Computer Science (arXiv)

Evaluation conclusions depend on evaluator-controlled semantics: legal references, scoreability, and aggregation. We call an artifact-defined endpoint Q(s) evaluation-semantically identified when it is invariant over a declared family. A frozen 217-row analysis appears stable within its restricted contract family. In TraceElephant, F_asym yields precise task-disjoint adoption effects from -40.76 to -43.03 percentage points, whereas both jointly frozen contrast-comparable treatments in F_cc yield exactly zero with [0, 0] intervals. Their union F_audit therefore does not identify T, even though F_cc identifies T = 0. A factorial audit attributes 100 percent of the disagreement to one-sided terminal deletion, with zero nonterminal contribution. Rankings remain specification-dependent across the symmetric treatments. This is a localized non-implication witness and reusable family-indexed audit, not a prevalence estimate, exhaustive semantic taxonomy, or independent replication.

Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach.

LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts alongside user queries creates an attack surface: adversarial inputs can induce models to disclose them. Prior probing studies suggest that leakage-related signals emerge in hidden states, yet the need to extract these states poses additional deployment challenges. In this paper, we explore whether this internal signal leaves a more accessible ``tell'' before decoding. We propose LeakGauge, which probes this response by appending a suffix that gauges leakage behavior and mapping its prefill token probabilities to an attack-risk score. While a direct gauge uses the initial tokens of confidential content, we find that a content-agnostic one that verbalizes leakage behavior yields more robust signals. Across 11 LLMs, including GLM-5.2 (753B) and Kimi-K3 (2.8T), LeakGauge reaches an AUROC range of 0.944--0.996 on unseen attacks. The signal remains stable when the content changes language or the attack shifts from verbatim to semantic disclosure. By activation-steering interventions, we further show that the risk score is sensitive to an internal leakage-related direction, relating the observable signal to the model's internal representation. In addition, LeakGauge enables an input detector with fewer than 0.5K extra parameters and added latency of 10.34 ms. Code: \href{https://github.com/yeasen-z/LeakGauge}.

Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily reflect English-language and US-centric settings, and often only evaluate task performance. In this paper, we present first results of MÖVE, a holistic evaluation framework for the German public sector, examining three rarely considered governance dimensions: energy consumption, provider transparency, and knowledge of German-party positions. Our results reveal significant trade-offs, with no single model excelling across all dimensions: estimated energy consumption varies more than 60-fold and is not explained by model size alone, information disclosure varies systematically across providers, and European models do not exhibit stronger knowledge of German party positions. Model selection for public institutions thus cannot rely on performance rankings alone. Instead, evaluations should also reflect the governance requirements of the deployment context.

Hierarchical KV-cache systems can retain long-context LLM execution state beyond GPU memory, but retention capacity does not determine the local memory required to make that state executable again. We isolate this second resource as the restoration working set (RWS): the peak local staging state whose lifetimes overlap during restoration. In the pinned upstream LMCache whole-plan path, measured full-reuse points for 1.956, 7.823, and 15.646 GiB/rank states first succeed at 2, 8, and 16 GiB L1 rungs, with successful L1 peaks of 1.956, 7.824, and 15.648 GiB/rank. We introduce Bounded-State Restoration (BSR), which separates complete discovery from local residency. BSR probes the complete reusable prefix without materializing the whole hit in L1, then installs confirmed state through a reusable window of at most $W$ chunks. Under bounded auxiliary state, peak restoration capacity is $O(W)$ while total transfer and installation work remains $Θ(|S|)$. Because reusable state spans heterogeneous allocator groups and tensor-parallel ranks, BSR uses a request-level commit rule: partial installation is never exposed as a valid reusable prefix; failures invalidate the advertised prefix and fall back to a lower valid tier or deterministic recomputation. On DeepSeek-V4-Flash with TP=2 across two DGX Spark nodes, a clean no-resume sweep grows external state from 1.956 to 31.277 GiB/rank while measured L1 RWS remains exactly 500.75 MiB/rank at $W=32$, a 63.959x largest-state external-to-live-staging ratio. A second fresh 524K-token run repeats the largest-state acceptance result. Evaluated tier and rank-asymmetric failures expose either complete reuse or zero external reuse before fallback. A matched SSD optimization reduces 512K restore TTFT from 43.1 to 17.6 seconds without changing RWS.

