model. Regarding sensor modality, the combined ACC+GYRO configuration generally outperformed ACC or GYRO alone on both datasets. The evaluation protocol also had a substantial effect: for CNNBiLSTMAttn with ACC+GYRO, random splitting increased macro-F1 by 0.033 on UCI-HAR and 0.093 on KU-HAR compared with grouped evaluation. These findings highlight the importance of model family, sensor modality, dataset characteristics, and group-aware evaluation when assessing sensor-based HAR systems.

Collision detection for complex non-convex objects is a bottleneck in physics simulation, virtual reality, and robotics. Inner sphere trees (ISTs) answer proximity and penetration queries efficiently, but their greedy leaf-sphere construction is sequential and computationally expensive, which limits both large-scale preprocessing and runtime use. In this work, we present ML-IST, a machine-learning-based method that reformulates leaf-sphere generation as a single-shot set-prediction problem: a network predicts a fixed set of inscribed sphere candidates from multichannel voxel geometry, differentiable coverage feedback corrects the coarse prediction and fills residual gaps at finer scales, and a lightweight geometric projection enforces validity. Averaged over the test set, a single-GPU implementation of ML-IST reduces mean leaf-generation time by a factor of $2.0$–$2.6$ over single-core CPU construction across target capacities of 64–512 spheres, and qualitative results on complex models show multiscale sphere distributions that follow principal volumes and slender features. We further integrate ML-IST into the Jolt Physics and Bullet engines; in an alpha-puzzle benchmark it reaches 55.89~FPS, the highest among the compared representations (conventional IST, GImpact, and convex decomposition). These results support learned leaf generation as a practical component for fast, runtime construction of detailed collision representations.

The size of the KV cache grows linearly with context length, making it a major memory bottleneck in LLM serving. Motivated by recent progress in identifying the functional roles of attention heads, a growing body of work compresses the KV cache non-uniformly across heads. Existing methods either fix the important heads via offline profiling or select them using attention signals from the prefill stage. In both cases, however, accuracy fluctuates substantially across workloads. While investigating the cause of this instability, we find that the active heads shift between the prefill and decode stages even within a single input. Along the decode path, by contrast, the activehead composition remains stable across content tokens once format tokens are filtered out. Based on this observation, we propose PeekKV. PeekKV observes a single content token immediately after prefill - a one-token peek - to jointly obtain head-group scores and token-importance scores. Guided by these scores, PeekKV allocates KV cache budgets to head groups in proportion to their group scores and retains only the top-scoring tokens within each budget. PeekKV requires no offline profiling or training and thus applies directly to unseen workloads and new models. Across four public benchmarks, PeekKV achieves the highest accuracy in more than half of the per-model comparisons against state-of-the-art methods, and stays closest to the full-cache accuracy on RULER and LongBench. On Llama-3.1-8B-Instruct, PeekKV retains 95.7% of the full-cache accuracy at a 10% memory budget on RULER with 16K contexts and 95.9% at a 1.5% budget on LongBench.

Driven by the growing integration of artificial intelligence and robotics in experimental science, we redefine the execution of user experiments at synchrotron soft X-ray beamlines by developing a highly automated end-station that can be operated without on-site staff. Installed at beamline BL08U of NanoTerasu, the system comprises four chamber units and two robots that automatically transfer samples from ambient air to an ultrahigh vacuum measurement stage for spectroscopic evaluations, before returning them to their original locations post-measurement. Soft X-ray absorption spectra are automatically acquired once programmed by scanning the micro-focused beam over the designated sample area, followed by automated evaluation using machine learning techniques such as principal-component analysis, multidimensional scaling, t-distributed stochastic neighbour embedding, and uniform manifold approximation and projection. The high-throughput data are systematically accumulated in the database for remote user examination. This unstaffed end-station provides efficient beamtime for users and allows beamline scientists/technicians to pursue more human and creative endeavors.

