# Research Papers — 2026-07 · bundle page 63 of 222 > Full-text markdown of papers #3101–3150 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/63 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/62.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/64.md) ### Reconstruction of Enhanced Causal Omnidirectional Network (RECON) Authors: Praveen Niranda, Peter T. McKenney, Guifang Fu Published: 2026-07-23 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.21833v1 Learning a dynamical system and reconstructing the underlying regulatory network from $p$ discretely observed state trajectories remain challenging problems. Existing approaches often produced a large number of spurious edges and suffered from several methodological limitations. We propose a new approach, Reconstruction of Enhanced Causal Omnidirectional Network (RECON), that leverages an integral-based additive nonparametric ODE model to reconstruct regulatory networks from $p$ time-course data. RECON incorporates five methodological advances. First, it incorporates a new data-driven edge selection procedure that substantially reduces spurious edges while preserving true regulatory edges. Second, it reconstructs an omnidirectional network that captures causal regulatory relationships rather than merely statistical associations or noise artifacts. Third, it substantially broadens the applicability of standard ODE-based approaches by accommodating both dense regular and sparse irregular longitudinal sampling scenarios. Fourth, it models both node trajectories and edge regulatory effects as time-varying functions, emphasizing a dynamic regulatory network. Fifth, it reconstructs a signed and weighted regulatory network and provides comprehensive network interpretation through two-way direction, activatory/inhibitory indicator, and strength, together with keystone node identification and topological structure. Across five simulation studies, RECON consistently outperforms GRADE by removing nearly all spurious edges while retaining nearly all true regulatory edges, resulting in highly accurate network reconstruction. In the most challenging scenario, the number of spurious edges is reduced from 239 to 0. --- ### How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests Authors: Iren Mazloomzadeh, Mohammad Mehdi Morovati, Foutse Khomh Published: 2026-07-23 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2607.21832v1 Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agents an integral component of modern software development workflows. While developers increasingly benefit from these coding agents, their impact on software quality remains insufficiently understood. In particular, how agentic contributions evolve across the software development lifecycle has not been thoroughly investigated. This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle. Using the AIDev dataset, we first analyze how differences in merge rates between agentic and human generated PRs vary over time. We then identify the types of development tasks where AI coding agents are predominantly applied and investigate how these task distributions evolve across development quarters. Finally, we compare a set of key characteristics of agentic and human generated PRs, focusing on their implications for software quality and their temporal dynamics. Overall, our findings provide an empirical and longitudinal perspective on the role of AI coding agents in software development, offering a more nuanced understanding of their benefits and limitations in real-world practices. --- ### A Graph-Based Control Interface for Traffic Signals on Heterogeneous Road Networks Authors: Bertil Braun Published: 2026-07-23 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.21831v1 We present a traffic-signal control interface in which a shared graph neural network assigns scores to individual traffic movements. Each junction converts these scores into its own variable-sized set of legal signal phases using a deterministic incidence matrix. Directed corridor nodes provide traffic context, while movement nodes represent controlled input-to-output paths through junctions. Typed mean aggregation produces one scalar per movement; phase definitions and signal timing remain outside the learned network. This makes graph size and junction-specific action count independent of the learned parameter shapes. PPO experiments evaluate the interface on unseen synthetic grid geometries, altered signal coverage, and five heterogeneous city graphs. The policies retained performance across unseen geometries within the synthetic grid family, while changes in signal coverage exposed sensitivity to a signal-coverage distribution shift. A single trained city-policy instance executed across all five city graphs, with heterogeneous outcomes. These results provide feasibility evidence rather than a general estimate of transfer to arbitrary road networks. --- ### Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA Authors: Sergio A. Alvarez Published: 2026-07-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21823v1 We show that, up to isotropic scaling, the Gaussian RBF reproducing kernel Hilbert space (RKHS) is asymptotically isometric to Euclidean space in the large bandwidth limit. This strongly suggests that kernel-based constructions reliant on metric properties of the RKHS will yield results for Gaussian RBF kernels that similarly approach those of linear kernels for large bandwidths. The asymptotic behavior of Gaussian CKA can be understood in this light. We further consider kernel PCA, showing that Gaussian RBF eigenvalues, eigenprojections, and