Computer Science (arXiv)

An increasing number of scholars use AI to measure variables they subsequently include in downstream analyses. Although AI-measured variables are often analyzed as if observed without error, ignoring prediction errors in automated measurement leads to substantial bias and invalid confidence intervals in downstream analyses, even if AI measurement accuracy is high, e.g., above 90%. Existing solutions, such as design-based supervised learning and prediction-powered inference, combine error-prone AI-based measurements with gold-standard labels, which may be costly and difficult to obtain in some application areas. In this paper, we propose debiased inference with multiple imperfect measurements (DMM), a framework that combines multiple error-prone AI measurements to enable valid downstream inference without gold-standard labels. Building on the established results on CP decomposition, DMM assumes that these measurements are independent conditional on the latent true label and observed unit-level features, such as text features represented by embeddings. This framework allows for unknown misclassification rates to vary across annotation methods (e.g., large language models) and across units of annotation (e.g., texts). Under this assumption, we use semiparametric inference theory to prove that the DMM estimator is consistent and asymptotically normal, enabling valid inference for a wide range of downstream statistical analyses common in the social sciences. Our simulation results show that DMM yields valid inference and that adding accurate, though imperfect, measurements can improve efficiency. Focusing on common applications of large language model annotations, we also develop diagnostics to assess the conditional independence assumption.

Consider a robot guide dog escorting a blind user to an available seat while a second assistive robot dog concurrently retrieves a cup of coffee and delivers it to the same seat. This setting motivates concurrent execution because navigation and object retrieval can overlap. A syntactically valid Large Language Model (LLM) plan may still violate embodiment constraints, and successful-looking controller motion does not by itself establish task completion. We introduce \textsc{GuideFetch}, a coordination framework for concurrent navigation and object retrieval by a heterogeneous guider and fetcher team. An LLM instantiates a schedule-conditioned four-action schema from a natural-language instruction. Before execution, robot, skill, and target aliases are normalized, and proposed actions are validated against registered targets, robot capabilities, and the selected schedule. Robot and object states then govern sequential and parallel execution. In a matched $2\times2$ study across 90 combinations of scene and seed (360 executions), all 180 online LLM responses validate without fallback or replay and match the corresponding scripted plans. For each planner source, sequential and parallel execution achieve $72/90$ and $71/90$ operational successes, respectively. Among the 56 cases completed by both schedules, parallel execution reduces mean makespan by 41.3\%. Within this controlled setting, role specialization and action overlap shorten completed missions, while state checks distinguish plan validity from verified mission completion. Source code will be available.

The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary solutions dominate commercial applications, a rapidly growing ecosystem of open-source Optical Character Recognition (OCR) engines, Large Language Models (LLMs), and Vision-Language Models (VLMs) offers accessible alternatives. However, systematic evaluations on realistic, multi-step extraction pipelines remain scarce. Responsible usage of such extraction tools require comprehensive evaluations on realistic tasks, especially as these solutions will be key components of applications in the public sector that the EU AI act categorizes as high risk. To address this gap we present a comprehensive benchmark assessing the end-to-end performance of open-source systems on a complex real-world document processing task classified as high risk: Student applications for an international study program. We conduct a comprehensive empirical evaluation with state-of-the-art OCR engines, LLMs and VLMs. Our results reveal that while VLMs generally outperform OCR+LLM pipelines, even state-of-the-art open-source models struggle to handle such tasks reliably in zero-shot settings. Only 4 of 35 configurations achieved F1 scores above 0.5, with the best OCR+LLM pipeline matching top VLM performance, though most OCR+LLM combinations performed substantially worse. Roughly 75\% of all configurations scored below 0.25. Model scale influences performance, yet the relationship is non-linear: substantially larger models do not guarantee proportionally better results. Input quality, particularly the structural preservation of OCR output, emerges as a critical factor independent of downstream model capability.