Recent latent reasoning methods move beyond discrete Chain-of-Thought (CoT) by replacing sampled tokens with continuous soft embeddings or hidden states, enabling richer intermediate representations and preserving alternative reasoning paths. However, the need for latent reasoning varies across decoding steps: confident predictions favor discrete commitment, whereas ambiguous steps benefit from preserving multiple plausible alternatives. Existing approaches typically handle this variation through either global soft activation or hard switching based on uncertainty thresholds, treating latent intervention as an all-or-nothing decision rather than continuously adapting its strength. To address this limitation, we propose Competitive Token Selection (CoTS), a training-free framework that reframes latent intervention from binary mode selection into continuous allocation at the token level. CoTS uses the probability competition between the two most likely candidates to dynamically balance discrete commitment and soft exploration at each reasoning step. The second candidate represents the strongest alternative to the model's preferred continuation, so the separation between the two directly reflects the stability of the current discrete choice. When one candidate clearly dominates, CoTS keeps the representation close to the sampled discrete token to preserve a stable reasoning trajectory; as the competition strengthens, it increases the contribution of the soft representation to retain plausible alternatives. This competition-based allocation requires neither manually tuned switching thresholds nor mixing coefficients, and introduces no additional forward passes. Experiments across six reasoning benchmarks demonstrate that CoTS consistently outperforms standard CoT and state-of-the-art training-free latent reasoning methods. Our code is available at https://github.com/OkinoYu/CoTSReasoning.

Post-route power recovery changes cell choices under tightly coupled timing, electrical and physical constraints, and the value of each change depends on what it costs to repair its side effects. We propose an AI-driven framework in which a learned model drives both phases of the optimization: it ranks the powerrecovery edits to try and the repair actions that follow, while deterministic electronic design automation (EDA) analyses govern every acceptance. The framework records baseline constraint margins, identifies the damage a recovery transaction introduces in each analysis view, holds pre-existing violations at their baseline rather than working them inside the power step, and caps repair spending at a fraction of the measured saving. An ensemble of gradient-boosted models predicts power change, normalized damage reduction and constraint-regression risk from action and timing-context features available before each trial; calibrated, conservative estimates feed separate acquisition scores for recovery and repair, with a deterministic fallback when the model is uncertain. Recovery and repair remain speculative until physical implementation and fresh analysis establish baseline preservation and positive net saving. We specify the contract, the learned policy, the transactional flow and a pre-registered public evaluation protocol on open designs. Evidence from a companion study on public designs supports the contract; the learned policy is proposed, and no trained-model results or proprietary design measurements are reported.

Estimating (heterogeneous) treatment effects is still challenging when the outcome is semicontinuous (i.e., exhibiting both a discrete point mass at zero and a skewed continuous distribution for positive values), despite the strong presence of this data type in real world settings. Existing methods either ignore the zero mass, impose fragile parametric assumptions, or suffer from extreme computational costs and data augmentation noise. This paper proposes Zero-Inflated Continuous Bayesian Causal Forests with Duan's Smearing (ZIC-BCF-Smear), a decoupled two-part nonparametric estimator that fits a Probit BCF on the full sample to model participation and a Gaussian BCF strictly on the active subpopulation to model positive intensity. Subpopulation Propensity Adjustment (SPA) mitigates regularization-induced confounding within the active subpopulation, and Duan's non-parametric smearing estimator re-transforms predictions to the response scale, bypassing the fragile scale multipliers of parametric models. A comprehensive simulation benchmark shows that ZIC-BCF-Smear matches well-specified parametric models without their assumptions and remains stable and calibrated where competitors either diverge or pathologically over-cover for nonlinear data. The method is then applied to individual-participant data from the SPECTRUM randomized phase III head-and-neck cancer trial, estimating the causal effect of assignment to panitumumab plus chemotherapy on the number of days patients spend with severe toxicity, an outcome for which a quarter of patients contribute an exact zero. Panitumumab assignment raises that burden by about ten days per patient under the trial's own differential treatment duration, and the decoupled structure localizes the effect mainly in the positive-intensity part rather than in whether the reconstructed severe-AE burden is positive.

