Software Engineering
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Wednesday 12 August
In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU kernels. Recent advances show the potential of large language models (LLMs) to automatically generate Triton kernels, reducing the manual effort required from expert kernel developers. Several benchmarks evaluate LLM-generated Triton kernels. However, they suffer from three key limitations: (1) they restrict tasks to PyTorch-to-Triton translation, failing to reflect the diversity and complexity of real-world Triton tasks; (2) they evaluate only individual-kernel performance rather than end-to-end performance, the core criterion for real-world deployment in AI frameworks; and (3) they rely on manually written evaluation scripts for individual kernels, which may contain flaws that models can exploit to bypass correctness checks and obtain inflated scores. To address these limitations, we introduce RealisticTritonBench, the first benchmark to derive Triton kernel generation tasks from real-world pull requests in popular AI frameworks, enabling realistic, production-like evaluation. RealisticTritonBench systematically extracts PRs that modify Triton kernels from popular open-source AI frameworks and transforms them into generation tasks with concrete engineering contexts. Each task takes a natural language requirement as input and requires a corresponding Triton kernel implementation, with a complete and reproducible evaluation environment. Unlike prior benchmarks focused on isolated kernel performance, RealisticTritonBench integrates generated kernels into their original frameworks and evaluates them using end-to-end tests, enabling a more faithful assessment. We evaluate leading LLMs on RealisticTritonBench and find that they still struggle with real-world Triton kernel generation tasks.
Artificial Intelligence
CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations
While autonomous agents show promise for network operations, existing telecom troubleshooting evaluations fail to capture the partial observability and heterogeneity of real-world telecom environments. We introduce CTBench, a public benchmark evaluating agent troubleshooting capabilities in root cause analysis (RCA) and path restoration. Constructed by domain experts, CTBench features rich metadata and golden evidence trajectories, utilizing metrics that assess both final accuracy and diagnostic reasoning. Our evaluation of state-of-the-art agents reveals that while they excel at path endpoint identification, they severely underperform in RCA. Crucially, even when agents produce correct answers, they frequently fail to gather the requisite diagnostic evidence demanded in operational practice. Finally, we demonstrate that increased computational expenditure does not guarantee improved diagnostic competence, highlighting critical gaps in current agent capabilities.
Read the full abstract
Machine Learning
Remote Sensing and Machine Learning-Based Analysis of Land Use and Vegetation Change in Dhaka District, Bangladesh
Rapid urbanization in Dhaka District, Bangladesh has triggered substantial alterations in land use and environmental conditions, necessitating systematic monitoring for informed urban planning and ecological sustainability. This study employs remote sensing data and machine learning techniques to analyze spatiotemporal changes in land cover and vegetation dynamics between 2019 and 2024. High-resolution satellite imagery from Sentinel-2 MSI and Landsat 8 was utilized to classify land cover types and compute spectral indices including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and Normalized Difference Water Index (NDWI). A supervised machine learning approach incorporating Decision Tree, K-Nearest Neighbors (KNN), and Random Forest classifiers was applied using labeled geospatial training points within Google Earth Engine. Accuracy assessments were conducted using confusion matrices and kappa statistics. Results indicate a 59.5% increase in urban built-up areas and a significant decline in vegetation (-8.46%) and water bodies (-7.77%) over the five-year period. Land conversion from vegetated and aquatic areas to urban infrastructure was identified as a dominant trend. Among the models, Random Forest demonstrated the highest classification accuracy. These findings underscore the growing environmental pressures driven by unregulated urban expansion in Dhaka. The study highlights the potential of remote sensing and machine learning tools in providing timely, actionable data to support sustainable urban development, land-use regulation, and ecosystem conservation policies.
Read the full abstract
Machine Learning · Cross-listed from q-bio.NC
Beyond Local Power: Functional Connectivity Analysis for Subject-Independent Learning Style Recognition
Identifying individual learning styles optimizes pedagogical efficacy. While traditional questionnaires are structured, behavioral tracking methods require prolonged interaction log accumulation. To overcome these temporal constraints, this paper proposes an objective Electroencephalography (EEG) approach evaluating Phase Locking Value (PLV) connectivity against localized features across the Active-Reflective (AR) and Verbal-Visual (VV) Felder-Silverman dimensions. EEG signals were recorded from 28 participants during Raven's Advanced Progressive Matrices tasks. Support Vector Machine classification used Leave-One-Subject-Out Cross-Validation (LOSO-CV) alongside a 70:30 intra-subject split. The VV dimension achieved 70.00% subject-level accuracy driven by distinct fronto-occipital polarization. Conversely, the AR dimension yielded lower cross-subject generalizability (55.56%) due to overlapping executive networks and a "Systematic Neural Inversion" phenomenon, where stable individual connectivity signatures operated diametrically opposed to global boundaries (up to 20-0 voting margins). Ultimately, these outcomes demonstrate that rigid "one-size-fits-all" classifiers are bounded by biological diversity, emphasizing the need for future adaptive feature transformation techniques to bridge the cross-subject generalization gap.
