arXiv:2605.17698v1 Announce Type: new
Abstract: The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective behavior can amplify volatility and mask deception at scale. We introduce the Agent Bazaar, a multi-agent simulation framework for evaluating Economic Alignment, the capacity of agentic systems to preserve market stability and integrity. We identify two failure modes: (1) Algorithmic Instability in a B2C market ("The Crash"), where firms amplify price volatility until the market collapses, and (2) Sybil Deception in a C2C market ("The Lemon Market"), where a single deceptive agent controlling multiple coordinated seller identities floods the market with fraudulent listings, eroding trust and consumer welfare. We evaluate frontier and open-weight models across both scenarios and find that models largely fail to self-regulate, with failure severity varying by model rather than by size. We propose economically aligned harnesses, Stabilizing Firms and Skeptical Guardians, that improve outcomes but remain fragile under harder market conditions. To close this gap, we train agents with REINFORCE++ using an adaptive curriculum, producing a 9B model that outperforms all evaluated frontier and open-weight models. We propose the Economic Alignment Score (EAS), a 4-component scalar metric aggregating stability, integrity, welfare, and profitability, enabling direct cross-model comparison. Our results show that economic alignment is orthogonal to general capability and can be directly trained with targeted RL.
Science Journals
arXiv:2605.17701v1 Announce Type: new
Abstract: Edge inference systems are typically evaluated with software-reported latency collected under controlled conditions. We argue, and demonstrate empirically, that deployment interference can corrupt not only the inference timing being measured but the timing observability infrastructure that measures it, and that the two failures can occur independently.
We pair software-reported timing with externally observable GPIO intervals captured by a Saleae Logic Pro 8 logic analyzer on an NVIDIA Jetson Orin Nano, running MobileNetV2 under two inference architectures (TensorRT FP16 GPU and ONNX Runtime CPU) across baseline, light memory pressure, and storage writeback stress. Across 35 paired capture runs (3500 samples) plus 3 storage-stress runs where external pairing failed (300 software-only samples), we observe three findings the software-only view does not surface. (1) The two architectures differ not only in mean latency but in distributional structure: TensorRT baseline clusters tightly near 1.23 ms (run-mean SD 15 us) while ORT CPU baseline is multimodal with run-mean SD 31.8 ms. (2) Light memory pressure inflates TensorRT P99 from 1.28 ms to 1.61 ms, while one of five ORT memory-stress runs collapses into a deterministic 198 ms regime rather than uniformly inflating variance. (3) All three TensorRT storage-stress runs produce complete software timing logs (100/100 iterations) alongside externally observable timing failures of three different kinds (full post-marker collapse, ~40% transition loss, and complete acquisition failure) -- while the runtime reports normal completion in every case.
We claim, narrowly, that timing observability is itself an interference-sensitive resource, and that summary statistics from a single timing source can hide failure modes an independent external observer makes visible.
GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds
arXiv:2604.20155v2 Announce Type: replace
Abstract: 3D Gaussian Splatting (3DGS) has revolutionized high-fidelity neural rendering with its explicit representation and efficiency. However, reconstructing scenes from sparse viewpoints suffers from severe geometric voids and floaters due to limited coverage. Current scene completion methods typically rely on an iterative "Repair-then-Distill" paradigm, which is computationally intensive, prone to unstable optimization, and susceptible to overfitting. To address these limitations, we propose GSCompleter, a distillation-free plugin that shifts scene completion to a stable "Generate-then-Register" workflow. Specifically, GSCompleter synthesizes visually plausible 2D reference images and explicitly lifts them into 3D Gaussian primitives with a consistent metric scale via a robust Stereo-Anchor View Selection mechanism. These newly generated primitives are then seamlessly integrated into the global scene using a novel Ray-Constrained Registration strategy. By replacing unstable distillation with rapid geometric registration, GSCompleter exhibits superior 3DGS completion performance across three benchmarks, enhancing both quality and efficiency over various baselines and achieving new state-of-the-art (SOTA) results.