We construct nonnegative bounded compactly supported functions on the real line that give the lower bound $\mathcal{A}\ge 0.4103779774321214877852987\ldots$ for the minimum-autocorrelation constant. This improves the explicitly certified bound $2378625/5958277=0.39921356\ldots$ reported by Russell. The construction combines a point mass with a monotone degree-ten polynomial density; a one-sided atom-removal argument then produces ordinary functions. Its numerical content reduces to exact rational polynomial identities and 20 Bernstein subinterval certificates. The finite certificate, actual overlap integrals, admissibility, mass formula, and ordinary-function witness bounds have been formalized in Lean 4.19.0; the pinned proof sources and recorded audit are supplied. The passage to the supremum constant is given separately as a mathematical argument. As applications, the same construction yields an upper bound below $1.5610183$ for the large-multiplicity generalized-difference-basis coefficient and a feasible squared mass below $2.436778$ for a continuous sparse-ruler relaxation. An appendix quantifies the loss under independent sampling followed by completion. No improved bound for the complete sparse ruler constant, or global optimality of the construction, is asserted.

Sierra and Townsend (ST) [1] showed that the “absorption spectrum” model of Connes [2] arises as the lowest-Landau-level (LLL) limit of a charged particle in crossed electric and magnetic fields, and suggested that the higher Landau levels supply the fluctuation part of the Riemann-zero counting function $N(E)$. Within the approximation used by ST we construct the eigenfunctions of an arbitrary Landau level $n$ and derive their asymptotics at the two box boundaries that ST identify. The boundary condition is the same as for $n=0$ up to an $E$-independent phase $(-\ii)^n$, so no $\ln E$ term arises for any fixed $n$. We also note that the $\ln E$ term in the semiclassical Eq.~(29) of ST is the first-order shift of the smooth LLL counting function, $E\to E+\gamma z^2$.

Using the spectral relation between irreducible cyclic codes (ICC) and generalized Paley (GP) graphs recently found by the authors, we study the weight distribution of irreducible cyclic codes of length $2^\ell$, $\ell \in \mathbb{N}$. These codes were previously studied by Sharma, Bakshi and Raka, who divided them into two families (each having two cases). First we characterize the GP-graphs spectrally related to these families of ICCs: they are complete, semiprimitive, Hamming, or Cartesian products of semiprimitive GP-graphs. We then compute the spectrum of these graphs and hence, by the mentioned spectral relation we finally obtain neat explicit expressions for the weight enumerators of all the irreducible cyclic codes of length $2^\ell$ with $\ell \in \mathbb{N}$.

Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded decisions that respect robot embodiment, workspace geometry, reachability, collision constraints, and grasp feasibility. This paper presents a hardware-aware large language model-vision-language model (LLM-VLM) manipulation framework for a simulated Franka Research 3 robot in NVIDIA Isaac Sim. The framework separates symbolic reasoning from metric execution: an API-hosted LLM planner receives a structured scene summary and generates only symbolic task information, including the object to manipulate, target relation, approach preference, and objects to avoid. A local Qwen3-VL 8B VLM verifier supports semantic confirmation of ambiguous objects and open-container surrogates. Both the LLM planner and the VLM verifier are prohibited from generating robot coordinates, grasp poses, keepout dimensions, gripper commands, trajectory waypoints, or success labels. Instead, these decisions are handled by deterministic grounding and execution modules that use the robot model, scene geometry, MoveIt 2 collision checking, inverse kinematics, grasp validation, release verification, and final visual assessment. Execution feedback is returned only as symbolic context for replanning. The framework is evaluated through simulated digital-twin trials involving pickup, occluded-source access, keepout reasoning, relation placement, and sequential manipulation tasks.

Accurate artery extraction from X-ray coronary angiography (XCA) is essential for coronary artery disease diagnosis and intervention. However, low vessel visibility, respiratory and cardiac motion, and limited annotations challenge existing methods. Moreover, most deep learning approaches produce binary vessel masks without preserving clinically relevant intra-arterial contrast information. We propose a Temporal Diffusion Bridge Model (TDBM) that formulates vessel extraction as image translation and learns from physics-informed synthetic data without manual vessel annotations. A physics-based XCA synthesis engine generates diverse, perfectly aligned pairs of contrast-enhanced and contrast-free images. Using these pairs, TDBM learns cross-domain mappings to recover high-fidelity vessel information. Temporal conditioning incorporates adjacent frames to improve consistency, while a vessel-aware contrastive loss exploits background-invariant synthetic pairs to enhance vascular discrimination. We evaluate TDBM on two XCA vessel segmentation datasets and conduct a reader study using two real-patient XCA sequence datasets. Zero-shot segmentation is further assessed on retinal imaging and fluorescence microscopy datasets. Results demonstrate that TDBM consistently outperforms existing methods and generalizes effectively across imaging modalities. Code and trained weights will be available at: https://github.com/Advanced-AI-in-Medicine-and-Physics-Lab/TDBM