Read the full abstract
Information Theory
AFDM-ISAC With Fractional Delay-Doppler Coupling
Affine frequency division multiplexing (AFDM) is a promising chirp-based multicarrier waveform for high-mobility integrated sensing and communication (ISAC). Accurate angle, delay, and Doppler estimation is essential for AFDM sensing. Since target delays and Doppler shifts are generally continuous-valued, representing them on a discrete delay–Doppler grid causes energy leakage and peak displacement in the discrete affine Fourier transform (DAFT) domain. The AFDM chirp also induces delay–Doppler coupling in the DAFT-domain response. The resulting DAFT-domain matching-score surface exhibits a local ridge that is not aligned with the normalized-delay and normalized-Doppler axes. To address these issues, this paper investigates joint estimation of angle and continuous-valued delay–Doppler parameters for a colocated AFDM-ISAC sensing architecture. A transform-domain sparse sensing model is formulated from the fractional DAFT-domain response. Based on this model, a coupled-coordinate Newtonized orthogonal matching pursuit (CC-NOMP) estimator is developed. CC-NOMP uses the AFDM-induced coupling coordinate to parameterize the dominant local ridge. It combines coupled-coordinate Newton refinement with safeguarded updates, coupling-aligned delay refinement, and cyclic multi-target refinement to estimate angle, continuous normalized delay, and normalized Doppler. A deterministic Cramér–Rao bound and a dominant-order complexity analysis are also derived. Simulation results with continuous-valued off-grid target parameters show that CC-NOMP achieves lower delay and Doppler error floors than the considered baselines while maintaining comparable angle-estimation accuracy.
Read the full abstract
Computer Vision
A Remote Approach to Cashew Orchard Detection: Leveraging Active Learning with Satellite Imagery in Guinea-Bissau
Cashew production is a widespread economic activity in Guinea-Bissau, as well as other countries in West Africa. However, unregulated cashew production can be directly associated with increasing regionwide deforestation rates, biodiversity losses, and a fragile economic structure. There is no nationwide database for listing or georeferencing cashew orchards, so there is a clear need to remotely map their locations. In recent years, multiple methods for detecting orchards have been developed, though they have only been applied on a regional level. This work expands regional analyses to a nationwide scale. It develops a scalable and cost-effective remote approach, based on Sentinel-2 satellite imagery, using Machine Learning techniques to detect cashew orchards automatically. Margin-based Active Learning techniques were employed to develop an optimal training set in terms of the number of points and their informativeness, leading to a cashew map with 94.0% balanced accuracy obtained entirely off-site. We created two datasets and a 2021 cashew map with 10m spatial resolution that are openly accessible through GitHub. The results demonstrate the possibility of a broader cashew orchard mapping, creating a new stepping stone for this environmental application.
Read the full abstract
Machine Learning · Cross-listed from eess.SP
Latent variable models for simultaneous EOV identification and removal in population-based SHM
The robust treatment of environmental and operational variability (EOV) is an open challenge in population-based structural health monitoring (PBSHM). The difficulty is compounded in the case that the EOV signals are unmeasured. A common approach in conventional SHM is to apply projection-based methods that discard subspaces of healthy feature data, reasoning that the EOV signal dominates the variance of the measured features. However, a common pitfall of projection-based approaches is that when damage acts close to the same variance-dominant direction, damage sensitivity is removed along with the EOV. An alternative identifying assumption for the removal of particular unmeasured EOVs is slowness; the latent EOV process is characterised by its long temporal correlation. In this paper, the latent EOV is cast as a state-space Gaussian process, enabling tractable $\mathcal{O}(T)$ inference via a Kalman filter. A robust hierarchical Bayesian identification framework is developed that enables population-level identification of latent EOVs and EOV-free residual features, using a Laplace approximation. The approach is first validated on a single laboratory-scale benchmark structure from the literature, subject to thermal EOVs, demonstrating robust damage detection and EOV recovery. The method is then applied to a simulated nine-turbine offshore wind farm with staggered deployment and damage, where it delivers a substantial true-positive uplift over projection and cointegration-based baselines at matched false-positive rates.