The traditional Software Development Lifecycle (SDLC) assumes that system behavior is determined primarily by source code, allowing correctness to be specified, implemented, and verified through code-centric practices. Data-intensive and AI-enabled systems challenge this assumption because their behavior emerges from the interaction of code, data, and learned models, while performance may degrade as real-world conditions drift from training data. This paper examines how integrating data engineering and software engineering practices, operationalized through DataOps, MLOps, and LLMOps, reshapes the SDLC for these systems. We make four contributions. First, we synthesize literature across software engineering, data management, machine learning systems, and human-centered computing into a phase-structured account of lifecycle transformation spanning requirements, architecture, development, testing, deployment, monitoring, governance, and organization. Second, we provide a lightweight formalization in which system behavior is defined over code, data, and model configurations; requirements become evaluation-led specifications with probabilistic acceptance regions; and promotion is controlled through statistically grounded validation gates. Third, we develop an adaptive five-layer lifecycle framework comprising artifact, contract, gate, control, and governance layers, positioning maintenance as a closed-loop control problem under configuration drift. Fourth, we propose a conceptual research model linking data engineering integration to measurable lifecycle outcomes and critically assess the evidence base. While the direction of transformation is increasingly established, its magnitude remains insufficiently quantified. We conclude with a research agenda for an empirically grounded, adaptive SDLC for data- and AI-centric systems.

Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series samples, gathered across 153 simulator rides from 51 participants under No, Low, and High TP scenarios. Across each sequence, we capture 64 distinct attributes covering vehicle motion, rider control actions, spatial proximity, and rule compliance indicators. Using this dataset, we introduce MotoSafety, a new edge-AI framework built on the Learned Temporal Importance (LTI) concept. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems.

Accurate building height information at the individual footprint scale is essential for material stock accounting and post-disaster damage assessments yet remains difficult to obtain at city scale in the Global South where airborne LiDAR coverage is rare and commercial very high-resolution imagery is cost-prohibitive or unavailable. While recent works have demonstrated building height estimation using freely available Sentinel imagery, the resolution ceiling of resulting products is still coarse for material stock analysis. This study incorporates products derived from data freely accessible under scientific research licenses, TerraSAR-X StripMap and PlanetScope, alongside Sentinel-1 to predict building heights in a large city in Brazil. To account for the spatial autocorrelation in the training set, features from all sources are integrated in a geographically weighted random forest model, returning an RMSE of 5.34 m and R2 of 0.756 against a LiDAR reference dataset. Local feature importance showed predictor dominance to vary consistently across intra-urban contexts, with footprint geometry dominating for low-rise buildings, shadow-derived height for taller and more isolated structures, and spectral reflectance for the tallest buildings in the set. Sentinel-1 backscatter and InSAR occupy complementary spatial niches, with no single sensor uniformly preferable across the set. Results provide optioneering guidance and insight over satellite-derived products predictive relevance in distinct contexts, which global machine learning or neural network models cannot offer.

Aerial manipulation extends robotic operations to previously inaccessible aerial environments. Unlike arm-equipped aerial systems, tiltable-multirotors can directly generate six-degree-of-freedom wrenches through their flight bases, enabling both efficient movement and omnidirectional operation by tilting the thrust direction. This work presents a design analysis and a wrench-based control framework for tiltable-multirotors in aerial manipulation. We show that a four-rotor tiltable configuration provides a balance between interference-free propeller sizing and hovering efficiency across different attitudes, and its null-space redundancy is crucial for traversing singular configurations under physical constraints. We further show that an upward end-effector placement yields a favorable trade-off between geometric clearance and available wrench. To address disturbances, we propose a dual strategy consisting of a modified integral term for model error and an acceleration-based estimator for external wrenches. Building on these insights, we develop an effector-centric nonlinear model predictive control (NMPC) framework that integrates design choices, singularity handling, and disturbance compensation into a unified formulation. The proposed framework runs fully onboard at 100 Hz on a custom-built tiltable-quadrotor. Real-world experiments, including a 90-deg step cartwheel rotation, whiteboard pushing, and continuous 360-deg valve turning, demonstrate the feasibility of wrench-based omnidirectional manipulation with singularity traversal on a one-DoF-per-arm tiltable-quadrotor.