Setting up, running, and assessing a computational fluid dynamics (CFD) simulation requires substantial manual effort, from meshing and solver setup to diagnosis and interpretation, and repeating it across design variants slows engineering iteration. We present CFD Forge, an agentic framework built around OpenFOAM that carries an engineering request through case construction, meshing, solver execution, diagnostics, and reporting. A large language model interprets the request, reads the simulation evidence, identifies likely causes of problems, and proposes actions from a closed set. Automation is only useful if its results can be trusted, so acceptance is not left to the model: deterministic checks, registered for each type of flow, measure explicit criteria and decide. We demonstrate the framework on a converging-diverging nozzle and a two-dimensional forward-facing step, including geometry and operating changes requested in text. A turbulent cube, run outside the agent loop, shows why the checks matter: the solver completed and the mean drag settled, but the lateral-force oscillations were still growing, so a retrospective assessment withheld acceptance. To test this separation, we replayed 36 recorded simulation states, some with deliberately altered diagnostics, through the same model in two setups. Judging from the evidence without the check results, the model accepted 12 of the 13 detectable faults in all three repeats; with CFD Forge's checks deciding, none was accepted. The two setups also differ in prompting, and a fixed rule reached the same verdicts, so the model's value lies in the open-ended work rather than the verdict. Case files, recorded model calls, and decisions are retained for audit. A model that does the work, paired with checks that decide what is accepted, is a step toward automated CFD that can be trusted in high-throughput design and active-learning loops.

This paper presents a case study on using Google AI Studio (version Pro) to vibe code a medium-complexity software application by a non-programmer who, moreover, needs it in a language other than English. We prove that, on one hand, almost anybody can successfully vibe code, not only developers, even if you do not speak or understand English, and, on the other, that although such a top AI product can build a reasonable approximation of a fine database software application, vibe coding still needs thorough testing, as even if the initial specification documentation is crystal clear and almost exhaustive, the resulting app may exhibit bugs and not that intelligent development decisions.

Sparse-view cone-beam computed tomography (CBCT) is severely under-constrained by limited X-ray projections. Learned reconstruction can provide complementary anatomical information, but using it as a prior in patient-specific Gaussian reconstruction introduces two challenges. First, the discrepancy between the learned prior and current reconstruction is spatially non-uniform: some local differences contain useful missing 3D information, whereas others reflect prior bias. Second, even a volumetrically beneficial correction can conflict with the observed X-ray measurements. Since X-ray measurements are line integrals, spatially separated corrections may affect overlapping rays, with their signed projection responses reinforcing or partially canceling in the measurement residual, so their feasibility cannot always be assessed independently. In this paper, we introduce RePrior, a multi-stage progressive prior-correction framework that addresses correction actionability, measurement feasibility, and representation expressivity. Selective Correction Proposal (SCP) first identifies actionable signed local corrections from prior–reconstruction discrepancies. Measurement-Constrained Reconciliation (MCR) then jointly enforces their consistency with patient-specific X-ray measurements, while Hybrid Residual Enhancement (HRE) recovers additional correction capacity through complementary voxel- and Gaussian-domain degrees of freedom around the reconciled anchor. RePrior requires neither test-time ground truth nor case-specific network fine-tuning. RePrior gains approximately 2.6~dB in 3D PSNR over R$^2$-Gaussian across LUNA16, PANORAMA, and PENGWIN. Beyond prior-assisted reconstruction, it delivers additional gains in volumetric quality and observed-view projection fidelity, with consistent gains in held-out-view fidelity in the backbone-matched evaluation.