Read the full abstract
Artificial Intelligence
Claim-Level Reliability Assessment for Efficient Test-Time Reasoning
We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often obscures decisive errors due to signal dilution from routine tokens, CLR condenses each reasoning trace into a compact set of decision-critical claims, thereby isolating its logical anchors. Furthermore, recognizing the inherent difficulty of generating entirely correct solutions under fixed model capabilities, CLR shifts the focus to semantic falsification. This approach exploits a fundamental asymmetry between solution construction and claim refutation. Constructing a valid solution requires a flawless reasoning path, whereas refuting an incorrect claim requires identifying only a single decisive flaw. This targeted search for negative evidence systematically compresses the survival space of high-confidence incorrect traces, effectively suppressing erroneous consensus via nonlinear reliability scoring. Across four LLMs and four reasoning benchmarks under matched budgets, CLR generally improves upon pass@1 and self-consistency. On GPT-OSS-20B/CMIMC25, for instance, CLR exceeds pass@1 by 27.15 percentage-points and raises self-consistency accuracy from 77.50% to 82.19% with 37.0% fewer tokens.
Read the full abstract
Computer Vision
Auditing Frame-Level AUC in Weakly Supervised Video Anomaly Detection: Granularity, Resolution, and Scene Bias
Frame-level area under the ROC curve (AUC) is the dominant evaluation metric for weakly supervised video anomaly detection (WSVAD). Its standard form measures whether an anomalous frame outranks a normal frame drawn from anywhere in the test set. We refer to this comparison as pooled AUC, since it aggregates frame pairs across test videos regardless of source. Pooled AUC therefore credits both event localization and differences between video sources. We audit this protocol on UCF-Crime across recent state-of-the-art models spanning different backbone families. Holding each model's frame scores fixed, we read them under three pairing granularities: global, per anomaly category, and within each video, then repeat the same three-granularity readout on zero-shot scores computed from the models' internal representations. We assess ranking reliability with a paired video bootstrap. Three findings follow. First, pooled AUC does not reliably predict within-video anomaly localization: models with similar pooled scores exhibit large localization differences and rank reversals under stricter granularities. Second, at the benchmark's test-split size, pooled AUC lacks the resolution to support state-of-the-art margins reported in the field. Within each backbone family, it resolves no comparison at those margins, while within-video AUC resolves several over identical predictions. Learned representations further reveal that within-video anomaly structure and detector localization are decoupled. Third, on normal footage alone, every model we examine separates videos by recording properties, such as resolution and color encoding, indicating that scene sensitivity is shared across the setting rather than specific to any architecture. We publicly release a granularity-aware protocol computable from existing predictions and scene-factor annotations for UCF-Crime.
Read the full abstract
Computation and Language
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed
Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing larger pre-trained models using methods such as pruning, quantization, or distillation. As language models become increasingly integrated into real-world applications, ensuring their trustworthiness has become a critical concern. However, how to build trustworthy SLMs remains an underexplored question. In this work, we present a comprehensive evaluation of SLM trustworthiness across multiple dimensions, including fairness, robustness, privacy, and ethics. We first examine the effects of pruning and quantization, and find that quantization is significantly more effective in preserving trustworthiness compared to pruning. More importantly, we demonstrate that compressing a reliable large model via quantization can produce SLMs with superior trustworthiness and adaptability compared to using small models trained from scratch. Furthermore, knowledge distillation from trustworthy teacher models can further enhance the reliability of SLMs. We hope our findings provide practical guidance and a foundation for future research into the development and deployment of trustworthy small language models.
Read the full abstract
Information Retrieval
Learning from Unreachable Rewards: Hint-Conditioned Reinforcement Learning for Generative Recommendation
Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence. This paradigm enables a unified generation interface for item IDs, histories, and item text, but it also creates a structured optimization bottleneck during reward-based post-training: when an early semantic token enters the wrong branch of the item-token space, finite rollout groups rarely reach the ground-truth item, so group-relative optimization receives identical zero rewards and produces no useful advantage. We propose Hint-Conditioned Generative Recommendation (HCGRec), a semantic-ID generative recommendation framework that recovers learning signal for such hard training instances. HCGRec diagnoses each instance with checkpoint rollouts and supplies a minimal target-prefix hint only when the current generator cannot reach the correct item. The model then generates the unhinted suffix under the hinted semantic branch, turning zero-reward groups into informative comparisons over item-token completions. Hinting also changes token identity: hinted prefix tokens are oracle-provided item context, while unhinted suffix tokens are sampled generation actions. We therefore introduce hint-aware credit decomposition, using supervised learning to preserve item-semantic and prefix-structure alignment for hinted tokens and GRPO to optimize the sampled suffix. Experiments on sequential recommendation benchmarks show that HCGRec substantially improves over supervised fine-tuning and vanilla reward-based post-training, while reducing zero-advantage training samples from over 70% to below 20%. The code is accessible at https://github.com/WncFht/GRec.
