Forskningsradar

Science Journals

Peer-reviewade publikationer — 56237 artiklar

arXiv (fysik & CS) Preprint 2026-07-15
Accuracy and Normalized Accuracy under Length Bias: Analysis, Guidelines, and a Bayesian Alternative
arXiv:2607.12767v1 Announce Type: new Abstract: Multiple-choice benchmarks that rank candidate completions by conditional log-probability suffer from a length bias: because log-probabilities sum over tokens, longer answers tend to be penalized relative to shorter ones in practice. A common mitigation is to normalize scores by completion length, but we show empirically that this heuristic frequently over-corrects, introducing a bias toward longer answers instead. We first analyze these scoring rules, characterizing when standard and length-normalized accuracy are appropriate and how their length biases depend on the distribution of completion lengths. Motivated by this analysis, we introduce \emph{Bayesian accuracy}, a scoring rule that computes the posterior probability of each candidate under an explicit prior over answer length, thereby removing linear length effects. Bayesian accuracy is a drop-in replacement for likelihood-based multiple-choice evaluation, requires no additional forward passes, and consistently exhibits lower empirical length bias than both standard and length-normalized accuracy across benchmarks and few-shot settings.
arXiv (fysik & CS) Preprint 2026-07-15
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
arXiv:2602.02244v3 Announce Type: replace Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore. Adding entropy regularization during SFT is not a cure-all; it tends to flatten token distributions toward uniformity, increasing entropy without improving meaningful exploration capability. In this paper, we propose CurioSFT, an entropy-preserving SFT method designed to enhance exploration capabilities through intrinsic curiosity. It consists of (a) Self-Exploratory Distillation, which distills the model toward a self-generated, temperature-scaled teacher to encourage exploration within its capability; and (b) Entropy-Guided Temperature Selection, which adaptively adjusts distillation strength to mitigate knowledge forgetting by amplifying exploration at reasoning tokens while stabilizing factual tokens. Extensive experiments on mathematical reasoning tasks demonstrate that, in SFT stage, CurioSFT outperforms the vanilla SFT by 2.5 points on in-distribution tasks and 2.9 points on out-of-distribution tasks. We also verify that exploration capabilities preserved during SFT successfully translate into concrete gains in RL stage, yielding an average improvement of 5.0 points.
arXiv (fysik & CS) Preprint 2026-07-15
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
arXiv:2602.04029v2 Announce Type: replace Abstract: Relational Foundation Models (RFMs) facilitate data-driven decision-making by learning from complex multi-table databases. However, the diverse relational databases needed to train such models are rarely public due to privacy constraints. While there are methods to generate synthetic tabular data of arbitrary size, incorporating schema structure and primary-foreign key connectivity for multi-table generation remains challenging. Here we introduce PLUREL, a framework to synthesize multi-tabular relational databases from scratch. In a step-by-step fashion, PLUREL models (1) schemas with directed graphs, (2) inter-table primary-foreign key connectivity with bipartite graphs, and, (3) feature distributions in tables via conditional causal mechanisms. The design space across these stages supports the synthesis of a wide range of diverse databases, while being computationally lightweight. Using PLUREL, we observe for the first time that (1) RFM pretraining loss exhibits power-law scaling with the number of synthetic databases and total pretraining tokens, (2) scaling the number of synthetic databases improves generalization to real databases, and (3) synthetic pretraining yields strong base models for continued pretraining on real databases. Overall, our framework and results position synthetic data scaling as a promising paradigm for RFMs.
arXiv (fysik & CS) Preprint 2026-07-15
Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliability
arXiv:2607.12056v1 Announce Type: new Abstract: Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and carry out parts of the purchasing process for users. Website design must now support both human and agent-mediated interaction. This paper introduces the agent-ready website, a design framework for enhancing the readability, interpretability, verifiability, and actionability of e-commerce platforms for AI agents. Existing web design, SEO, and generative engine optimization (GEO) metrics do not fully assess a website's capacity for agent-mediated interaction. The proposed framework is structured around three dimensions agent interpretability, agent executability, and agent decision reliability supported by features such as machine readability, semantic clarity, agent actionability, and contextual decision-reliability signals. The framework is evaluated through a controlled experiment comparing a human-oriented baseline and an agent-ready version of an identical website prototype, with identical catalogs, pricing, stock, and shopping workflows. The evaluation involved five tasks, three browser-agent models (GPT-4.1, Gemini-2.5 Flash, and Grok-4 Fast), and 300 runs, measuring PASS,PARTIAL,FAIL outcomes, strict and functional success rates, error patterns, step counts, and token consumption. The agent-ready website achieved 134 PASS runs out of 150 versus 74 out of 150 for the baseline (strict success rates of 89.3% vs. 49.3%), with the largest gains in product detail extraction, comparison, and multi-constraint selection. It also reduced PARTIAL outcomes from 43 to 3 and lowered the average step count from 9.31 to 6.49. These results provide preliminary evidence that enhanced structural clarity, action cues, evidence signals, and temporal validity indicators can substantially improve the reliability and efficiency of AI browser agents.