We present Fin_Agent, our submission to the FinEval 2026 shared task on multilingual fi nancial language understanding. Our sys tems address Greek financial named-entity recognition, Japanese implicit communication recognition, and multilingual financial ques tion answering. For Greek NER, we com bine annotation-aware numeric rules with zero shot Qwen2.5-32B classification, achieving 0.9521 public F1 and 0.8884 private F1. For Japanese implicit communication, an inter pretable cue-based ordinal scorer achieves 98.0% test accuracy. For multilingual financial QA, BGE-M3retrieval with Qwen3-32B gen eration achieves 0.3023 and 0.3419 ROUGE-1 F1 on the public and private splits. Key limita tions include dataset-specific rules, handcrafted cues, and limited supervision. Implementa tion code is available https://github.com/ Rashidnira/finagent-fineval-2026.

Let $\Lambda_n$ be the set of all eigenvalues of standardized Laplacian matrices of order $n$, equivalently, of stochastic $n\times n$ matrices with off-diagonal entries at most $\frac1n$. In 2005, a polygon $S_n\subseteq\Lambda_n$ was constructed, and it was conjectured that $\Lambda_n=S_n$; this holds for $n\le3$. We show that the conjecture fails for every $n\ge5$. The vertices of $S_n$ are eigenvalues of circulant Laplacians built from powers of the directed $n$-cycle. To first order, no perturbation of these circulants moves such an eigenvalue out of $S_n$; however, adding chords with nonconstant weights moves it along an edge of $S_n$ to first order and, with an explicit coefficient, beyond the supporting line of this edge to second order. Consequently, every edge of $S_n$ not incident to $0$ or $1$ contains interior points of $\Lambda_n$, except possibly, for even $n$, the two horizontal edges, whereas the four edges incident to $0$ or $1$ lie on $\partial\Lambda_n$. For $n=4$, whose only other edges are horizontal, the question remains open. We certify an explicit weighted counterexample for $n=5$, lying only $1.5\cdot10^{-3}$ outside $S_5$, and an unweighted one for $n=7$: the directed $6$-cycle with a duplicated vertex. Its eigenvalue outside $S_7$ is also an eigenvalue of the two-chord digraph that ends the above perturbation; for the analogous digraphs of order $n$, the excess is asymptotic to $\frac{\pi^2}{2n^4}$. We also observe that $S_n$ is a zonotope, describe $\Lambda_n$ in terms of eigenvectors, and prove that $S_m\subseteq S_n$ whenever $m\mid n$.

A geometric $(n_4)$ configuration is a set of $n$ points and $n$ lines in the real projective plane such that every point lies on exactly four of the lines and every line contains exactly four of the points. The question of which $n$ admit such a configuration was posed by Grünbaum in 2000, and successive work of Bokowski, Grünbaum, Schewe, Pilaud and Cuntz settled every case but $n=23$. We settle this last case by bounding the symmetry of such configurations and classifying the most symmetric ones exactly. We prove that for every prime $n\equiv3\pmod4$ the group of projective symmetries of a geometric $(n_4)$ configuration has order at most four, explaining why symmetric constructions failed at $n=23$, and the same argument bounds the symmetry of $(n_5)$ configurations for primes $n\not\equiv1\pmod5$. Reducing the Klein four-group case to 4021 bilinear polynomial systems and solving all of them exactly with Gröbner bases, we show that exactly two $(23_4)$ configurations reach this bound up to projective equivalence and that there are no others even over $\mathbb{C}$. Both are self-polar; the first has integer coordinates and the second is defined over $\mathbb{Q}(\sqrt{17})$ but not over $\mathbb{Q}$. Consequently geometric $(n_4)$ configurations exist if and only if $n\ge18$ and $n\ne19$. The same classification recovers Cuntz's $(22_4)$ and $(26_4)$ configurations and finds three new combinatorial types at $n=22$ and $94$ at $n=26$. Among self-polar $(23_4)$ configurations with a single involution we find $50$ more, defined over number fields of degree at most $7$. Four of them deform in one-parameter families, and computing three of these exactly, one birational to the modular curve $X_1(11)$, we prove that there are infinitely many geometric $(23_4)$ configurations, among them infinitely many with rational coordinates that are self-polar and have no projective symmetry.