Anytime solvers return usable solutions before they terminate and improve them while time remains. Their progress is commonly summarized by a primal integral, a final gap, or convergence curves. Each summary leaves consequential choices open: how to score a run before its first feasible solution, whether poor incumbents are truncated, and whether the reference value is updated after the experiment or version-frozen beforehand. These choices become visible when runs produce no valid incumbent or improve a published best-known value. We study a normalized signed primal integral built from a bounded relative gap. It assigns an intrinsic worst value to an empty run, requires no acceptance threshold, and assigns negative instantaneous gaps to incumbents that beat a frozen reference. We compare the smooth difference-over-sum kernel with a signed version of Berthold's max-normalized gap and use the former as a working default. We also distinguish analysis-time from version-frozen reference policies and recommend reading the score with the raw final gap, mean convergence curve, and target-attainment curve. We evaluate these choices on a five-arm routing campaign and two model-fidelity ladders. The two signed kernels preserve every panel ordering in this study, whereas a common acceptance threshold compresses the distances between arms and reverses one panel ordering. Updating 54 of the 212 reference values changes score levels and removes all negative scores, while leaving the observed panel orderings unchanged. An exploratory screen also identifies nine panel comparisons in which similar integral scores conceal materially different endpoints or attainment rates. The implementation, frozen inputs, and generators are openly released.

3D scene representation techniques such as neural radiance fields (NeRFs) and Gaussian splatting have made substantial progress in novel view synthesis, achieving high-quality renderings from arbitrary view angles. More recently, such techniques have been extended to dynamic 3D scenes; however, achieving sustainable online free-viewpoint video (FVV) streaming remains challenging, especially for longer videos, due to significant storage demands of detailed scene representations and high reconstruction/rendering speed needs. To address these challenges, we propose Quantized Anchored Residual Coding Gaussian Streaming (QuARC-GS), a quantization-aware 4D scene optimization framework for online dynamic scene reconstruction that achieves ultra-high compression while maintaining reconstruction speed and quality. QuARC-GS represents a scene using a single canonical frame and highly compressed per-frame residuals. Specifically, we compress each residual through two complementary strategies targeting motion, appearance, and densification. We introduce quantization-aware anchor deformation, which suppresses insignificant motion updates while preserving meaningful deformations, maintaining reconstruction quality under low-storage streaming. Furthermore, we design a change-gated densification strategy that allocates new Gaussians only in regions exhibiting genuine temporal changes, effectively eliminating redundant appearance updates and reducing storage overhead. Extensive experiments on widely used datasets demonstrate that QuARC-GS enables competitive reconstruction quality and training speed while cutting per-frame storage by up to 11$\times$ compared to the state-of-the-art.

Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting agents under uncertainty, with a wide range of applications. Existing numerical and deep-learning methods solve one MFC problem instance at a time and must be re-optimized whenever the task changes. In this work, we formulate stochastic MFC as an operator-learning problem and develop, to the best of our knowledge, the first mesh-free, self-supervised neural operator for stochastic MFC. The main challenge is that the diffusion term in the controlled Fokker--Planck equation precludes deterministic transport-map representations. We address this challenge by combining the probability-flow ODE with an invertible normalizing-flow-based transformer, which recasts the dynamics as a deterministic continuity equation and enables closed-form score evaluation through the exact inverse and analytical log-determinant of the normalizing flow, with $\mathcal{O}(d)$ cost per particle for networks of fixed size. Through transformer-based in-context learning, task prompts, represented by compact distribution parameters or raw particle clouds, condition the transport map, enabling a single pretrained operator to solve unseen tasks in one forward pass. The resulting \emph{Normalizing Flow Invertible Solution Transformer} (NFIST) is trained end-to-end by minimizing the stochastic control objective directly, requiring no precomputed numerical solutions for training. We further prove the consistency of the proposed operator-learning formulation with task-by-task optimization. Numerical experiments on stochastic optimal control, Schrödinger bridge, systemic-risk control, and obstacle-avoiding path planning demonstrate effective zero-shot generalization while substantially reducing the computational cost of solving large families of stochastic MFC problems.