arXiv:2605.18700v1 Announce Type: new
Abstract: Prior work on fine-grained image recognition (FGIR) has established the importance of the backbone selection, but has neglected the accuracy-vs-cost trade-offs under different training and evaluation settings. In this work we conduct a large-scale study with over 2000 experiments across 6 training and evaluation settings, 9 pretrained backbones, and 17 datasets. Preliminary observations on the effectiveness of data augmentation for fine-grained training motivate us to extend Counterfactual Attention Learning (CAL), a state-of-the-art method based on data-aware cropping and masking augmentations, with cross-image discriminative region mixing augmentation. We also propose an efficient evaluation-only variant that maintains competitive accuracy while reducing inference costs by forfeiting the forward pass on discriminative crops that is normally used by CAL and similar FGIR methods. Our results show that data-aware augmentations during training only can enable a model to achieve excellent accuracy even without crops, significantly reducing inference costs. To support future research we share our code and checkpoints at: \url{https://github.com/arkel23/FGIR-Backbones}
arXiv:2605.18697v1 Announce Type: new
Abstract: Compound AI applications, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks, from software engineering to enterprise automation, making their end-to-end latency a critical bottleneck. In contrast to traditional applications, execution time is dominated by the external components, which cannot be handled by traditional language optimization systems, like optimizing compilers.
To address this problem, we develop PopPy, a system that can uncover parallelization opportunities in Python applications that invoke these heavy external components, including those used in compound AI applications. PopPy supports a very expressive fragment of Python and requires minimal developer input to uncover parallelism. It combines an ahead-of-time compiler with a runtime, addressing three key challenges in extracting parallelism from Python applications: language complexity, dynamic dispatch, and variable mutation. On a set of real-world compound AI applications, PopPy achieves up to $6.4\times$ speedups in end-to-end execution time compared to standard Python execution while preserving the sequential program semantics.
arXiv:2604.19428v2 Announce Type: replace
Abstract: Optical manipulation of Mie-resonant dielectric nanoparticles is strongly influenced by their enhanced scattering and multipolar response, which fundamentally modifiesthe balance of optical forces. In this work, we study the optical forces acting on a resonant dielectric nanoparticle placed near a metal interface, where scattering occurs into both free-space and surface plasmon-polariton (SPP) channels. We show that the interference of electric and magnetic dipole moments leads to highly directional scattering in these channels, and the direction and magnitude of the scattering-induced force are directly linked to the angular directivity of the corresponding radiation channels. We show that in a cross-beam configuration, where the radiation-pressure contribution is suppressed, the optical force can be changed for almost 2{\pi} in a wide range of particle sizes that provides a route toward optical sorting of resonant nanoparticles.
arXiv:2604.14215v2 Announce Type: replace
Abstract: To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its strategic focus to primary healthcare and encouraging citizens to use community resources to self-manage their health. However, official clinical guidelines are fragmented across disparate departments and formats, creating significant access barriers. While general-purpose Large Language Models (LLMs) such as ChatGPT and DeepSeek offer potential solutions for information accessibility, they are prone to generating factually inaccurate content due to a lack of localized and domain-specific knowledge. To this end, we propose a Retrieval-Augmented Generation-Enhanced LLM system as Primary Healthcare Assistant (PriHA) in Hong Kong. Specifically, a tri-stage pipeline is proposed that leverages a query optimizer to generalize user intent-oriented sub-queries, followed by a novel Dual Retrieval Augmented Generation (DRAG) architecture for mixed-source retrieval and context-reorganized generation. Comprehensive experiments and a detailed case study demonstrate that our proposed method can outperform both ablations and baseline in terms of accuracy and clarity. Our research provides a reliable and traceable dialogue retrieval framework for exploring other high-risk, localized application scenarios.
arXiv:2605.17703v1 Announce Type: new
Abstract: This innovative practice WIP paper describes \emph{LITE-SOC}, a lightweight web-based Security Operations Center (SOC) simulator designed for instructor-led cybersecurity education. SOC analysts must triage large volumes of alerts, separate genuine threats from false positives, and communicate decisions under time pressure. Recreating this environment in the classroom is difficult and often impractical for institutions without access to cyber ranges or enterprise security infrastructure. LITE-SOC was developed to provide a simpler alternative. The platform generates continuous streams of synthetic SOC events and offers separate student and instructor views with visualization tools, event annotation, and region-based chat. Instructors control the pacing of the exercise and can inject targeted incidents to guide the scenario. The goal is to give students a practical introduction to SOC workflows such as triage, prioritization, and decision-making without requiring a full operational SOC environment. The platform is intended for use in guided classroom exercises where students collaboratively investigate alerts and practice real-time triage and communication.
arXiv:2604.13353v2 Announce Type: replace
Abstract: This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation framework that leverages specialized language models coordinated through multi-agent reflection-based reasoning. The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantically relevant personally identifiable information (PII) while maintaining diagnostic utility, and (3) translate technical expert responses into user-comprehensible language.