arXiv (fysik & CS) Preprint 2026-07-15
Predicting Acceptance and Review Effort in Human and Agent Pull Requests
arXiv:2607.12057v1 Announce Type: new Abstract: Pull requests (PRs) are a central mechanism for reviewing and integrating code changes in modern software repositories. As AI coding agents begin to submit more code changes alongside human developers, maintainers face a new challenge: deciding which PRs are likely to be accepted and which ones may require substantial review effort. This paper studies whether such outcomes can be estimated at the time a PR is opened, before reviewer discussion, CI feedback, or merge decisions are available. Using the AIDev dataset, we construct a leakage-aware prediction pipeline for human- and agent-authored PRs. The feature set is limited to submission-time information, including PR text characteristics, metadata, repository context, temporal signals, and lightweight diff statistics. We evaluate classical machine-learning models, including Logistic Regression, Random Forests, Gradient Boosting, Extra Trees, and MLPs, across pooled, human-only, agent-only, and balanced contributor views. Our results show that acceptance prediction is feasible from early signals: tree-based models achieve F1 scores above 0.95, with textual clarity and metadata among the most influential predictors. Review-effort prediction is more difficult. Comment counts and time-to-merge are only modestly explained by submission-time features, suggesting that reviewer availability, project workflow, and team-specific review practices play a major role. These findings indicate that early PR models can support triage and reviewer prioritization, but should be used as advisory tools rather than automated decision-makers.
arXiv (fysik & CS) Preprint 2026-07-15
The Benjamini--Hochberg Procedure Can Fail to Control the FDR for Correlated Two-Sided Gaussian Tests
arXiv:2607.12208v1 Announce Type: cross Abstract: We show that the Benjamini--Hochberg procedure can fail to control the false discovery rate (FDR) at its nominal level for correlated two-sided Gaussian $p$-values. We construct a factor model for which, at level $\alpha=0.01$, a rigorous interval-arithmetic certificate proves $FDR>0.0104$ for all sufficiently large numbers of hypotheses. This disproves a conjecture widely believed to be true for twenty years. Monte Carlo experiments are consistent with the theoretical result. The proof was obtained by GPT-5.6 Pro and carefully checked by the author.
arXiv (fysik & CS) Preprint 2026-07-15
Partial Identification with Multiple Nonlinear Measurements of a Latent Regressor
arXiv:2607.12219v1 Announce Type: cross Abstract: We study linear regression when the regressor is latent and observed only through multiple noisy measurements, each a smooth but possibly nonlinear function of the latent variable. The problem is acute in the measurement of occupational exposure to artificial intelligence, where competing scores yield downstream estimates that differ by a factor of eleven. A regression on any single measurement recovers a source-specific coefficient rather than the structural one. We fix the latent scale by requiring the consensus measurement function to be linear and bound the remaining curvature heterogeneity across sources relative to slope. Under this bound, the structural coefficient lies in a closed-form interval centered at a symmetric cross-source estimator. The interval is invariant to unknown source loadings, and its half-width is second order in the curvature bound and sharp to the same order. With at least four measurements, the bound is estimable from the joint distribution of the sources through a split-instrument auxiliary regression, and Imbens-Manski confidence intervals with the Stoye critical value attain uniform coverage over the curvature class, including at the point-identified boundary. The application matches six exposure measures to an American Community Survey panel of 8.88 million person-year observations for 2015 to 2024. The post-2022 employment coefficient changes sign between the language-model measures and the Webb patent-text measure, and an ex ante factor-analytic rule separates the Webb measure as a distinct construct. The five retained sources yield a loading-invariant consensus coefficient of -0.239, with a partial-identification half-width of 1.23 percent of the point estimate, or 1.88 percent at the one-sided 95 percent upper bound on the curvature. We read the application as measurement reconciliation rather than as a causal estimate of AI displacement.