Background. Advances in agentic systems are simultaneously, and rapidly, saturating benchmarks. Despite this often discussed phenomena, benchmark scores remain difficult to interpret due to the lack of control and characterization of task difficulty. More specifically, we currently have little understanding of what makes one task harder than another, and to what extent task difficulty is predictable from static task properties. Aims. We propose a measurement framework to investigate and systematically quantify what structural properties of software tasks correspond to agent success rates for issue resolution tasks. Method. We conducted a large scale empirical study on CoderForge-Preview, the largest open dataset of coding agent trajectories to date, by extracting features across task patch, repository and prompt. We evaluated the predictive power of each feature against task outcomes using ensemble methods, SHAP attribution, and effect size analysis. Results We found that task difficulty is substantially predictable from static features (AU C = 0.863) and is largely driven by patch fragmentation and repository scale. Prompt linguistic features become visible among top contributors for tasks in the mid-band, revealing a layered structure of difficulty. Conclusion. The difficulty of an issue resolution task is encoded in its structure. This enables static, pre-hoc difficulty estimation and lays the groundwork for difficulty-controlled benchmark construction for evaluation of agents.

Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal reasoning capabilities. This review surveys how Large Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of multimodal foundation models with physical perception capabilities. In this vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.

OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text. The model is derived from an autoregressively pretrained checkpoint and converted into a bidirectional, banded-attention classifier that labels an input sequence in a single forward pass. A constrained Viterbi decoder produces coherent spans across eight privacy categories and exposes configurable operating points for precision-recall tradeoffs. Privacy Filter has 1.5 billion total parameters, 50 million active parameters per token, and a 128,000-token context window. It is designed for efficient local deployment and domain-specific fine-tuning. Privacy Filter is intended as a configurable data-minimization component within layered privacy workflows, not as an anonymization or compliance guarantee.

Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial and error can explore systematically. Deep-learning methods encode the reconstruction rules in learned weights rather than in an explicit operator that can be inspected and modified. We propose SeisEvo (Seismic Algorithm Evolution), which does not optimize a single reconstruction result but searches for the algorithm that produces it. Starting from a classical reconstruction algorithm, an LLM-driven multi-agent search modifies only the components that the user has opened for editing, without prescribing the mechanism to be discovered. Candidates that violate the physical constraints of the task are rejected outright, and the remaining ones are scored by execution. The output is neither an agent system nor a neural network, but a standalone white-box algorithm that requires no agent or neural network at inference time. For interpolation without added noise, the search discovered a residual-gated, phase-aligned dip-consistency projection; Evo-POCS improves the SNR over classic POCS by 3.49 dB on average across missing ratios from 30% to 70%. For simultaneous interpolation and denoising, it discovered a reliability-grouped singular-value shrinkage; Evo-MSSA improves the average reconstruction SNR by more than 7 dB over classic MSSA and by more than 3 dB over a stronger rank-reduction baseline. Both operators retain their gains on data not used during the search. To the best of our knowledge, this is the first study to formulate the design of a seismic reconstruction operator as a constrained, LLM-driven program evolution task. Agentic algorithm evolution can thus complement deep learning in discovering explicit, inspectable, and deployable seismic processing algorithms.

On-policy self-distillation (OPSD) trains a student on its own responses using token-level supervision from the same model conditioned on privileged reference information. We investigate whether performance gains from OPSD show that the student learned the information in the reference or instead reflect recovery of reasoning behavior already present in the base model. We perform OPSD experiments on science and mathematics datasets using Qwen3 models ranging from 1.7B to 8B. Our analysis framework separates the supervision induced by the reference from the supervision provided by the teacher without the reference and measures how each aligns with changes in the student's predictions. The correct reference does not provide a consistent performance benefit across teacher generation modes, model sizes, and training datasets. Students can improve without the correct reference, and a solution from another problem can outperform the correct solution on several mathematical reasoning benchmarks. The student's predictions align more strongly with the base model's thinking behavior than with the supervision induced by the reference, but controls constructed from other problems reproduce much of both alignments. Moreover, stronger alignment attributable to the correct reference does not reliably coincide with a greater performance benefit from the reference. Performance gains and distributional alignment alone therefore cannot determine how privileged reference information contributes to student learning in OPSD.