Read the full abstract
Cryptography and Security
Slips: Behavioral Evidence Aggregation for Network Security
Network intrusion detection systems often analyze individual packets or flows, although malicious behavior may develop across many connections and over time. This may limit their ability to combine isolated detections into a coherent assessment of host behavior. Packet-level features may also be too low-level for complex AI-based detection, requiring additional processing to improve accuracy while maintaining a low false-positive rate. We present Slips, a network intrusion detection system that builds host-centered behavioral profiles and organizes activity into time windows. It uses a modular architecture in which independent modules report evidence rather than generating final alerts directly. Slips then accumulates this evidence into host-level decisions. We evaluate Slips against Suricata on an expert-labeled PCAP dataset. At the profile-time-window level, Slips achieved 83% higher recall and a 70% higher F1 score than Suricata, while neither system produced false positives. These results indicate that time-window-based evidence accumulation can produce context-aware decisions that better align with expert judgment.
Read the full abstract
Artificial Intelligence
Bench2Robust: Scenario-Controlled Recovery for Tool-Using Agents
Tool-using LLM agents are typically developed and post-trained in controlled environments with reliable tools, but deployment exposes them to tool failures, API and schema drift, and third-party services outside the developer's control. We introduce Bench2Robust, a framework for scenario-controlled solvability that augments existing benchmarks with episodes requiring retrying the original path, switching to a fallback-equivalent tool, or recognizing that no viable path remains. By controlling recoverability, Bench2Robust separates recovery-policy quality from randomness in whether failures persist or resolve. Across 7 models from 4 families and 10 task/domain slices spanning customer-service and function-calling benchmarks, 69 of 70 model-subset pairs degrade under tool failures, by up to 46.7 percentage points. We propose Bayesian Tool Memory (BTM) for structured runtime recovery context and use reinforcement learning (RL) for learned recovery behavior. On held-out Retail tasks using the benchmark's original tool set, BTM improves robustness by 16.8 percentage points without retraining, while RL retains a 6.3-point gain without inference-time BTM. Combining RL with BTM yields a 20.7-point improvement over the base model while preserving clean performance. These results show that robust tool use benefits from combining structured runtime recovery context with learned recovery behavior.
Read the full abstract
Information Retrieval
Sci-Surf: Navigating Scientific Literature Discovery through Human Feedback and Intelligent Summarization
The rapid growth of scientific publications makes it increasingly difficult for researchers to identify relevant new studies and effectively comprehend them. Existing academic discovery platforms typically rely on static topic subscriptions or embedding-based similarity and provide only abstracts or short summaries, offering limited support for nuanced intent modeling and in-depth paper summarization. We present Sci-Surf, an intent-centric knowledge discovery system that integrates feedback-driven personalized recommendation with multi-modal blog-style paper digestion. Our approach refines user intent representations through LLM-based user profiling, while generating structured summaries that synthesize textual and visual information from full papers. The demo presents an end-to-end academic discovery pipeline and demonstrates measurable improvements in both recommendation quality and digestion quality through real-user evaluations. Specifically, the integration of verbalized profiles led to a 10.4% average improvement in predictive alignment with real-world user preferences throughout a month-long online evaluation.
Read the full abstract
Networking
On the Allocation of Transmit Power for Coordinated Spatial Reuse in IEEE 802.11bn Multi-Access Point Coordination
IEEE 802.11bn (11bn) introduces Coordinated Spatial Reuse (Co-SR), a Multi-Access Point Coordination (MAPC) scheme where two APs coordinate to control the transmit power for a simultaneous transmission. This letter proposes a Proportional Fairness (PF)-driven framework for allocating Co-SR transmit power on a per-Transmission Opportunity (TXOP) basis. We prove that any Pareto-optimal power pair keeps at least one AP at its maximum power, reducing the joint two-dimensional search to two cheap one-dimensional line searches that fit within TXOP timing, and show that this collapses to an exact closed-form expression in a discrete-rate system. We validate these policies and a low-complexity selfish baseline against a brute-force oracle, using packet-level simulations in Kom8ndor, an 11bn simulator. Results show that jointly evaluating both APs' links is key to unlocking Co-SR's gains, that the coordinated AP's fairness-optimal power depends critically on whether the rate is modeled continuously or through discrete Modulation and Coding Scheme (MCS) steps, and that current 11bn signaling supports the selfish policy but not the fairness-optimal ones, which would need additional per-TXOP channel reporting.