Facade articulation at building scale is usually resolved manually or through parametric systems that encode design intent as explicit rules. This paper investigates a complementary workflow in which a designer-authored prototype supplies transferable articulation logic. Prototype and target massing are represented as heterogeneous attributed graphs, and a Siamese graph attention network with instance-local triplet supervision embeds their segments in a shared metric space. Many-to-one nearest-neighbor retrieval then routes prototype Patterns to the larger target. On the original 85/15 within-corpus holdout, prototype-to-massing top-1 accuracy reached 96.5%, compared with a reported 76.5% raw-feature baseline. A Rhino demonstrator converts predicted correspondence into reusable facade Patterns, and qualitative applications on four built projects show the workflow across distinct massing organizations. The contribution is not automated facade generation, but an authoring model in which resolved geometry serves as a computational specification for project-scale propagation.

High-dimensional sparse recipe formulation in process industries involves nonlinear association of various covariates, bounded by sparsity constraints and multi-criteria tolerances. Traditional physics-based classical methods (such as Kubelka-Munk) fail to generate sparse candidate recipes properly due to their simplified assumptions and industrial process variations. This study proposes a hybrid physics-informed uncertainty-aware framework that is structured into three modules: (a) Module A, a multi-target forward quality model; (b) Module B, a sparse inverse reconstructor; and (c) Module C, a feasibility-constrained ranking layer. Then it has been validated in an industrial textile dyeing context with recipe-grouped cross-validation under multi-illuminant quality assessment comprising process and production information, target reflectance, K/S values, and spectral descriptors. Histogram Gradient Boosting (HGB) with spectral-only features ($R_\lambda$, K/S) and Gradient Boosting Regressor (GBDT) with recipe-process features outperforms other configurations with out-of-Fold MAE of 0.1655 and 0.1523 in the forward quality model. For inverse reconstruction, a component-wise median blend achieved a recipe-vector MAE of 0.0295. Exploratory conditional treatment effect (CATE) suggests an observational association that alkali adjustment reduces error for red and pale shades (CATE = -0.196). This framework provides a human-in-the-loop decision-support tool that minimizes costly laboratory trials across industrial formulation domains.

Coding agents increasingly interact with users by generating interactive software on the fly rather than replying in text, yet many bugs in such software reveal themselves only after multi-step interactions. Today, users must discover these bugs and wait for fixes, making the development loop slow and expensive. Existing benchmarks typically assume the bugs have already been identified, leaving agents' ability to find interaction-dependent failures largely unevaluated. We introduce SWEeper-Bench, 200 tasks built from real bug fixes in 200 widely used open-source web applications. Each task gives the agent only the codebase and an open-ended request such as "Find and fix issues in Focalboard's board sharing and membership." Because these bugs are hard to detect from code alone, agents must design interactive tests to uncover them. An agentic verifier then judges each repair by what a user would observe in the browser. The best of 15 frontier agents passes only 59.0% of tasks. Through stage-by-stage analysis of agent trajectories, we show that the biggest bottleneck is identifying the buggy behavior: agents often reach the relevant feature but never trigger the failure or fail to recognize it. SWEeper-Bench measures progress toward agents that close this loop themselves, delivering software that works without waiting for user feedback.

Importance: The search for reliable neuroimaging biomarkers of mental disorders has remained elusive despite decades of research. Why clinically consequential disorders yield weak neuroimaging separability remains unresolved. Drawing on statistical thermodynamics and the metabolic costs of neural coding, we propose that psychiatric disorders produce constrained deformations of a largely shared repertoire of brain activity patterns, limiting the class-specific information available for classification. Observations: We develop a framework linking physical resource constraints, landscape deformation, distributional separation, and attainable classification, and examine its components using human neuroimaging, synthetic data, and an exactly specified physical model. In resting-state fMRI from 1952 FOR2107 participants (823 with major depressive disorder; 1129 healthy controls), held-out energy-landscape estimates and nonlinear classifiers agreed across 13 comparisons (r = 0.996). Similar results emerged at both FOR2107 centers and in 900 SRPBS participants spanning multiple psychiatric diagnoses. In synthetic data, classification improved with distributional separation and approached the optimum. In an equilibrium three-well model, statistical energy equaled physical potential energy scaled by inverse temperature. Modest deformation redistributed state occupancy while optimal snapshot classification remained weak. A literature map found insufficiently comparable evidence to test the human metabolic constraint. Conclusions: Clinically consequential differences may arise within a largely shared neural repertoire. The thermodynamic framework connects physical deformation to classification under specified assumptions; its metabolic implementation in humans remains untested. Testing this mechanism requires joint measurements of brain activity, bodily physiology, and metabolism.