We show that Integer Quadratic Programming is W[1]-hard parameterized by the number of variables. Thus, under standard complexity assumptions, Integer Quadratic Programming cannot be solved in f(n)|I|^{O(1)} time for any computable function f where |I| is the size of the encoding and n is the number of variables.

This overview article presents arguments why the computational study of Pop music culture needs to be conducted in a multi-modal way beyond mere audio analysis, gives a survey of already published quantitative work on analyzing Pop music at scale, and discusses challenges and promising research avenues for future work. We argue that Pop music culture is a rich tapestry of audio, visual, textual and cultural connotations and relations which needs to be studied in an integrative way as a multi-modal socio-cultural phenomenon. What is needed is an approach which is reminiscent of "distant reading", i.e. algorithmic analysis of thousands of books as a research tool in digital humanities. In addition to listening to audio, algorithms need to view album artwork and music videos, to read meta-information, lyrics, music magazines and books. Our review of already available work on distant reading/listening/viewing and multi-modal combinations thereof reveals two major open issues: a scarcity of truly multi-modal approaches and questionable external validity rooted in sampling practices when building music corpora. In trying to overcome these shortcomings we sketch three exemplary avenues for future research on Pop music culture: charting the topic universe of music lyrics, providing an iconography of album cover art, tracking retro cycles in music's timeline.

The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive constructs. Challenging this assumption, we investigate whether the latent factors governing LLM performance carry the same substantive, human-interpretable meaning as the cognitive constructs governing human learners. Using responses from humans and six LLMs across quantitative reasoning and chemistry assessments, we conducted Exploratory Factor Analysis (EFA) separately for both groups. Subject-Matter Experts (SMEs) then blindly evaluated the resulting factor graphs to ascribe pedagogical meaning to the emerged constructs. SMEs successfully interpreted most of the human-derived factors. Conversely, they could not ascribe meaning to any LLM-derived factors in quantitative reasoning and interpreted only half of the LLM factors in chemistry. By combining data-driven EFA with blind expert interpretation, this framework shows that LLMs frequently operate on statistically opaque mechanisms distinct from human reasoning.

Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of the weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief; chains of thought that explicitly fact-check show lower accuracy on false information than those that do not; and a single instruction can reverse the failure across verb families. Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods. Our findings clarify prior results and show how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs. Our code is available at https://github.com/ngqm/belief-fact-phrasing.

We present an optical random access memory (ORAM) based on warm cesium (Cs) atomic vapor and demonstrate its operation as the physical substrate of a reservoir computer. Information is stored in the hyperfine population distribution of a Cs ensemble via optical pumping and retrieved through differential probe absorption. Spatial multiplexing via acousto-optic deflection provides eight addressable memory rails able to store up to 3.8 bits of information per rail. Employing this platform as a temporally multiplexed reservoir, we achieve a kernel rank ($\mathrm{KR}= 8.8 \pm 0.4$), and a minimum bit error rate of $0.02 \pm 0.01$ on the Exclusive-or (XOR) benchmark. We find the limited memory lifetime constrains the achievable temporal depth, encouraging further research into fast addressable memories. This constitutes the first demonstration of a free-space, optically writable atomic RAM as a substrate in an optical reservoir computing system.

Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, terminal training-rollout audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probes that miss endpoint changes, and rewards that can select broad-topic answering with low semantic leakage during optimization.

Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures.

Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below. For the normalized Rademacher sum, we determine how its higher moments depend on the fourth-order mass. Combining a sharp fixed-q moment envelope with a separate argument below the convexity threshold gives the Gaussian stability inequality for the full range $p\geq4$ of this linear-in-q bound. The same fourth-order framework determines the sharp finite dimensional $L_p/L_4$ Khintchine constant for $p\geq5$, with the flat coefficient vector as the extremizer. These results settle the conjectures of Jakimiuk and of Barański, Murawski, Nayar, and Oleszkiewicz stated below. We also prove Jakimiuk's conjectured quadratic stability estimate at $p=3$. The resulting bounds retain information about sparsity and effective dimension, with applications to Rademacher random projections and randomly signed errors; those applications are not developed further here. Their Laplace-transform form also gives coefficient-sensitive tail bounds. The proofs are discovered with substantial assistance from ChatGPT 5.6 Sol.

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks.

Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal contrast, and the scarcity of annotated data. This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data. We show that synthetic data provides an effective basis for learning initial object representations, while real in-domain thermal imagery is still essential for reliable deployment. Even small amounts of real IR data substantially reduce domain gaps. Our experiments indicate that dataset alignment has a stronger impact on performance than model scale. Finally, our analysis of the dataset suggests that semantic alignment in feature space is the strongest predictor of model performance, while radiometric properties such as entropy and dynamic range also contribute to detection robustness. This work provides a foundation for combining synthetic and real IR data for effective G2A drone detection.

Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness against adaptive adversaries. Detectors trained on hand-crafted attacks with fixed scaling multipliers degrade catastrophically (F1-score drops of about 47 percent to 100 percent, depending on scenario) when confronted with realistic, distribution-preserving samples. We propose Diff-DDoS, a three-phase framework for realistic attack synthesis and robust detection using tabular diffusion models. Phase 1 trains a baseline CNN cell-level detector on spatiotemporal grids from call detail records (CDRs). Phase 2 trains a tabular denoising diffusion probabilistic model (TabDDPM) on normal CDR aggregates to generate realistic attacks and expose detector vulnerabilities. Phase 3 introduces adversarial diffusion training (ADT), using inverse classifier guidance to generate hard yet distribution-preserving samples until the detector converges. On a Milano CDR dataset across SMS-flooding, silent-call, Internet-signaling, and blended scenarios, ResNet50 with ADT recovers F1-scores of 79.62 percent (silent-call), 100 percent (Internet), and 92.79 percent (blended). After validation-based threshold calibration, ADT reaches 100 percent SMS F1 versus 47.3 percent for CTGAN, and matches the strongest gradient-based adversarial-training baseline on silent-call. These results support tabular diffusion models for stress-testing and hardening intrusion detectors in data-scarce 5G cyber-physical deployments.

Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled candidate SQLs and assigning correctness scores to unseen queries, yet they still provide limited visibility into the signals behind each verification. To address this limitation, we propose TraceSQL, a lightweight and traceable verification model built on explicit diagnostic features. TraceSQL combines 67 features capturing question ambiguity, question requirements, question-schema-SQL consistency, SQL structure, and intent alignment. These signals remain available for examining which factors influence each prediction and for tracing decisions back to diagnostic evidence. On BIRD development databases, TraceSQL achieves 66.47% F1 and 64.48% ROC-AUC, compared with 61.87% F1 and 58.26% ROC-AUC for the GradeSQL-7B ORM baseline on the same generated-SQL evaluation. Feature attribution further shows that the model relies on both semantic grounding and deterministic SQL-structure signals. These results show that SQL verification can be performed with a lightweight learned model while retaining feature-level evidence for inspecting and diagnosing its predictions.

Vehicular consumer electronics increasingly support computation-intensive and latency-sensitive services, imposing stringent efficiency, reliability, and security requirements on vehicular edge computing (VEC) systems. In dynamic vehicular environments, inference-based information leakage and anomalous communication behaviors further threaten system performance and data privacy. To address these challenges, this paper proposes a UAV-assisted cooperative VEC architecture that integrates threat-aware task offloading with intelligent spatiotemporal caching across roadside units (RSUs) and UAV edge nodes. A security-aware uplink transmission model is developed to capture potential information leakage risks and abnormal communication patterns, enabling adaptive offloading decisions. We formulate a joint optimization problem to minimize end-to-end task execution delay while improving cache utilization under limited computing and storage resources. To efficiently solve this problem, a Threat-Aware Joint Optimization (TAGO) framework is designed by combining proximal policy optimization for adaptive task offloading and a gradient-based caching update derived from the Frank-Wolfe algorithm to capture spatiotemporal service popularity. Simulation results demonstrate that the proposed approach significantly reduces task delay and improves cache efficiency compared with several baseline strategies, showing its effectiveness for secure and efficient UAV-assisted vehicular consumer electronics systems.