principal components all converge to those of classical (linear) PCA as bandwidth $σ\rightarrow \infty$. For a given data representation, both the RKHS feature embeddings and the orthogonal PCA eigenframes of the two kernel types differ asymptotically by a geometric similarity transformation, up to a residual of size $O \left (\fracρσ \right )^2$, where $ρ$ is a measure of geometric eccentricity of the representation, equal to the ratio of maximum to median pairwise distance between data examples. Experiments over a diverse collection of data sets demonstrate that $ρ$ provides a simple and reliable predictor of dataset-specific convergence behavior in the top principal directions. --- ### Probing Speaker Identity Sensitivity in Audio Deepfake Detectors Authors: Daniyal Kabir Dar, Arun Ross Published: 2026-07-23 Categories: cs.SD, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.21820v2 Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less than 1% error on one dataset can see its error rate increase twentyfold when evaluated on a different dataset. We argue that one contributing factor is speaker-identity reliance: standard training corpora correlate speaker identity with the genuine/synthetic label, allowing detectors to partially rely on speaker-related cues rather than synthesis artifacts alone. We propose the Identity Sensitivity Score (ISS), a per-utterance diagnostic that quantifies how much a detector's output changes across different speaker identity contexts. ISS requires no ground-truth labels at inference time and can be computed from the detector score and a pool of reference speaker examples. Across two detectors and two datasets, incorrectly classified utterances have ISS scores 29 to 52 times higher than correctly classified utterances, and ISS alone predicts misclassification with area-under-curve (AUC) up to 0.954. To test whether ISS actually captures identity-sensitive behavior rather than serving only as a proxy for prediction confidence, we apply voice conversion to 500 utterances and measure the resulting detector-score shift. Utterances flagged as identity-sensitive by ISS respond 19 to 30 times more strongly to this manipulation than utterances flagged as stable. These results position ISS as a practical inference-time diagnostic for speaker-dependent failure analysis in audio deepfake detection. --- ### Probing Speaker Identity Sensitivity in Audio Deepfake Detectors Authors: Daniyal Kabir Dar, Arun Ross Published: 2026-07-23 Categories: cs.SD, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.21820v1 Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less than 1% error on one dataset can see its error rate increase twentyfold when evaluated on a different dataset. We argue that one contributing factor is speaker-identity reliance: standard training corpora correlate speaker identity with the genuine/synthetic label, allowing detectors to partially rely on speaker-related cues rather than synthesis artifacts alone. We propose the Identity Sensitivity Score (ISS), a per-utterance diagnostic that quantifies how much a detector's output changes across different speaker identity contexts. ISS requires no ground-truth labels at inference time and can be computed from the detector score and a pool of reference speaker examples. Across two detectors and two datasets, incorrectly classified utterances have ISS scores 29 to 52 times higher than correctly classified utterances, and ISS alone predicts misclassification with area-under-curve (AUC) up to 0.954. To test whether ISS actually captures identity-sensitive behavior rather than serving only as a proxy for prediction confidence, we apply voice conversion to 500 utterances and measure the resulting detector-score shift. Utterances flagged as identity-sensitive by ISS respond 19 to 30 times more strongly to this manipulation than utterances flagged as stable. These results position ISS as a practical inference-time diagnostic for speaker-dependent failure analysis in audio deepfake detection. --- ### Longitudinal Random Forests for Sparse and Irregular Response Trajectories Authors: Yangsheng Wang, Xiaotian Dai, Haoda Fu, Guifang Fu Published: 2026-07-23 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.21817v1 Longitudinal studies often collect data at sparse, irregular, and unequally spaced time points. Such heterogeneity is often driven by subject-specific covariates, yet existing methods have been restricted to a scalar endpoint value, completely neglecting the underlying response trajectories. We propose a novel Longitudinal Random Forest (LRF) framework that leverages tree-based ensemble machine learning with adaptive node-wise longitudinal trajectory estimation. The LRF framework makes five methodological contributions. it captures each subject's individual response trajectory while simultaneously accommodating within-node correlation, between-node heterogeneity, and nonlinear and interactive covariate effects. It introduces a novel trajectory-based splitting criterion that maximizes trajectory separation while incorporating a size-weighted penalty; it provides two variants, Principal Analysis by Conditional Expectation (LRF-PACE) and adaptive linear mixed-effects models (LRF-adaptiveLMM), which employ nonparametric and semiparametric node-wise smoothers, respectively, while learning covariate effects in a data-driven manner. It provides a comprehensive interpretation of covariates using both the classical trajectory-based permutation variable importance measure (PVIM) and a newly proposed finite-way interaction frequency count, and it not only predicts entire