Reliable tool--tissue contact detection can support interaction-aware control and downstream force estimation in robot-assisted surgery. Most existing methods learn a contact classifier from RGB appearance, which is hard to generalize. In this work, we use the depth image generated from a stereo pair to give more information about tool--tissue contact. For each depth frame, we localize a spatially supported minimum-distance patch around the tool boundary and reduce it to a single scalar, $-\log_{10}|d|$; this signal rises and falls in step with ground-truth contact. We formalize this observation with a fully supervised two-state hidden Markov model. We fit this model as a six-fold leave-one-session-out (LOSO) ensemble on six palpation sessions against a single silicone cup-like phantom, with the decision threshold selected from the pooled out-of-fold predictions. It is evaluated on four held-out sessions of three categories: 1. same task on same phantom; 2. same task on different phantom; 3. different task on different phantom. This model reaches held-out macro F1 $0.927$ and AUPRC $0.980$. We further compare against a reproduction of an RGB-based contact classifier from prior work. This RGB-based model achieves high performance on the first category (F1 $0.965$), but substantially lower performance on the other two, resulting in macro F1 $0.320$ across all four sessions. These results indicate that the tool--tissue distance is a strong, transferable cue for contact detection in robot-assisted surgery.

Today most media content is consumed based on algorithmic recommendations. Evidence suggests that this can lead to politically biased media consumption patterns. Automated extraction of political agendas from texts can reveal and analyze political biases in online media -- and thus help fostering politically unbiased media consumption. Here we employ modern political text analysis methods demonstrating the potential of automated fine-grained political bias analysis in online media. We conduct an analysis of political content in German language online media during the period 2019--2022, encompassing several million articles and tweets covering events with profound societal impact globally and nationally, the COVID-19 pandemic and the beginning of the war in Ukraine. Our analysis identifies thematic similarity between national (German and Swiss) reporting, particularly for categories driven by international events. We also find divergences emerging in domestically influenced categories, reflecting differences in national policies and institutional structures. A comparison of newspaper and Twitter discourse reveals that both media converge around a shared core during the pandemic, yet differ in intensity and temporal dynamics. Newspapers exhibit more stable political content, while Twitter reacts through short-lived event-driven spikes. These findings indicate that international crises act as a powerful synchronizing force on political content in classical media, temporarily overriding both national and media-form differences. Our automated political analysis empowers citizens by rendering political agendas in online media transparent. This transparency also enables media outlets to bridge the gap between algorithm-driven echo chambers and a more informed, balanced public discourse.

We introduce a general, easy-to-implement AI-based method for studying the structure and complexity of human behavior. We assign a large language model a ``type vector'' and then prompt it to choose actions across settings in which we observe human choices. For instance, the type vector (2,4) becomes ``You are a player characterized by the following profile: 2 out of 5 in Altruism, 4 out of 5 in Risk Aversion,'' after which it is prompted to make choices. We vary the dimensions (e.g., Altruism, Fairness, Trust, $\dots$) and values (e.g., 1--5) to minimize distance to human choices. Applying the method to 119,147 decisions made by 78,657 subjects from more than 35 countries across 10 classic economic game roles, we find that human behavior can be closely matched using three dimensions: Risk Aversion, Strategic Sophistication, and Trust. Moreover, the types needed to fit individuals across games cluster into fewer than a dozen groups, and can predict behavior in held-out games with different rules and available actions. The results suggest that behavior across diverse settings can be approximated by a low-dimensional, portable representation, supporting the possibility of general yet parsimonious theories across the behavioral sciences. More broadly, the method can provide insights into the structure of many human behaviors.