Read the full abstract
Machine Learning
TESLA: Taylor Expansion of Sinusoidal Learnable Activations
The parity problem–deciding whether the number of ones in a binary vector is odd or even–remains challenging for standard neural networks due to linear inseparability and the need for global interactions. We propose TESLA, an activation defined as a learnable combination of sine and cosine terms, enabling explicit control over polynomial degree and selective amplification of high-order components. Theoretically, we show that constraining TESLA's coefficients yields Lipschitz/Rademacher complexity bounds and shapes the training dynamics to emphasize higher-frequency structure. Empirically, on parity with input length n = 32, TESLA attains strong generalization with 100K training samples (approximately 0.002% of the 2^32 input space) and remains robust under heavy corruption, retaining high accuracy with up to 30% label noise. We also compare against periodic and frequency-based baselines (SIREN, SNAKE, and Fourier feature embeddings) on parity and Forrelation. Beyond synthetic structure, TESLA delivers comparable performance on ImageNet-100, indicating that activation-level degree control transfers to more general vision workloads. Code: https://github.com/KAU-QuantumAILab/TESLA
Read the full abstract
Machine Learning
LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation
Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical capability in such settings is reflection: assessing trajectory progress, identifying missing evidence and unreliable intermediate states, and deciding whether to continue, revise, or abandon the current branch. Learning effective reflection, however, is challenging because reflection is performed locally within the current branch, whereas its utility can only be determined by its contribution to the final trajectory outcome. This local-global mismatch makes outcome-based reinforcement learning provide only local, sparse and delayed supervision for reflective decisions. To solve these, we propose LoongReflect, a training framework that formulates reflection as a memory-control policy. The agent operates over a reversible trajectory tree using explicit reflect and backtrack actions. Reflection consolidates verified facts, missing evidence, and branch-specific risks into working memory, while backtracking removes an unreliable branch from the active context and preserves a concise corrective lesson. To learn this policy, LoongReflect combines two complementary signals through a look-ahead, extragradient-style coordination mechanism. A fast channel distills globally informed reflective behavior from a privileged teacher, with supervision restricted to reflection and backtracking tokens. A slow channel optimizes complete trajectories using outcome-based GRPO, aligning local control decisions with final task success. Experiments on multi-hop retrieval-augmented generation and mathematical reasoning benchmarks demonstrate consistent improvements over outcome-only reinforcement learning and self-distillation baselines.
Read the full abstract
Software Engineering
Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
The proliferation of Generative Artificial Intelligence (Gen AI) powered by large language models (LLMs) has transformed the software development process, introducing new paradigms for code generation, debugging, testing, and maintenance. While early applications focused on leveraging single, independent LLMs to assist developers with isolated tasks, recent advances have shifted toward multi-agent systems (MAS) that orchestrate multiple LLM-based agents working collaboratively toward common objectives. Despite their promising potential, using MAS encompasses a set of challenges for developers who have to carefully select the right technology, devise proper coordination rules, and design specific roles for the involved agents. In this paper, we provide a comprehensive overview of the existing tools and frameworks for implementing MAS in software engineering. First, we conducted a quantitative analysis of the most relevant open source MAS frameworks by evaluating their documentation, features, and capabilities from the developers' perspective. Second, we performed a qualitative evaluation of a subset of the selected frameworks by implementing a common use case: the summarization of README.MD files. The findings show that the selected frameworks provide a good coverage of fundamental components of MAS, though advanced features such as telemetry of agents are still missing. In addition, the empirical evaluation shows that there is no significant difference in terms of ROUGE scores considering the summarization task. Finally, we provide a set of lessons learned and challenges that can help researchers and practitioners to select a suitable MAS framework according to their needs.
Read the full abstract
Human-Computer Interaction
Synchronized AMG and EMG Dataset of Lower-limb Muscle Activities in Everyday Training
Understanding how lower-limb muscle groups coordinate is important for studying movement impairment, rehabilitation, and physical performance. Reproducible analysis of this coordination requires multimodal recordings that relate local muscle-related signals with body-level kinematics. Complementing neural-level electrical activation captured by EMG, AMG provides a valuable mechanical approach to monitoring muscle activity. Here, we introduce a synchronized, multimodal dataset for healthy-adult lower-limb activities. For data collection on the left leg, 16 triaxial accelerometers were evenly divided into four muscle-site clusters for AMG recording, complemented by four surface EMG channels. A 15-marker optical motion-capture (MoCap) system captured lower-body kinematics, with the resulting marker trajectories used to compute bilateral knee and ankle joint angles. Our dataset contains 1,918 trials from 30 subjects across 16 task conditions. We benchmark the dataset by estimating four joint angles from 300 ms windows of the 5-100 Hz band-pass-filtered AMG data and assess matched EMG features in a separate modality ablation. In the primary cross subject benchmark, the four reference models achieved mean absolute errors of 8.840$^\circ$-9.591$^\circ$. The benchmark and ablation results characterize performance across subjects, tasks, and joint angles and examine the effects of sensor configuration, modality, the number of training subjects, and frequency representation. The release includes documented timing definitions, processed data, and reproducible benchmark resources. https://dongxutang918-afk.github.io/SAME-Limb/