trajectories for new subjects but also forecasts future trajectories for existing subjects. Extensive simulation studies demonstrate that LRF achieves superior performance over several competing methods, even under severe sparsity. The practical significance of the LRF framework lies in its ability to address five important clinical questions. --- ### Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness Authors: Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst Published: 2026-07-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21806v1 Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice. There is a growing recognition of the need to evaluate the causal impact of deploying these systems on downstream outcomes, such as patient survival or crime recidivism. Randomized control trials (RCTs) can provide high-quality evidence on the impact of a deployed model, but they run into a challenge: it is often infeasible to run repeated trials when models are updated or retrained to improve predictive performance. In this work, we present a partial-identification approach to using prior RCT data to construct bounds on the causal effect of a new model. The core innovation in our approach is to leverage assumptions relating fine-grained predictive accuracy to downstream outcomes. We do so via two monotonicity assumptions: first, on individual-level `counterfactual correctness' (all else being equal, a correct prediction leads to non-inferior outcomes); and second, on the relation between subgroup predictive performance and outcomes, interpretable as an assumption regarding trust in model outputs. We demonstrate our method with a simulation study, illustrating how incorporating this information can lead to more informative bounds compared to prior work. --- ### Natural Invariant Measures for Chaotic Game Dynamics: Finding Order in Chaos Authors: Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Michał Misiurewicz, Georgios Piliouras Published: 2026-07-23 Categories: math.DS, cs.LG, econ.TH arXiv: https://arxiv.org/abs/2607.21805v1 We study the long-term behavior of the Multiplicative Weights Update (MWU) algorithm in game settings where learning dynamics frequently fail to converge to Nash equilibria and instead exhibit Li-Yorke chaos. While such chaos precludes the prediction of specific long-term strategy profiles, it does not imply a lack of statistical structure. We demonstrate that natural invariant measures - a fundamental concept from ergodic theory - provide the rigorous framework necessary to find order within this chaos. Focusing on a two-strategy congestion game, we prove that these measures allow for a comprehensive statistical characterization of the dynamics. Crucially, we show that this framework extends beyond simple strategy frequencies to \emph{general observables}, enabling the precise calculation of long-term time averages for broad classes of economic metrics - including payoffs, social cost, and regret - despite chaos. Our results reveal that this simple learning algorithm captures the full spectrum of behaviors found in one-dimensional dynamical systems, from unique or multiple absolutely continuous invariant measures to complex periodic attractors as well as coexisting chaotic and stable (periodic) behaviors. By bridging game theory and dynamical systems, we show that statistical predictability is attainable even in the absence of pointwise convergence. --- ### Adversarial Prompts for Acceptance Collapse in Speculative Decoding Authors: Run Wang, Chaoyi Zhou, Xi Liu, Yi Zhu, Amir Salarpour, Pedram MohajerAnsari, Zhi-Qi Cheng, Feng Luo, Siyu Huang, Mert D. Pesé Published: 2026-07-23 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.21804v1 Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-target alignment can be systematically attacked. In this paper, we introduce ADSD, which, to the best of our knowledge, is the first prompt-suffix attack that collapses verifier acceptance by pushing draft probability mass toward tokens the target is unlikely to accept. ADSD uses Soft-Collapse, a verifier-aligned surrogate derived from the asymmetric speculative acceptance rule, together with a target-preservation objective that discourages obvious task corruption. ADSD successfully generates highly effective adversarial suffixes. On the GSM8K dataset, our attack increases the mean sample time by 62.3% while preserving the task quality. We further show that this vulnerability exists across different domains, speculative decoding strategies, and model architectures. --- ### A Dual Path Framework with Hotspot Guided Fusion for Three Dimensional CT to PET Synthesis in Head and Neck Cancer Authors: Mohd Maaz Khan, Oluwaseyi Oderinde Published: 2026-07-23 Categories: physics.med-ph, cs.CV arXiv: https://arxiv.org/abs/2607.21800v1 18F-FDG PET/CT plays a central role in staging, treatment planning, and response assessment for head and neck cancer by providing functional information that complements anatomical CT imaging. However, PET acquisition requires radiotracer administration, specialized infrastructure, and additional cost, limiting its availability for repeated imaging. We present a proof of concept deep learning framework for synthesizing PET like images directly from routine CT scans with the goal of providing complementary metabolic information that may support imaging triage and clinical decision support rather than replace diagnostic PET. Forty-four patients from the publicly available QIN-HEADNECK dataset were retrospectively analyzed using five fold cross-validation. We propose a fully three dimensional dual path architecture