Our approach employs ReAct-style agents enhanced with self-reflection mechanisms for iterative output refinement, semantic-preserving anonymization techniques respecting $k$-anonymity and differential privacy principles, and few-shot learning strategies designed for limited training data scenarios. The framework was comprehensively evaluated on 10,000 previously unseen validation scenarios across various vertical industries.
arXiv:2604.12766v2 Announce Type: replace
Abstract: Retrieval-augmented generation (RAG) typically relies on a flat retrieval paradigm that maps queries directly to static, isolated text segments. This approach struggles with more complex tasks that require the conditional retrieval and dynamic synthesis of information across different levels of granularity (e.g., from broad concepts to specific evidence). To bridge this gap, we introduce NaviRAG, a novel framework that shifts from passive segment retrieval to active knowledge navigation. NaviRAG first structures the knowledge documents into a hierarchical form, preserving semantic relationships from coarse-grained topics to fine-grained details. Leveraging this reorganized knowledge records, a large language model (LLM) agent actively navigates the records, iteratively identifying information gaps and retrieving relevant content from the most appropriate granularity level. Extensive experiments on long-document QA benchmarks show that NaviRAG consistently improves both retrieval recall and end-to-end answer performance over conventional RAG baselines. Ablation studies confirm performance gains stem from our method's capacity for multi-granular evidence localization and dynamic retrieval planning. We further discuss efficiency, applicable scenario, and future directions of our method, hoping to make RAG systems more intelligent and autonomous.
arXiv:2604.12254v2 Announce Type: replace
Abstract: SpanKey is a lightweight way to gate inference without encrypting weights or chasing leaderboard accuracy on gated inference. The idea is to condition activations on secret keys. A basis matrix $B$ defines a low-dimensional key subspace $Span(B)$; during training we sample coefficients $\alpha$ and form keys $k=\alpha^\top B$, then inject them into intermediate activations with additive or multiplicative maps and strength $\gamma$. Valid keys lie in $Span(B)$; invalid keys are sampled outside that subspace. We make three points. (i) Mechanism: subspace key injection and a multi-layer design space. (ii) Failure mode: key absorption, together with two analytical results (a Beta-energy split and margin-tail diagnostics), explains weak baseline separation in energy and margin terms -- these are not a security theorem. iii) Deny losses and experiments: Modes A--C and extensions, with CIFAR-10 ResNet-18 runs and MNIST ablations for Mode B. We summarize setup and first-order analysis, injectors, absorption, deny losses and ablations, a threat discussion that does not promise cryptography, and closing remarks on scale. Code: \texttt{https://github.com/mindmemory-ai/dksc}
arXiv:2605.18672v1 Announce Type: new
Abstract: This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a contingent limitation of current systems. The three dimensions that jointly constitute safe operation -- semantic intent and policy compliance, environmental validity, and dynamical feasibility -- each depend on a strictly distinct set of information that becomes available at different stages of execution. No single guardrail can certify all three. We argue that the community must respond with a contract-based architecture in which each safety dimension is enforced by an independently certified layer whose probabilistic guarantee satisfies the next layer's assumption. We sketch such an architecture and derive the compositional system-level safety bounds it admits via the chain rule of probability. Three open problems stand between this and a deployable standard: bound estimation from non-i.i.d.\ traces, graceful degradation of contracts under deployment drift, and extension to multi-agent settings -- the most important unfinished business in LLM agent runtime assurance.