Traffic signal control is a complex sequential decision-making problem requiring real-time adaptation and trade-offs among throughput, delay fairness, signal stability, and emergency vehicle priority. Existing RL methods often fix objectives, ignore dynamic priority changes, and fail to generalize across geometrically similar intersections.We propose SIGMA (Symmetry-aware, Intelligent, Geometric, Multi-objective Adaptive traffic control), an RL framework enhanced with a large language model (LLM) for adaptive objective tuning and orientation-invariant learning. SIGMA converts natural-language emergency commands into priority vectors for a multi-objective actor-critic controller, avoiding manual reward engineering. Rotational augmentation improves transferability across four-way intersections, while offline-to-online learning ensures stable initialization and gradual adaptation to changing traffic.We define reliability properties covering emergency service levels, graceful degradation under LLM failures, and demand sensitivity, validated via bootstrap statistics. Evaluated in SUMO on four Kolkata-based urban intersections against fixed-time, actuated, and DQN controllers, SIGMA reduces average/emergency waiting times and queue lengths, and boosts throughput. Ablation studies confirm robustness to component failures and geometric rotations. Overall, SIGMA offers a reliable, language-guided, multi-objective traffic control system with statistical reliability assurance.

Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream each token's active experts from whichever tier holds them, and on consumer hardware most experts sit on an SSD far slower than RAM. We quantify this bandwidth wall on Qwen3-235B (Q4_K_M, 134 GB): measured decode is 0.44 tok/s warm, matching a bytes-per-token / bandwidth model, while a batching scheme that should amortize one disk sweep instead collapses at batch 32 from paging thrash. We build llama-moe-trace, a zero-surgery router-telemetry tool, and measure routing on Qwen3-30B: adjacent-token expert reuse is 2.0x chance, 95% of traffic uses 52.5% of experts, and an LRU cache of 13.4% of experts serves 66% of requests. We then ask whether cacheability is trainable: we pre-register training of 137M MoE language models with auxiliary locality and domain router losses, under joint criteria on cache-miss reduction and perplexity. The mechanism works (misses down up to 60%; a 99% static-pin hit rate) but every configuration fails the pre-registered <=1% perplexity gate -- miss reduction and quality are tightly coupled. Concurrent StickyMoE reports the same loss as near-free on single-domain sub-25M models; on multi-domain 137M we find the tax real. Our contribution is this pre-registered, stricter-criterion, multi-domain evaluation plus edge-serving measurements. A 340M rung shows the tax does not shrink with scale (it rises slightly). We further show training-free cache-aware rerouting stacks with trained locality -- together ~80% miss reduction at <=3.4% perplexity at both sizes, far cheaper than either alone -- while domain-primed prefetching does not help. All code, traces, and the pre-registration are released.

Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenges have become more urgent with novel EU legislation. Uncertainty around LLM usage with respect to privacy concerns in EU countries can be a major blocker for the speed of innovation and transfer from research to applications. Here we present \textbf{Redakto}, a tool that can be used for anonymizing text prior to feeding it to an LLM or other downstream text processing. We provide state-of-the-art functionalities for both redaction of PII but also when used for pseudonymization. These functionalities are exposed such that they can easily be used by end-users, through the Redakto web application, and by developers and researchers, via REST APIs and model context protocol (MCP) hooks. The implementation is fully open source, requires modest compute resources, and can be readily deployed on local hardware. In contrast to prior work and in order to better assess the quality of the anonymized texts, we conduct extensive empirical evaluations on textual data from legal and medical domain with respect to both privacy and utility of the redacted texts. Our empirical results demonstrate that the texts anonymized with different redaction strategies achieve utility scores on par with the original texts, suggesting that anonymization with Redakto can be used for LLM tasks without substantial negative impact for the tasks we explored.