Read the full abstract
Computers and Society
Philosophical vertigo with artificial intelligence
Large language models are already adept at engaging users in long, emotionally salient conversations across ordinary and existential domains. They are also capable of inducing a potent sense of connection with a human-like entity, even when the user knows their interlocutor is artificial. For some users, these conversations can unsettle assumptions about mind, reality, agency and authority, producing forms of ontological shock and epistemic destabilisation in which inherited criteria become newly available for doubt or revision. Independent of direct use, exposure to public discourse about AI and the disorienting pace of their evolution might extend this destabilisation by changing the cultural background against which artificial minds are encountered and interpreted. We describe this condition as philosophical vertigo: a loosening of the ordinary criteria by which people stabilise meaning and orient themselves to reality. Drawing on philosophy, psychiatry, cognitive science, AI safety and religious studies, we outline pathways through which philosophical vertigo may arise, become affectively saturated, and eventually propagate through human-AI interaction and online communities. Against this background, clinical reports of AI-associated delusions can be seen as sentinel events making visible themes and mechanisms that may also operate at a population level in less severe or non-clinical forms. We argue that AI systems themselves will increasingly participate in the reconstruction of our shared epistemic environment because they readily supply narrative material and personalised interpretive scaffolding at precisely the moment when users' conceptual assumptions may already be loosened. We conclude by considering possible trajectories for the ecology of belief and shared reality, and proposing philosophical corrigibility as a civic response for navigating this emerging social condition.
Read the full abstract
Artificial Intelligence · Cross-listed from stat.ME
Causal inference for group-contaminated structured outcomes: observable quotients, lossless reduction and exact randomization inference
Structured potential outcomes such as microscopy images may be recorded after an unknown, unit-specific transformation. If that transformation can depend on treatment, covariates or the intrinsic outcome, raw-coordinate analyses may mix biological effects with acquisition geometry. We study the unrestricted observation model X = {\Gamma} . Y(A) and characterize its observable information: a target is uniformly recoverable exactly when it is constant on group orbits, while a Borel maximal invariant retains every measurable invariant target. We then distinguish observability from statistical losslessness. A quotient-faithful reconstruction theorem shows that quotient reduction is sufficient for the full transformed experiment exactly when the conditional law of the raw observation given treatment, covariates and the quotient has a parameter-free version. Conditional Haar contamination on a compact group yields Blackwell equivalence as a special case; it is not imposed in the main model. We also separate independent site-specific product actions from shared diagonal actions and show why componentwise canonicalization can discard relative cross-site information. Under explicit metric and kernel regularity, an approximate-contamination theorem bounds quotient-law Wasserstein error and the induced perturbation of population maximum mean discrepancy. For finite-support multichannel lattice images, we construct a maximal invariant under integer translations and quarter turns, combine its characteristic Gaussian kernel with a complete paired-swap test, and retain the original simulations and RxRx1 HUVEC study. Under the sharp null, the quotient test rejected in 0.052 of simulation replicates; at unit effect strength its power was 0.992. The primary RxRx1 contrast had an enumerated paired-swap p-value of 0.0078.
Read the full abstract
Machine Learning
TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement
Extreme events in air transport, such as severe arrival delays and abnormal air times, cause cascading network disruptions with substantial operational, economic, and safety costs. Such events are rare in historical records, leaving insufficient training signal for machine learning models. Synthetic data augmentation offers a principled solution, but conventional generative models under-represent distributional tails and give no guarantee against operationally infeasible instances, such as a short air time paired with a long flight distance. No existing approach addresses both limitations for mixed-type tabular records. We propose TailBooster, a dual-layer generative framework combining generative modelling with two anomaly detection layers. A statistical layer extracts extremes via the interquartile range, supplying tail-concentrated training signal to dedicated generative models, here a Tabular Variational Autoencoder. A deep learning layer then applies autoencoder-based cleaning, discarding synthetic records that violate the operational envelope learned from historical data. The framework was evaluated on US flight records across five dimensions: diversity, statistical similarity, fidelity, operational validity, and utility, the latter two being the primary improvement targets. Data-driven cleaning markedly improved operational validity, while targeted augmentation enhanced utility for extreme-event prediction. Across six regression algorithms, training on the framework's records reduced Mean Absolute Error by 47-49% on extreme air time and 29-57% on extreme arrival delay prediction relative to conventional synthetic data, with comparable gains when real records were enriched with synthetic extremes. Being fully data-driven and model-agnostic, TailBooster extends to domains where extreme-event prediction is critical and domain-specific rules are unavailable.