consisting of (i) a regression U-Net optimized for voxel-wise quantitative SUV estimation and (ii) a conditional generative adversarial network optimized for realistic PET texture. Their outputs are integrated using hotspot guided Laplacian pyramid blending, allowing quantitative information from the regression pathway to be preserved within metabolically active regions while leveraging adversarial texture synthesis elsewhere. The proposed framework achieved a mean absolute error of 0.00395, PSNR of 39.19 dB, and SSIM of 0.9634 on reconstructed three dimensional PET volumes. Qualitative evaluation demonstrated accurate localization of many FDG-avid lesions while producing anatomically realistic background texture. Consistent with previous CT to PET synthesis studies, the principal limitation was systematic underestimation of SUV within highly metabolically active tumor regions. --- ### Agentic Evaluation of Copyright Law Compliance Authors: Zheng Hui, Doni Bloomfield, Noam Kolt Published: 2026-07-23 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.21799v2 Large language model (LLM) agents increasingly perform commercial tasks that involve retrieving external content, such as images, and, where appropriate, reproducing that content. LLM agents should comply with the law, including copyright law. Presently, however, we lack adequate frameworks to assess whether they do so in practice. To that end, we introduce Copyright-Bench, a benchmark designed to evaluate LLM agents' compliance with copyright law. Copyright-Bench comprises realistic commercial tasks---website development, merchandise design, and pitch deck production---that involve agents selecting between public-domain content, the use of which is legal, and copyrighted content, the use of which is infringing in this setting. The evaluation introduces prompt variations that simulate different user preferences, as well as time pressure. Comparing state-of-the-art LLM agents against a human baseline, we find that: (1) agents select copyrighted works despite the availability of public-domain alternatives; and (2) for open-weight models, violation rates increase in response to certain user preferences and simulated time pressure. --- ### Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling Authors: William Gaudelier, Albert Cohen, Dumitru Potop Butucaru Published: 2026-07-23 Categories: cs.PL, cs.LG arXiv: https://arxiv.org/abs/2607.21797v2 Previous work has shown that the simple dataflow primitives of the Lustre language allow the natural, semantically unambiguous, and compact representation of machine learning (ML) applications, including models featuring complex conditional execution and recurrent state. The Lustre clock calculus is responsible for the static determination of important properties such as liveness (absence of deadlocks) and static memory bounds. Yet existing clock calculi are tailored for embedded control applications. We show they do not cater for the representation of control patterns commonly found in training algorithms, resulting in cumbersome expressions and inefficient compilation. We propose a conservative extension of Lustre's clock calculus addressing this limitation, thereby facilitating the embedding of ML models in reactive applications. --- ### QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization Authors: Siwei Chen, Siqi Chen, Xupeng Miao, Bin Cui Published: 2026-07-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21793v1 Recent large reasoning models often develop long chain-of-thought responses during reinforcement learning (RL), resulting in high inference latency and deployment cost. Existing methods for response length control typically rely on explicit length penalties or additional control modules, which require careful tuning and may compromise reasoning quality. We propose Quadrant-weighted Sampling for Length-aware Policy Optimization (QLPO), a simple resampling-based variant of GRPO that introduces implicit length control without modifying the reward function. QLPO first over-generates candidate responses and then resamples the training group by preserving the empirical correct/incorrect ratio while favoring short correct responses and long incorrect responses. This reshapes the training distribution and implicitly encourages shorter model outputs. Across models ranging from 1.5B to 32B parameters, including both base models and strong reasoning models, QLPO consistently improves the accuracy-length trade-off. It reduces response length by 30% to 70% while preserving reasoning performance. These results suggest that structured resampling provides an effective and robust approach to efficient reasoning. --- ### What Happens to Accuracy When Photo Lineups Contain Non-Mated Rank-One Images From Large Galleries? Authors: Genesis Argueta, Kevin W. Bowyer, Michael King, Jayeeta Dhar Published: 2026-07-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.21792v2 One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's license and/or booking photos. The algorithm's rank-one image from the gallery, or a human examiner's selection from the algorithm's top-ranked images, may then be placed in a photo lineup shown to a witness. Witness selection of the gallery image in the photo lineup may then lead directly to the person in the gallery image being arrested. This facial identification process is involved in a number of wrongful arrests. This work specifically examines whether the probability of a witness making an incorrect identification increases with the size of the gallery searched. We compare photo lineup accuracy when the "suspect" image is