arXiv (fysik & CS) Preprint 2026-07-15
Physically Consistent Parameter Inference: Transparent Machine Learning Emulation in High Energy Physics and Cosmology
arXiv:2607.12726v1 Announce Type: cross Abstract: Global fits in high energy physics and cosmology often face the challenge of exploring high-dimensional parameter spaces with computationally expensive or topologically complex likelihood functions. In this work, we present a Machine Learning framework designed to emulate complex, often non-Gaussian likelihood landscapes using gradient-boosted regression trees (XGBoost). We discuss the advantages of the Machine Learning approach in terms of computational efficiency and the resolution of confidence regions, particularly in scenarios with complex correlations or "curved" degeneracies. We validate this methodology by applying it to a recent analysis on flavour anomalies in semileptonic $B$ meson decays and discussing the adaptability of this framework to other phenomenological systems, such as axion-like particles or cosmology global fits. Finally, we utilise SHAP (Shapley Additive exPlanations) values to provide a transparent analysis of feature importance, ensuring that the Machine Learning predictions remain physically interpretable and consistent with the underlying physics.
arXiv (fysik & CS) Preprint 2026-07-15
picoMUX: microcontroller based time-domain multiplexing readout for kilopixel TES arrays
arXiv:2607.13004v1 Announce Type: cross Abstract: Advances in cryogenic SQUID-based time-domain multiplexing (TDM) have outpaced their warm readout electronics. Next generation CMB telescopes are baselining kilopixel TES arrays with few viable electronic options. We present picoMUX, a new TDM readout electronics architecture that replaces the FPGA typically used in such systems with a complement of modern microcontrollers. Designed around the current generation NIST multiplexer, it fully exploits its differential nature and two-level switching. The system achieves the desired timing metrics (sub {\mu}s row dwell time) while reducing cost, complexity, and power consumption over a comparable FPGA solution. Preliminary noise measurements are consistent with expectations and show no evidence that the novel architecture introduces excess noise. picoMUX demonstrates how recent advances in microcontrollers enable simpler, low-power, low-cost TDM readouts for kilopixel TES arrays.
arXiv (fysik & CS) Preprint 2026-07-15
Image Matching Filtering and Refinement by Planes and Beyond
arXiv:2411.09484v5 Announce Type: replace Abstract: This paper provides a consistent and extensive evaluation of state-of-the-art filtering and refinement methods on common image matching pipelines. Unlike previous comparisons, the designed benchmark also takes into account the more general, real, and practical cases where camera intrinsics are unavailable. Moreover, a novel and effective strategy combining non-deep traditional computer vision approaches based on planar constraints and cross correlation is presented. Experimental analysis provides several insights for current application design and future research directions. In particular, the choice of a proper evaluation protocol discloses the effective differences within the compared solutions which otherwise would tend to flatten. Moreover, the proposed classical algorithmic approach is competitive with recent deep methods. Besides providing robust baseline using traditional computer vision for the evaluation of deep-based methods, this knowledge is useful to improve and better understand the deep image matching architectures. On one hand, geometry-based filtering is effective in presence of outliers without degrading already robust deep pipelines; on the other hand cross-correlation refinement is valid in the case of corner-like keypoints and allows to not directly discard inaccurate matches by default in deep pipelines but to retain and refine them for achieving a better coverage of the scene.