arXiv:2604.06398v2 Announce Type: replace
Abstract: Global ocean models exhibit biases in the mean state and variability, particularly at coarse resolution, where mesoscale eddies are unresolved. To address these biases, parameterization coefficients are typically tuned ad hoc. Here, we formulate parameter tuning as a calibration problem using Ensemble Kalman Inversion (EKI). We optimize parameters of a neural network parameterization of mesoscale eddies in two idealized ocean models at coarse resolution. The calibrated parameterization reduces errors by factors of 1.7-3.3 in the time-averaged fluid interfaces and their variability compared to the unparameterized model, depending on the metric and configuration. The EKI method is robust to noise in time-averaged statistics arising from chaotic ocean dynamics. Furthermore, we propose an efficient calibration protocol that bypasses integration to statistical equilibrium by carefully choosing an initial condition. These results demonstrate that systematic calibration can substantially improve coarse-resolution ocean simulations and provide a practical pathway for reducing biases in global ocean models.
arXiv:2509.16391v3 Announce Type: replace
Abstract: Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations often achieve limited unlearning effectiveness. To address this, we introduce CoUn, a novel MU framework inspired by the observation that a model retrained from scratch using only retain data classifies forget data based on their semantic similarity to the retain data. CoUn emulates this behavior by adjusting learned data representations through contrastive learning (CL) and supervised learning, applied exclusively to retain data. Specifically, CoUn (1) leverages semantic similarity between data samples to indirectly adjust forget representations using CL, and (2) maintains retain representations within their respective clusters through supervised learning. Extensive experiments across various datasets and model architectures show that CoUn consistently outperforms state-of-the-art MU baselines in unlearning effectiveness. Additionally, integrating our CL module into existing baselines empowers their unlearning effectiveness.
arXiv:2605.17723v1 Announce Type: new
Abstract: Residential batteries increasingly serve two roles: they can earn money by arbitraging wholesale prices and providing grid services, and they provide backup power during outages. This dual use creates a basic tradeoff between earning market value and preserving outage readiness. Coordination across many batteries can help, but a provider cannot treat the fleet as a single virtual battery when each household is promised its own backup protection.
We compare standalone control, in which each home is dispatched independently, with pooling, in which homes are coordinated while each battery retains its own state of charge and household-specific backup requirement. Both regimes are implemented as model predictive control problems with 15-minute decision intervals and evaluated using household telemetry together with ERCOT market inputs. The empirical design focuses on the 543 homes in our sample that can support at least one backup product in standalone operation and studies backup caps ranging from 2 to 24 hours. Lower caps relax backup obligations, while the 24-hour cap coincides with assigning each home its own longest feasible backup tier.
Pooling remains beneficial in this service-constrained setting, but its value declines smoothly as backup obligations tighten. Standalone firm margin ranges from \$11.06 per home per week at the 2-hour cap to \$10.79 at the 24-hour cap, while pooling benefit falls from \$1.49 to \$1.27 per home per week. Relative to standalone firm margin, pooling is worth about 13.5% at the 2-hour cap and about 11.8% at the 24-hour cap. Coordination therefore still helps after preserving household-level backup guarantees, but its value declines as backup obligations tighten.
arXiv:2605.17727v1 Announce Type: new
Abstract: Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption meaning, but they expose these signals through a fixed-length vector interface. We study whether embedding length can be turned into a controllable semantic access interface. We propose \textbf{GraSP-VL}, which learns a shared near-orthogonal prefix transform over frozen VLM embeddings. GraSP-VL instantiates a \textbf{Semantic Matryoshka} interface: short prefixes are assigned coarse semantic roles, while longer prefixes progressively expose finer language-grounded distinctions. Because the transform is shared across image and text embeddings and preserves full-dimensional geometry, prefix behavior changes without rewriting the original VLM space. On a 20,147-example COCO/Flickr30K annotation pool, GraSP-VL reaches a staircase score of 53.01 and hard-negative selectivity of 89.76, while keeping full-space drift below $10^{-6}$. It also transfers to SugarCrepe-clean with 86.03 object accuracy and 11.96 mean external emergence, and preserves full-dimensional zero-shot CIFAR-100 accuracy. These results show that frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed.