Existing jailbreak attacks have exposed serious safety weaknesses in multimodal large language models (MLLMs). Most prior attacks rely on specially constructed visual inputs to carry or support harmful intent. In this paper, we uncover a different vulnerability: task-relevant scene semantics alone can shift an MLLM from refusal to compliance, even when the visual input introduces no additional attack instructions and the original task intent remains unchanged. We formalize this failure as a scene-grounded visual safety vulnerability and introduce SceneSafetyBench to investigate it across eight risk categories and nine white- and black-box MLLMs. Our analysis reveals that this failure is associated with how task-relevant visual evidence influences downstream safety representations, suggesting that visual grounding alone cannot fully explain the observed safety shift. Building on this finding, we propose Scene-Grounded Attacks (SGA), which preserve the original task while constructing validated scene-grounded queries and combining their independent responses. Across nine target MLLMs, SGA achieves an average attack success rate (ASR) of 86.17%, outperforming the strongest baseline by 8.55 percentage points and achieving the highest ASR on eight models. Our results identify scene semantics as an overlooked attack surface in MLLMs and highlight a growing tension between stronger visual grounding and robust multimodal safety alignment.

Despite advancements in sub-pixel decoding, modern Human Pose Estimation (HPE) architectures remain constrained by deterministic coordinate extraction from discrete heatmaps, which systematically fails under dense occlusions and Out-of-Distribution (OoD) ambiguities. To address these limitations, we propose a post-hoc continuous probabilistic framework that intercepts raw heatmaps and models them as a Gaussian Mixture Model (GMM) augmented with a spatially agnostic uniform distribution, requiring no architectural modifications or retraining. This continuous representation allows us to comprehensively explore the distinct contributions of density modeling to HPE. We show that the spatial expectation of our fitted GMM achieves precision parity with leading sub-pixel decoders without heuristic post-processing. Leveraging this continuous space, our test-time augmentation aggregates probability distributions rather than discrete activations, mitigating multi-scale heatmap poisoning. Furthermore, because our multimodal GMM parameterization isolates competing spatial hypotheses, it naturally interfaces with geometric regularizers such as Markov Random Fields. However, our analysis exposes the inherent vulnerabilities of 2D kinematic priors under perspective foreshortening and visual degradation. Crucially, this density formulation yields significant improvements in uncertainty quantification: our calibrated geometric covariance volume outperforms standard peak-intensity heuristics in OoD anomaly detection under severe occlusion. For in-distribution calibration, dynamically fusing our geometric metric via Adaptive Softmax reduces or matches baseline Area Under the Sparsification Error (AUSE) across benchmarks and degradation levels. Finally, we establish that this continuous parameterization is extensible to multi-view 3D architectures, bypassing the $\mathcal{O}(N^3)$ voxel memory bottleneck.

Liquid Haskell is an extension of the Glasgow Haskell compiler (GHC) that adds support for refinement types: types restricted by logical predicates. Specifications are automatically checked by an SMT solver, thus offering lightweight verification directly within the language. However, the necessarily large trusted codebase behind Liquid Haskell (from GHC to the SMT solver to the refinement typechecker itself) raises the question of trust in the verification and the necessity for a formalized semantics of Liquid Haskell linked to its implementation. Grounding Liquid Haskell in theory is complicated by the interaction between two semantic levels in the language: a computational one and a logical one (for refinement predicates). While both are well understood separately, their interaction is subtle and has only been partially described. We give a semantics to Liquid Haskell by translation to Rocq. Both the computational and logical parts are translated to the same language, with a well-understood semantics; our translation makes the discrepancy between the two semantic levels explicit. The translation is implemented in Haskell and comes with a Rocq library that includes powerful proof automation standing in for the SMT solver. Thus, on the practical level, our tool Lava serves as a certificate checker for the supported subset of Liquid Haskell.