arXiv (fysik & CS) Preprint 2026-07-15
Auditable Context-Aware HFMD Forecasting with Structured LLM Agents
arXiv:2511.23276v2 Announce Type: replace Abstract: Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and policy or surveillance reports. In clinical settings, forecasts must be trusted and actionable; thus, beyond point accuracy, decision-makers require concise, auditable explanations of why risk is expected to rise or fall. Classical models (e.g., ARIMA and Prophet) and foundation models (e.g., Chronos, Moirai, and TimesFM) treat external covariates as numerical inputs, lacking semantic reasoning to reflect epidemiological mechanisms or resolve conflicting signals. We propose a two-agent neuro-symbolic framework that decouples contextual interpretation from probabilistic forecasting. An LLM-based Event Interpreter ingests heterogeneous signals -- school schedules, weather summaries, government reports, and clinical guidelines -- and outputs a scalar transmission-impact signal. A Forecast Generator combines this signal with historical case counts to produce point forecasts that are mapped to probabilistic predictions through Poisson/negative-binomial moment matching. We focus on one-week-ahead rolling forecasts, aligning with weekly hospital-capacity planning and the rapid, context-driven inflections typical of HFMD. We evaluate on two datasets: Hong Kong surveillance (90 target weeks in 2023--2024) and Lishui hospital visits (33 target weeks in 2024). Against traditional and foundation-model baselines, our approach achieves competitive point accuracy while providing robust 90\% intervals (coverage approximately 0.85--1.00) and concise rationales. This demonstrates that integrating domain knowledge through LLM-based agents can match strong numerical forecasters while yielding interpretable, context-aware forecasts aligned with public-health decision-making.
arXiv (fysik & CS) Preprint 2026-07-15
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
arXiv:2512.01113v2 Announce Type: replace Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models. Prior work has evaluated reasoning for executing a single algorithmic task, whereas a more desirable objective is to perform multiple algorithmic reasoning tasks simultaneously. We start by noting that this is inherently difficult due to differences arising from the execution traces of the algorithms (such as depth- vs. breadth-first search), which cause interference when they are trained together. In this paper, we introduce {branching neural networks}, a new architecture for multitask algorithmic reasoning. The main idea is to search for a recursive tree-structured partition of $n$ algorithmic tasks into a $k$-ary tree (divided into $L$ layers). Naive search requires $O(k^{nL})$ complexity; we develop an algorithm that reduces this to $O(nL)$ by solving a convex relaxation at each layer to approximate an optimal partition. Our approach clusters these tasks using gradient-based affinity and can be used on top of any base model. We validate our approach on algorithmic reasoning benchmarks and their extensions with text descriptions. We show that gradient-based affinity scores help estimate true performance with less than 5% error, measured across eight different architectures with up to 34 billion parameters. On the CLRS benchmark, our approach outperforms existing graph neural networks by 3.7% and baselines by 1.2%, while reducing runtime by 48% and memory usage by 26%. The learned branching structure shows a hierarchical clustering of related algorithms. On three text-based graph reasoning benchmarks, our approach improves over baseline methods by 3.2%. Finally, we validate our approach for overlapping community detection.
arXiv (fysik & CS) Preprint 2026-07-15
GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures
arXiv:2512.09925v2 Announce Type: replace Abstract: Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, the accuracy of these methods degrades under sparse-view settings, where limited observations lead to severe ambiguity between geometry, reflectance, and lighting. We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures), a two-stage inverse rendering framework that leverages foundation models as priors to stabilize geometry and material estimation. The core technical contribution of this paper is an inverse rendering framework that unifies foundation model priors with physically-based representations in an optimization scheme. GAINS first refines geometry using monocular depth, normal, and diffusion priors, and then employs segmentation, intrinsic image decomposition (IID), and diffusion priors to regularize material recovery. Extensive experiments on synthetic and real-world datasets show that GAINS significantly improves material parameter accuracy, relighting quality, and novel-view synthesis compared to state-of-the-art Gaussian-based inverse rendering methods. While GAINS outperforms and remains competitive across a wide range of objects captured with 4 to 32 cameras, the improvement is particularly pronounced under sparse-view settings, where ambiguity is high and learning-based priors become especially beneficial. Project page: https://patrickbail.github.io/gains/
arXiv (fysik & CS) Preprint 2026-07-15
AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts
arXiv:2512.14461v2 Announce Type: replace Abstract: Sleep is essential for health, yet studying its dynamics requires manual sleep staging, a labor-intensive step in research and clinical care. Across centers, polysomnography (PSG) recordings are traditionally scored in 30-s epochs for pragmatic, not physiological, reasons and vary in electrode count, montage, and subject characteristics. These constraints challenge harmonized multi-center studies and the discovery of robust biomarkers on shorter timescales. We present AnySleep, a deep neural network that scores sleep from any electroencephalography (EEG) or electrooculography (EOG) data at adjustable temporal resolutions. We trained and validated the model on over 20,000 overnight recordings (> 200,000 hours of EEG and EOG) from 28 datasets across multiple clinics to promote robust generalization across sites. The model attains state-of-the-art performance and surpasses or equals established baselines at 30-s epochs. Performance improves with more channels, yet remains strong when EOG is absent or only EOG or single EEG derivations (frontal, central, or occipital) are available. On sub-30-s timescales, the model captures short wake intrusions consistent with arousals and improves prediction of pathophysiological conditions (obstructive sleep apnea, narcolepsy type 1, insomnia) over 30-s scoring. We make the model publicly available to facilitate large-scale studies with heterogeneous electrode setups and accelerate biomarker discovery in sleep.