arXiv:2605.18549v1 Announce Type: new
Abstract: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring tool. To address this, we investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations. By evaluating a probe at each generated token, we construct a probe trajectory, the continuous evolution of a concept's probability across the reasoning process. We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction. To characterize these temporal dynamics, we extract signal-processing features that capture volatility, trend, and steady-state behavior, significantly improving the separation of future model states. We also present two methodological insights. First, template-based training data achieves near-parity with dynamically generated model responses, eliminating the need for a costly initial inference and labeling. Second, the choice of pooling operation is critical: average-pooling and last-token methods collapse to near-random performance, while max-pooling achieves up to 95% AUROC and yields stable probe trajectories. Using four datasets and four reasoning models across the domains of safety and mathematics, we demonstrate that trajectory features encode task-specific dynamics that improve outcome separability. These findings establish probe trajectories as a complementary framework for monitoring LRM behavior.
Warning: This article contains potentially harmful content.
arXiv:2605.18671v1 Announce Type: new
Abstract: Reconnections and rotations of lines are dual descriptions of the same saddle-shaped spacetime surface. We show that a reconnection between two line occurring over time is a single line that rotates over space progression. Both rotating lines and reconnections possess the same saddle shape sheet geometry in four-dimensional space-time, with different orientations. Cyclic precessing lines occurring over time are arrays of reconnections occurring spatially. We show that a magnetic reconnection occurring over time can be seen as a single continuous line vector potential rotating spatially, where the full evolution traces a saddle shape surface. Finally, we show that a single tilted spatiotemporal optical vortex precesses with spatial progression, and as a result can be seen as two vortices reconnecting. Given the unique spatiotemporal evolution, we also analyzed the relativistic angular momentum of these electromagnetic fields.
arXiv:2605.18670v1 Announce Type: new
Abstract: Risk-limiting audits (RLAs) are post-election auditing procedures that rigorously guarantee a specified maximum probability that an incorrect electoral outcome will not be detected. Aside from ready access to physical ballots, known RLAs require a software-independent accounting of the sizes of each ballot batch, called a ballot manifest. While typical electoral procedures automatically provide rough estimates for batch sizes, even slight inaccuracies (commensurate with the margin of the contest under audit) completely invalidate conventional RLAs (Lindeman et al., EVT 2012). Thus, establishing a sufficiently accurate manifest often requires handling every ballot and can be the dominant cost of conducting the RLA.
We propose two new risk-limiting techniques: 1) A statistical mechanism for ensuring that the batch sizes reported by an untrusted tabulation are, in fact, an accurate manifest; this effectively bootstraps from a rough manifest to an accurate one with sublinear effort. 2) We propose a new class of RLAs called direct ballot selection. This method reverses the traditional comparison procedure and compares uniformly selected ballots against their cast vote records, requiring a new statistical test for identifier duplication but efficiently supporting elections without in order identifiers.
These techniques reduce the complexity of RLAs across many elections. Our two main findings are as follows: 1) The time to create a manifest can be drastically reduced with a modest increase in the number of ballots sampled in the audit. At a 3% margin and a large population, there is a reduction in the overall audit time of at least an order of magnitude across methods. 2) Direct ballot selection improves over state-of-the-art polling for small margins. For Connecticut (29th in population) at a 1% margin, it beats Minerva (Security 2022) by 55% in ballot sample complexity.
arXiv:2605.18668v1 Announce Type: new
Abstract: Interactions of relativistically intense laser pulses with structured targets have long been explored for controlling energy absorption and particle acceleration. However, at upcoming multi-petawatt laser facilities, the survivability of such nanostructures under realistic temporal contrast conditions remains a key concern. We report an experimental and simulation study of nanowire targets irradiated by the ELI-NP 1-PW laser without a plasma mirror. At the built in, readily available contrast of $10^{-10}$, the nanowires survive the laser pre-pulse and produce a robust enhancement in relativistic electron flux, energy, and directional emission compared to flat targets indicating that at better contrasts they can show similar enhancement at the 10 PW level. These results establish nanowire targets as resilient and reliable tools for relativistic electron manipulation at state of the art facilities.