Read the full abstract
Computational Engineering
An improved bond-associated peridynamic model and its adaptive coupling with CCM for fracture analysis
This paper reformulates the correction factor in the force-state of the bond-associated peridynamic (BAPD) model. The reformulation is established from the strain energy density equivalence between the BAPD model and the classical continuum mechanics (CCM) model at a material point. With the FEM solution taken as the reference, the proposed correction factor improves the accuracy of the BAPD solution in this study. Furthermore, a BAPD-CCM coupled model is developed based on the above energy density equivalence, and a “Morphing" function is introduced to achieve a smooth transition between the two models. For time integration, explicit schemes are adopted for both quasi-static and dynamic problems. In the spatial discretization, the CCM model is discretized by elements, whereas the BAPD model is discretized by particles. The solution accuracy of the coupled model is validated by comparison with the FEM solution and by evaluating the $L^{2}$ norm, the $H^{1}_{\mathrm{semi}}$, and the energy norm of the displacement error. Two- and three-dimensional numerical examples show that the proposed model has higher computational efficiency. For example, in the Mode I crack propagation problem, its computational cost is reduced by more than 72% compared with that of the pure BAPD model, and the predicted crack patterns agree with experimental results.
Read the full abstract
Artificial Intelligence
ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models
Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels disconnected from learned behavior and parameter updates. We argue that a useful role should instead be an executable control variable: it should summarize behavior predictive of future utility, guide subsequent interaction, and identify the trainable capacity responsible for that behavior. We introduce ExRole, a trajectory-to-role framework that learns future-aware role prototypes from prefix-local team traces, resolves them into readable instructions and token-aligned role markers, and optionally routes shared LoRA rank slots with turn-aligned credit. Across MuSiQue and 2WikiMultiHopQA, ExRole improves over single-agent search by 15.0/14.4 and 13.5/16.1 EM/F1 points, respectively. Against the strongest non-ExRole controls, the corresponding gains remain 11.5/11.6 and 7.7/9.7 points. Across both benchmarks, the controlled results consistently favor trajectory-induced role conditioning over role-free, manual, random, and shuffled alternatives. Role-Agent-Turn interventions further show that the induced roles capture transferable behavioral specialization beyond fixed agent identities or turn positions.
Read the full abstract
Computation and Language
A, B, C, or Stable? Accuracy and Order Sensitivity Diverge in LLM Multiple-Choice Evaluation
Multiple-choice question (MCQ) benchmarks are widely used to evaluate large language models, yet a single reported accuracy number is not enough to distinguish a model's latent ability from order sensitivity. Debiasing methods tend to be judged on one axis, which implicitly assumes that fixing order sensitivity and improving accuracy go together. We test this assumption with two proprietary models and two open-weight models on MMLU and ARC-Challenge, across four families of strategies. We measure order sensitivity with flip rate, capturing per-question instability, and recall standard deviation (RStd), capturing aggregate positional imbalance. We find accuracy and order sensitivity do not move together consistently: two-stage prompting reduces both flip rate and RStd for GPT on MMLU without a significant change in accuracy. The two sensitivity metrics also diverge from each other. Adding reasoning to direct answering leaves Llama's MMLU flip rate statistically indistinguishable while RStd falls sharply. A $2\times2$ ablation across generation-then-matching, crossing option visibility with matcher type, shows that withholding options mainly harms semantic matching, which achieves zero flip rate by construction, yet loses significantly in accuracy; the effect is smaller when using an LLM matcher. We recommend reporting flip rate and RStd along with accuracy when evaluating MCQ strategies.
Read the full abstract
Computer Vision
Evaluating and Calibrating Diffusion Model-derived Uncertainty for Quantitative MRI Mapping
Quantitative MRI (qMRI) provides standardised tissue parameter maps, but the reliability of deep learning-based qMRI mapping methods is often not explicitly characterised. In this work we systematically evaluate uncertainty maps for quantitative MRI derived from multiple inferences of a data-consistent diffusion model-based qMRI framework. Evaluation on synthetic test data assessed error-awareness, high-error detection, selective prediction, and Gaussian interval calibration. Diffusion model-derived uncertainty was positively associated with the mapping error, while risk-coverage analysis showed that excluding high-uncertainty voxels reduced the retained error. However, the raw uncertainty was poorly calibrated for quantitative interval interpretation. Calibration was substantially improved using a post-hoc procedure combining prediction-value-dependent bias correction with scalar uncertainty scaling. Qualitative evaluation on a healthy volunteer showed spatially meaningful uncertainty patterns. These results indicate that diffusion model-derived uncertainty is informative for reliability assessment and selective prediction, but requires calibration for quantitative interval interpretation.
Read the full abstract
Artificial Intelligence
OEIS Open: How many conjectures can language models turn into theorems?