arXiv (fysik & CS) Preprint 2026-07-15
Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
arXiv:2512.15748v2 Announce Type: replace Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology, palynology, evolutionary biology, systematics, and phylogenetics. Automating VSR through machine learning can significantly accelerate these efforts. However, species-level annotation requires extensive domain expertise, making large-scale labeled datasets difficult to obtain. Consequently, few-shot learning (FSL) is a practical paradigm, where an expert model is trained using only a few labeled examples. Meanwhile, Large Multimodal Models (LMMs) have demonstrated unprecedented zero-shot visual recognition capabilities, raising the question of whether they can serve as an alternative to FSL expert models for VSR. We start this work with a systematic comparison between FSL expert models and LMMs, revealing that, despite advanced prompting strategies, contemporary LMMs significantly underperform FSL expert models. Interestingly, we find that LMMs possess a complementary strength: given an image and a shortlist of candidate species generated by an expert model, LMMs can often recover the correct label when the expert model's top prediction is incorrect. Motivated by this, we propose Post-hoc Correction (POC), a simple training-free framework that leverages an LMM to post-process an expert model's top predictions. We develop a multimodal prompting strategy to enable POC to improve FSL expert models by 6.4 accuracy points, averaged over five VSR benchmarks. We show that POC generalizes across diverse FSL methods, visual encoders, and LMMs, making it a practical and effective framework for VSR.
arXiv (fysik & CS) Preprint 2026-07-15
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
arXiv:2512.17788v2 Announce Type: replace Abstract: Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance and label spaces. However, existing MIPL approaches often suffer from poor calibration, undermining classifier reliability. In this work, we propose a plug-and-play calibratable disambiguation loss (CDL) for classification and calibration, which modulates a disambiguation objective by a top-vs-competitor prediction margin. The competitor is instantiated either as the second strongest candidate label or as the strongest non-candidate label, yielding two variants that respectively emphasize candidate-level separation and candidate-vs-non-candidate suppression. Theoretically, we analyze CDL as a margin-modulated momentum-based disambiguation loss (MDL) objective, derive a lower-bound and a pseudo-label confidence-alignment bound for calibration, and show through gradient and momentum analyses how margin shaping affects weight updates. Experimental results on benchmark and real-world MIPL datasets, together with representative PLL adaptation, confirm that our CDL significantly improves both classification accuracy and expected calibration error.
arXiv (fysik & CS) Preprint 2026-07-15
Schwarz Information Criterion Aided MAB for Resource Allocation in Dynamic LoRa System
arXiv:2512.22089v4 Announce Type: replace Abstract: This paper proposes a lightweight distributed learning method for transmission parameter selection in Long Range (LoRa) networks that can adapt to dynamic communication environments. In the proposed method, each LoRa End Device (ED) employs the Upper Confidence Bound (UCB)1-tuned algorithm to select transmission parameters including channel, transmission power, and bandwidth. The transmission parameters are selected based on the ACKnowledgment (ACK) feedback returned from the gateway after each transmission and the corresponding transmission energy consumption. Hence, it enables devices to simultaneously optimize transmission success rate and energy efficiency in a fully distributed manner. However, although UCB1-tuned based method is effective under stationary conditions, it suffers from slow adaptation in dynamic environments due to its strong reliance on historical observations. To address this limitation, we integrate the Schwarz Information Criterion (SIC) to our proposed method. SIC is adopted because it enables low-cost detection of changes in the communication environment, making it suitable for implementation on resource-constrained LoRa EDs. When a change is detected by SIC, the learning history of UCB1-tuned is reset, allowing rapid re-learning under the new conditions. Experimental results using real LoRa devices demonstrate that the proposed method achieves superior transmission success rate, energy efficiency, and adaptability compared with the conventional UCB1-tuned algorithm without SIC.