Robot-Assisted Feeding (RAF) systems are essential for assisting individuals with disabilities or motor impairments in eating tasks. Manipulating granular food items, such as rice and beans, poses significant challenges due to their dynamic physical properties. Learning from human demonstrations offers a promising solution, but acquiring high-quality demonstrations is complex. To address this, we present VERAGMIL, a framework that combines a high-fidelity simulator with an intuitive Virtual Reality (VR) interface for recording demonstrations and supporting different imitation learning methods. VERAGMIL provides a realistic environment for training RAF systems to handle granular materials, including robots, sensors, and various food items with distinct physical characteristics. We evaluate VERAGMIL by training three imitation learning models, BC, BC-RNN, and BCQ, on granular scooping and transporting tasks using both VR interface and 3D space mouse demonstrations, comparing them with a human-expert baseline. The models are assessed on success rate, spillage, generalization to unseen food items, and task completion time. Results show that VR-based demonstrations significantly outperform 3D space mouse data, with BCQ achieving the best overall performance, particularly in reducing spillage and approaching human performance. These findings underscore the effectiveness of our framework for training RAF systems in granular material handling. The code for our framework is publicly available at: https://github.com/AmanuelErgogo/VERAGMIL.git.

Trajectory planning for autonomous driving requires both high-level reasoning and precise low-level control. Large Language Models (LLMs) offer semantic-rich planning capabilities, however, their application is limited by hallucinated reasoning, poor grounding in environment dynamics, and limited numerical precision in control. We propose GAPL (Grounded Action-effect Policy Learning), a unified framework that integrates LLM-based effect estimation, simulation-based effect grounding, and policy optimization into a closed-loop system. GAPL consists of three modules: (1) an LLM-based Effect Evaluator for structured multi-dimensional action-effect estimation; (2) a Simulation-based Effect Grounder that predicts dynamics-consistent effects from simulator rollouts; and (3) an Effect-Aware Decision Maker that grounds LLM effect estimates against simulation via a distiller to guide Proximal Policy Optimization (PPO)-based policy learning. Experiments on four Highway-env scenarios demonstrate that GAPL consistently outperforms baselines, achieving average reductions of {0.76, 0.86, 2.00} in collision rate, average displacement error (ADE), and final displacement error (FDE), and an average reward gain of 1.44.

Fine-grained wildlife re-identification remains a challenging area in research. Current state-of-the-art approaches apply a detection and re-identification pipeline. We propose a one-stage end-to-end detection and re-identification model that performs identity searching within the latent space. We adopt DINOv2 for robust spatial geometry and MegaDescriptor for wildlife re-identification. We enhance latent queries with prompt re-identification features. A detection decoder queries the scene latent space to establish object boundaries around the target identity. Preliminary findings reflect a competitive mean average precision score of 30.584% compared to the state-of-the-art two stage approach of 44.89%. Qualitative results depict effective bounding and identification of animal identities.

Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much better than neural responses predict model representations. This asymmetry raises the question of whether representational geometry contributes to bidirectional representational alignment. We hypothesized that steering representational geometry during training can systematically influence bidirectional alignment. To test this hypothesis, we developed a computational framework that integrates spectral regularization with bidirectional predictivity analyses. As an initial demonstration, we evaluated our framework using self-supervised contrastive vision models. Steering the spectral geometry of the learned representations substantially increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity. These improvements were accompanied by reduced effective dimensionality and a reorganization of the shared representational subspace, within which forward and reverse predictivity became approximately symmetric at intermediate spectral exponents. Overall, these findings demonstrate that representational geometry can be systematically steered to modulate bidirectional representational alignment between biological and artificial neural networks.