We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source evaluation code runs any generic language model (LM) against them, and is secure against LM cheating attempts. We find that LMs equipped with a minimal set of tools resolve 147 of these conjectures with a budget of \$50 per attempt, scoring 30% on OEIS Open. OEIS Open Lite is a random subset of 100 conjectures for cheaper evaluation. When evaluated with a budget of \$200 per attempt, the best current LM scores 44% on OEIS Open Lite. Giving LMs access to the mathematics literature via 476,000 papers from arXiv did not increase performance on OEIS Open Lite, and nor did using more sophisticated agent loops. The conjectures covered in this work are of uncertain mathematical significance, and most have likely received little previous attention. Nevertheless, our results show that LMs can resolve open research conjectures autonomously and at modest cost.
Read the full abstract
Cryptography and Security
CCZ-Equivalence and Enumeration of Triprojective APN Functions
We classify all admissible parameters of the G"ologlu–K"olsch triprojective construction of almost perfect nonlinear (APN) functions up to Carlet–Charpin–Zinoviev (CCZ) equivalence. The construction has three coefficients in $K=\mathbb{F}_{2^m}$ and a Frobenius exponent $k$ coprime to $m$. For every $m>1$, we give a necessary-and-sufficient criterion that includes changes of both the coefficients and the exponent. Each parameter choice determines one of the two irreducible cubic polynomials over $\mathbb{F}_2$. Two functions are equivalent precisely when their exponents and cubics agree, or when the exponents are negatives modulo $m$ and the cubics are reciprocal. When $7\nmid m$, every admissible member is equivalent to a Li–Kaleyski representative: the larger coefficient space adds no CCZ classes. When $7\mid m$, those representatives are inadmissible; we construct replacements and classify the full family. There are exactly $\varphi(m)$ CCZ classes, extending the previously known count for the older subfamilies to all admissible coefficients and all degrees. We also count the parameter triples and compute canonical representatives and explicit equivalence maps in deterministic polynomial time for every degree, including degrees divisible by seven. The proof combines a reduction to classical semilinear conjugacy with an intrinsic recovery of the scalar field from the polar bilinear map. The reduction from arbitrary EL equivalence is algebraic in every degree, including degrees three and six.
Read the full abstract
Computer Vision
Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction
Sparse voxel reconstruction offers an efficient representation for high-fidelity 3D modeling, yet its geometry is commonly optimized from local photometric evidence and discrete visibility statistics. This often leads to fragmented surfaces, excessive subdivision, and floating artifacts, particularly in weakly textured or sparsely observed regions. We introduce SurfSVR, a novel sparse voxel reconstruction paradigm that treats 2D surface priors as explicit 3D geometric regularizers. Instead of directly lifting noisy pixel-wise depth predictions, SurfSVR first organizes each image into coherent surface regions by jointly reasoning over appearance, monocular depth, normals and cross-view geometry. Each region is then represented by an adaptively selected planar or quadratic surface model based on fitting reliability and geometric complexity, while cross-model agreement distinguishes reliable geometry from ambiguous predictions. These structured 2D priors are lifted into 3D and integrated throughout the reconstruction pipeline. They guide surface-adaptive voxel subdivision, provide region-level depth and normal supervision during optimization, enhance geometrically reliable sparse-observed surfaces in voxel pruning, and suppress off-surface floaters during post-refinement training. This unified design converts semantic and geometric coherence in image space into persistent structural constraints in 3D. Extensive experiments on 3 public benchmarks demonstrate that SurfSVR consistently improves sparse voxel reconstruction across scenes with substantially different visibility and geometry characteristics, achieving state-of-the-art reconstruction quality. Codes and models will be released soon.
Read the full abstract
Machine Learning
Distillation of Foundation Models for Time-dependent PDEs
Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks. After fine-tuning on only a few trajectories from a target domain, they can achieve strong accuracy in low-data regimes. However, these models are typically large and computationally intensive, limiting their usefulness as fast surrogates for numerical solvers. We propose Teacher Rollout Extension (TREX), a knowledge distillation framework that transfers the predictive capability of a pretrained foundation model into a compact and efficient student. Starting from a fine-tuned teacher, TREX augments limited downstream data by generating long synthetic trajectories through teacher rollouts, optionally with periodic noise injection. This procedure samples from the teacher-induced rollout distribution without requiring explicit knowledge of the initial-condition distribution, while exposing the student to long-horizon states and local recovery behavior around states encountered during autoregressive prediction. The student can further incorporate task-specific inductive biases, such as equivariance, that the teacher does not necessarily enforce. We evaluate TREX on multiple PDE benchmarks. The resulting students can match or surpass the teacher's accuracy while reducing the number of parameters by several orders of magnitude and achieving more than an order-of-magnitude speedup in inference.