arXiv (fysik & CS) Preprint 2026-07-15
Rzk: a Proof Assistant for Synthetic $\infty$-Categories
arXiv:2607.12207v1 Announce Type: new Abstract: Homotopy type theory (HoTT) is a type theory that allows for synthetic reasoning about $\infty$-groupoids. Several proof assistants (such as Rocq and Agda) implement variants of HoTT. Directed type theory is a type theory for synthetic reasoning about $\infty$-categories, where morphisms (or paths) of dimension 1 are not necessarily invertible. Among the proposals for directed type theory, the most developed is Riehl and Shulman's simplicial type theory (RSTT), based on simplicial shapes such as directed intervals and triangles. We present Rzk, a proof assistant implementing (a refinement of) RSTT for synthetic reasoning about $\infty$-categories. Specifically, the type theory implemented by Rzk is a computational variant of RSTT adjusted to make type checking practical. We define a translation from RSTT to Rzk and prove that it is sensible: every RSTT proof translates to an Rzk proof (faithfulness), and Rzk proves nothing new about RSTT types (conservativity). We also give a tutorial introduction to proving in Rzk, and describe its implementation, including the type-checking algorithm and the automated prover for the logic of shapes.
arXiv (fysik & CS) Preprint 2026-07-15
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
arXiv:2607.12796v1 Announce Type: new Abstract: When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer every other model picks? Asked to "pick a word -- any word," 44 models chose "serendipity" 41% of the time. We characterize this convergence with a deliberately minimal instrument: 31 single-turn prompts, each naming a category with many valid one-word answers ("Name a tree."), asked four times per model with no system prompt. Analysis is exact-match on normalized tokens -- no embeddings, no judge -- at about a dollar per model. That models converge is well documented; our contribution is the instrument itself -- the One-Word Census -- and what it reveals about the structure of the convergence. We score each model by answer-choice surprisal: the average $-\log2$ probability of its answers under the pooled answers of all other models, leave-one-out. Convergence is extreme -- in 7 of 31 categories one answer takes over 80% of all answers -- yet conformity varies more than fourfold across models, and the variation is structured. Persona- and community-tuned models are the most divergent; the newest mainline flagships are the most conformist, producing almost no answer no other model gave. Within four lineages (Claude, GPT, Qwen, Grok) conformity rises with each generation -- but reverses for the latest flagship Claude and GPT models, a possible early signal of repositioning at the top tier. Rankings are robust to roster composition (leave-one-family-out rho = 0.985). Against human category-production norms, the field is more concentrated than people in 18 of 20 shared categories. All prompts, transcripts, and code are public.
arXiv (fysik & CS) Preprint 2026-07-15
ArchSim: Computer Architecture Simulation as a Service
arXiv:2607.12359v1 Announce Type: new Abstract: Conducting a complete computer architecture simulation study is challenging because configuration, execution, and analysis are often encoded implicitly in scripts or directory conventions rather than represented explicitly. As a result, studies are difficult to scale, hard to reproduce, and dependent on custom tooling at every stage. We present ArchSim, which makes the structure of a simulation study explicit. In ArchSim, hardware topologies are described as declarative graphs that automatically generate executable simulation code, eliminating hand-written simulator programs. Stateless runners autonomously claim and execute jobs from a shared experiment store, enabling configuration-benchmark matrices to scale without manual orchestration. Simulation outputs are stored as structured artifacts tied to configurations, benchmarks, and hardware components, enabling systematic result exploration without custom parsers. We evaluate ArchSim on a 12 x 8 = 96-configuration simulation matrix spanning memory-bound, compute-bound, and mixed-intensity GPU workloads. Declarative simulation specifications drive full simulations with a median kernel time error of 0.18% relative to hand-written MGPUSim configurations across 95.8% of configurations. The platform introduces only 1.6 seconds of overhead per simulation, negligible relative to realistic simulation workloads.