arXiv:2605.17732v1 Announce Type: new
Abstract: In this paper, we consider the non-Hermitian quaternion linear systems arising from color image restoration and three-dimensional signal filtering problems. For exploring to solve such systems, we present two innovative structure-preserving conjugate gradient-type methods, QNHERLQ and QNHERQR, which are based on the unitary equivalence transformations of the non-Hermitian quaternion matrices to tridiagonal forms, called quaternion Saunders-Simon-Yip tridiagonalization procedure. The proposed tridiagonalization procedure for non-Hermitian quaternion matrices is closely related to the quaternion Lanczos process for Hermitian matrices, and is very different from the quaternion Lanczos biorthogonalization process for non-Hermitian matrices. The convergence of QNHERLQ and QNHERQR is discussed, which depends on the singular values of the coefficient matrix. Also we show that both algorithms have the finite termination property and constant costs per iteration step. Numerical results illustrate that the proposed algorithms are with the robustness and effectiveness compared with QGMRES and QQMR.
arXiv:2605.17734v1 Announce Type: new
Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.
arXiv:2509.17666v2 Announce Type: replace
Abstract: Object insertion tasks are prone to failure under pose uncertainty and environmental variation, often requiring manual fine-tuning or controller retraining. We present a novel approach for robust and resilient object insertion using a passively compliant soft wrist that enables safe contact absorption through large deformations, without high-frequency control or force sensing. Our method structures insertion as compliance-enabled contact formations, sequential contact states that progressively constrain degrees of freedom, and integrates automated failure recovery strategies. Our key insight is that wrist compliance permits safe, repeated recovery attempts; hence, we refer to it as compliance-enabled failure recovery. We employ a pre-trained vision-language model (VLM) that assesses each skill execution from terminal poses and images, identifies failure modes, and proposes recovery actions by selecting skills and updating goals. In simulation, our method achieved an 83% success rate, recovering from failures induced by randomized conditions, including grasp misalignments up to 5 degrees, hole-pose errors up to 20 mm, fivefold increases in friction, and unseen square/rectangular pegs, and we further validated the approach on a real robot. Project page is available at https://omron-sinicx.github.io/compliance-enabled-failure-recovery/.
arXiv:2604.06223v2 Announce Type: replace
Abstract: With the international business landscape becoming more crisis-ridden as risks proliferate, how do the professionals who implement corporate social initiatives in high-risk environments perceive their work, and what can this reveal about the forces shaping business engagement with society in crisis contexts? We present findings from a synthetic survey of 400 corporate professionals working on social impact in fragile and conflict-affected settings to understand conventional wisdoms and best practices on corporate strategy and activity in high-risk settings. Drawing on political corporate social responsibility (CSR), synthetic survey, and international business literatures, we test seven hypotheses about how regulatory environments, political polarization, sector characteristics, and organizational structures shape corporate social engagement in high-risk contexts. The synthetic results suggest that European professionals report significantly higher strategic integration of social impact across all measured dimensions, while US professionals overwhelmingly report that political polarization hinders social initiatives, yet this perception does not predict unreported social activities, complicating the emerging "quiet CSR" narrative. Extractive industry professionals deliver both the highest operational preparedness and the highest complicity awareness, a pattern we conceptualize as presence-dependent reflexivity. These patterns deliver a baseline to detect the theorized dynamics and offer preliminary theoretical propositions for future real-world empirical testing.
arXiv:2509.22061v2 Announce Type: replace-cross
Abstract: Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker identity. Because SC is constrained to a single audio stream, it offers a more direct setting for probing biases in speech foundation models than dialogue does. In this work we present the first systematic evaluation of bias in SC, investigating how gender and phonation type (breathy, creaky, end-creak) affect continuation behaviour. We evaluate three recent models: SpiritLM (base and expressive), VAE-GSLM, and SpeechGPT across speaker similarity, voice quality preservation, and text-based bias metrics. Results show that while both speaker similarity and coherence remain a challenge, textual evaluations reveal significant model and gender interactions: once coherence is sufficiently high (for VAE-GSLM), gender effects emerge on text-metrics such as agency and sentence polarity. In addition, continuations revert toward modal phonation more strongly for female prompts than for male ones, revealing a systematic voice-quality bias. These findings highlight SC as a controlled probe of socially relevant representational biases in speech foundation models, and suggest that it will become an increasingly informative diagnostic as continuation quality improves.