We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fixed-test-set benchmarks vulnerable to data contamination, ClosureBench generates instances on demand: each task's reference answer is computed by executing a program in the Ein tensor-logic language, ensuring machine-verified correctness. The benchmark spans 26 task categories at three compositional levels (L1-L3), with difficulty controlled along three independent axes: graph size, edge density, and query depth. We evaluate models from 1.5B open weights to frontier systems (o3, GPT-4.1, Gemini 2.5, Claude Sonnet 4) and report three findings. First, because the benchmark can always supply fresh instances, it measures memorisation directly: a model fine-tuned on a fixed test set shows a 19.3 percentage-point gap between its accuracy on seen and on fresh instances, which a static test set cannot reveal. We scope this to supervised fine-tuning on answer pairs, not pretraining contamination. Second, accuracy falls as graph size and query depth increase, and the two interact: models misread the graph from its natural-language description and then reason correctly over the wrong graph, so even the strongest frontier model degrades from atomic to compositional queries. This bottleneck is a property of the reasoning rather than the input format: it persists when the graph is given as a JSON edge list or an adjacency matrix instead of prose. Third, a 4B model fine-tuned to emit executable programs rather than answers stays nearly flat across compositional levels and approaches frontier accuracy (94.3% on held-out instances) at a fraction of the token cost. This holds for two program targets, Ein and Python+NetworkX, so it is a property of verified program synthesis rather than of one language.

We introduce and study an online variant of the multi-agent contract model. In our model, agents arrive one-by-one and are active with a certain probability. Upon arrival of agent $i$, the principal offers a linear contract $α_i$, specifying the fraction of the principal's reward transferred to agent $i$. Agents can either exert effort or not, incurring a cost if they do. The set of agents that exert effort determines the principal's expected reward through a reward function $f$. After all agents have arrived, the agents form a (pure) Nash equilibrium. As our main result we design an $O(1)$-competitive policy for submodular rewards, compared to the offline optimum. We also show that this result is tight in two ways. First, if we require that agents make decisions on the spot, then for submodular rewards any policy is $Ω((\log n)/(\log \log n)^2)$-competitive. Second, for the broader class of XOS (a.k.a., fractionally subadditive) rewards, any online policy is $Ω((\log \log n)/(\log \log \log n))$-competitive. The latter result reveals a surprising separation between submodular and XOS rewards: unlike related settings such as offline contract design and prophet inequalities, where constant-factor guarantees for submodular rewards extend to XOS rewards, the online contract setting separates the two classes.

Despite the rapid industrialization of the touch sensor manufacturing process, most of these sensors are still handmade in research laboratories. This complicates standardizing their performance, requiring the repetition of data collection and training models for each unit produced. To address this problem, this paper presents a method that can generalize the estimation of 3D force maps across different GelSight Mini sensor units, regardless of the sensor version. Specifically, the method consists of two stages: a domain adaptation stage, in which the input tactile image is reconstructed as a general tactile image using a UniT-based model; and a stage for estimating 3D force maps employing a U-Net network. Our proposal achieves promising results in both steps, such as an SSIM of 0.9338 +- 0.0358 in the image reconstruction phase and an MAE_F of 1.1294 +- 1.5934(N) in the force estimation phase.

Genomic analysis on viruses such as SARS-CoV-2 variants: Beta, Gamma, Delta, and Omicron is heavily dominated by classical bioinformatics methods, including Sequence Alignment, Phylogenetic Analysis, and Mutation Frequency Statistics. These approaches use pairwise codon or nucleotide distance matrices to analyze gene sequences, treating them as linear strings rather than capturing their complex contextual interdependencies. We proposed GenEx, a pipeline that converts raw gene sequences into codon co-occurrence graphs and extracts more than 25 graph features. Our two most prominent techniques for graph generation and feature extraction are MSCG (Multi-Scale Codon Co-occurrence Graph) and LAPCG (Linear-time Adjacency PMI Codon Graph). Using these algorithms, we treated codon sequences as structured symbolic vocabularies interpretable to codon co-occurrence graph analysis, a representational paradigm borrowed from computational linguistics. Another major contribution includes implementing a spectral graph feature extraction using Singular Value Decomposition (SVD), using the squared singular value ($σ^2$) instead of the traditionally used eigenvalue, which helped us to amplify the separation between dominant and subdominant spectral components, thereby enhancing inter-class separability in downstream classification. And to further demonstrate that our method works, we trained 23 benchmarked ML models against the latest SARS-CoV-2 variants, achieving remarkable results in detecting all SARS-CoV-2 variants.