arXiv (fysik & CS) Preprint 2026-07-15
Symmetry-Informed Deep Learning for Electromagnetic Scattering
arXiv:2607.12810v1 Announce Type: new Abstract: Deep learning can accelerate the modeling of electromagnetic devices by replacing costly simulations with neural networks trained to map design parameters to scattering parameters. However, data efficiency remains a central bottleneck, as training data is typically generated through expensive numerical simulations. Here we show that symmetry provides a powerful and largely untapped route to overcoming this limitation in electromagnetic scattering problems. Leveraging the equivariance of Maxwell's equations, we obtain general transformation rules that map symmetries of electromagnetic devices to corresponding transformations of their scattering parameters. This enables both systematic data augmentation and the construction of exactly equivariant neural networks. We implement the framework for both discrete and continuous symmetry groups and demonstrate its effectiveness on photonic-crystal slabs and free-form diffraction gratings. Incorporating symmetry improves data efficiency by an order of magnitude compared to standard architectures, while equivariant models additionally enforce physical constraints exactly. Our approach is general and complementary to existing physics-informed strategies, provides a first-principles framework for constructing physically grounded surrogate models, and establishes symmetry as a unifying inductive bias for data-efficient and physically consistent learning in computational electromagnetics and beyond.
arXiv (fysik & CS) Preprint 2026-07-15
Calculating Mutual Information between a Reward Maximizer and its Environment
arXiv:2602.12963v2 Announce Type: replace Abstract: An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world. In this work, we quantify the amount of information an optimal policy provides about the underlying environment. We consider a Controlled Markov Process (CMP) with $n$ states and $m$ actions, assuming a uniform prior over the space of possible transition dynamics. We prove that observing a deterministic policy that is optimal for any non-constant reward function then conveys exactly $n \log m$ bits of information about the environment. Specifically, we show that the mutual information between the environment and the optimal policy is $n \log m$ bits. This bound holds across a broad class of objectives, including finite-horizon, infinite-horizon discounted, and time-averaged reward maximization. These findings provide a precise information-theoretic lower bound on the ``implicit world model'' necessary for optimality.
arXiv (fysik & CS) Preprint 2026-07-15
Xray-Visual Models: Scaling Vision models on Industry Scale Data
arXiv:2602.16918v2 Announce Type: replace Abstract: We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.
arXiv (fysik & CS) Preprint 2026-07-15
GraphPolaris: A System for Query, Analysis, and Visualization of Graph Databases
arXiv:2607.12845v1 Announce Type: new Abstract: Graph databases are increasingly adopted as alternatives to tabular, aggregation-focused data models used in business intelligence (BI) systems such as Tableau, Power BI, and Looker. They capture complex relationships between entities, processes, and events, enabling analysis of information propagation in networks. As a result, graph analysis is central to applications such as fraud detection, social influence analysis, and supply chain resilience. Despite these advantages, existing tools do not adequately support interactive analysis of graph databases. Tabular BI systems lack mechanisms for reasoning over nodes and edges, while graph databases require specialized query languages and fragmented workflows that hinder accessibility. We present GraphPolaris, a no-code Visual Analytics system that enables users to explore, analyze, and visualize graph databases without programming skills. At its core, GraphPolaris features the GRAPHPOLARIS QUERY LANGUAGE (GPQL), a formal query grammar that facilitates flexible and composable graph queries, providing a formal foundation for analyzing relationships and graph patterns. GPQL serves as an intermediary between user interactions and the underlying database. Its formal foundation enables no-code query construction, database-agnostic query generation, and guarantees that every interaction produces a valid executable query. Informed by a formative user study, we designed GraphPolaris' interface and visualizations to lower technical barriers and foster iterative, collaborative exploration of complex networks. We evaluate GraphPolaris through two real-world case studies in telecommunications and supply-chain analysis and a 22-month-long formative mixed-method study, including a MILC-based assessment of its fit to analysts' graph analytics workflows.
arXiv (fysik & CS) Preprint 2026-07-15
Phase Angle and Effective Second-Harmonic Generation Coefficient in Uniaxial Crystal
arXiv:2607.12851v1 Announce Type: new Abstract: In this paper, the calculation formulae of phase angle are given for two classes of largest effective SHG coefficients in uniaxial crystals by means of the optimization theory. With the help of such calculation formulae, we present the best phase angles and azimuth angles of all uniaxial crystals class, as well as their effective SHG coefficients. Furthermore, these calculation is only dependent upon some principal subtensor of second order susceptibility tensor.