Near maximum distance separable (NMDS) codes of dimension 3 and length n over the finite field with q elements are equivalent to (n,3)-arcs in PG(2,q). For every odd prime power q we construct, by adding five suitable points to a conic of PG(2,q), a family of [q+6,3,q+3] NMDS codes and determine their weight distributions completely; three distinct weight enumerators occur, governed by two explicit quadratic-character conditions on the parameters. For every odd prime power q, no code of our family is monomially equivalent to a code of the recent [q+6,3,q+3] NMDS family of Fan, Wang and Xu, even where the weight enumerators of the two families coincide: the separating invariant is a triple of geometric data attached to the underlying arc. Extending the configuration by a sixth point on a distinguished external line, we further obtain [q+7,3,q+4] NMDS codes, together with their weight distributions, for every odd prime power q >= 11 (admissible parameters exist for no q <= 9); the existence proof combines exact and Weil-type character sum estimates with a finite computer verification. Our proofs are purely geometric and rest on a simple counting identity for the trisecant lines of a point set obtained by extending a conic. All the codes constructed are optimal locally recoverable codes with locality 2.

Dynamic vision sensors (DVS) are enticing candidates to reach the low-latency, sub-ms target of edge-vision applications, as they generate events with a $μ$s-level time resolution. However, using DVS front ends also calls for novel algorithm/hardware back ends capable of efficiently handling streams of sparse spatiotemporal events. While event-driven graph neural networks (EV-GNNs) have emerged as a solution on the algorithmic side that is both accurate and efficient, there is no dedicated hardware to date capable of efficiently supporting their mixed requirements of dense-regular compute operations and sparse-irregular memory accesses. We therefore introduce ETHEREAL, the first EV-GNN processor chip, capable of bridging this gap by means of a neighbor-parallel spline-convolution engine combined with a split-2D/3D memory hierarchy that introduces a novel spatiotemporal event-caching mechanism. Measurement results demonstrate a 25.6$μ$s latency and a 1.6$μ$J energy per end-to-end event-wise inference on the state-of-the art DAGr-GNN workload and VGA-resolution (640x480 pixels) DSEC dataset.

ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than input-local interactions. We test this in retrieval-augmented generation (RAG), where evidence utility can be measured under controlled interventions. Holding query, evidence, task, scoring, and intervention fixed, nine readers disagree on effect sign in 33\% of jointly affected cells; reader$\times$query interaction explains 29.8\% of utility variance versus an 8.4\% permutation null; and self-selected evidence improves F1 by $+0.031$ ($t=3.39$). We then ask the sharper question: \emph{which components of this heterogeneity are stable reader properties across queries?} Separating three measurable objects---evidence \emph{activity}, \emph{ordinal preference}, and \emph{conditional signed direction}---we find ordinal reader geometry stable across four independent settings (split-half $ρ=0.60$--$0.83$): leave-one-out interventions, PRISM preferences, RAMDocs, and RAGuard. Signed geometry is task-bounded: weak in open-ended QA (0.14, 0.35), especially for misleading and irrelevant evidence, but strong in binary fact-checking (0.75) with no significant ordinal gap, though still below its sparsity-matched ceiling. Sparsity, decoding noise, and metric artifacts do not explain the main ordinal--signed gap. Finally, stable ordinal similarity fails to predict cross-reader intervention transfer (oracle-distance $ρ=-0.27$; regret reliability $-0.28$). Reader-specific utility exists, but preference is not intervention: stable ranking similarity does not license transfer of help/harm decisions.