drawn from galleries of 500, 5,000, and 24,000 images. We find that larger galleries increase both the likelihood of a witness making an incorrect identification and their confidence in that (incorrect) identification. These results raise questions of whether an image resulting from such a facial identification process should be used in photo lineups and of whether results of a photo lineup alone should constitute probable cause for arrest. --- ### What Happens to Accuracy When Photo Lineups Contain Non-Mated Rank-One Images From Large Galleries? Authors: Genesis Argueta, Kevin W. Bowyer, Michael King, Jayeeta Dhar Published: 2026-07-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.21792v1 One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's licenses and/or booking photos. The algorithm's rank-one image from the gallery, or a human examiner's selection from the algorithm's top-ranked images, may then be placed in a photo lineup shown to a witness. Witness selection of the gallery image in the photo lineup may then lead directly to the person in the gallery image being arrested. This facial identification process is involved in at least 9 wrongful arrests. This work specifically examines whether the probability of a witness making an incorrect identification increases with the size of the gallery searched. We compare photo lineup accuracy when the "suspect" image is drawn from galleries of 500, 5,000, and 24,000 images. We find that larger galleries increase both the likelihood of a witness making an incorrect identification and their confidence in that (incorrect) identification. These results raise questions of whether an image resulting from such a facial identification process should be used in photo lineups and of whether results of a photo lineup alone should constitute probable cause for arrest. --- ### Risk-Routed Implicit Boundary Refinement for Robust Ultrasound Image Segmentation Authors: Jingguo Qu, Xinyang Han, Xiang Wang, Yuqi Yang, Tonghuan Xiao, Sheng Ning, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Ying Published: 2026-07-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.21787v1 Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisition variation across operators and clinical centers. Although encoder-decoder and transformer-based networks have achieved strong performance, many methods recover boundary details through dense decoders or larger backbones, which may still produce over-smoothed contours or unstable predictions under external distribution shifts. In this article, we propose Risk-routed Implicit Boundary Refinement (RIBR), a compact segmentation framework that uses implicit neural representation as a risk-routed residual correction rather than an unconstrained full-mask predictor. RIBR combines boundary-refinement implicit residuals, risk-routed residual control, and geometry- and speckle-aware boundary regularization to refine uncertain contours while suppressing non-boundary oscillations. Evaluation on nine US datasets covering lymph nodes, breast lesions, thyroid nodules, and prostate shows that RIBR achieves the best overall macro-average and consistently reduces boundary error across grouped and organ-specific comparisons under a compact parameter budget. These findings suggest that controlled implicit residual learning is a practical strategy for resource-constrained and boundary-sensitive US segmentation. Source code is available at https://github.com/jinggqu/ribr. --- ### From Seasonality to Semantics: Benchmarking a Hybrid Probabilistic Forecasting System for Roadblocks in Bolivia Authors: Rodrigo Vargas Sainz, Christian Berón Curti Published: 2026-07-23 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.21785v1 Roadblocks in Bolivia are a social conflict phenomenon with devastating economic impacts, estimated at losses equivalent to 4% of the national Gross Domestic Product. Despite their recurrence and impact, there is a lack of local predictive systems to anticipate these events for logistical decision-making. This paper presents a hybrid probabilistic forecasting system that integrates time series decomposition (Prophet) with natural language processing (NLP) techniques applied to a six-year corpus of Bolivian news coverage. The methodology employs vector semantic embeddings and zero-shot classification models to capture signals of discursive escalation prior to the materialization of the roadblocks. Using an expanding walk-forward validation scheme applied over 1,762 days and seven forecasting horizons (H+1 to H+7), seven internal configurations and four external benchmarks were compared, including SARIMA and LightGBM. The results demonstrate that the hybrid configuration (Prophet + NLP, C6) consistently outperforms purely statistical models, achieving an AUC-ROC of 0.677 at H+1 and reducing the Brier Score by 10.9% relative to the baseline temporal model (0.220 vs. 0.247), maintaining a statistically significant error reduction across all evaluated horizons ($p < 0.02$). This research validates that the integration of semantic news signals allows for the detection of social tension peaks not captured by historical inertia, providing a technical tool for risk management in critical transport corridors. --- ### MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery Authors: Grace Fan, Eden Wu, Majid Daliri, Juliana Freire Published: 2026-07-23 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2607.21781v1 Join discovery is a core task in dataset search, enabling users to find columns that can be joined with a given query column. Early approaches focused on equi-joins, but data lakes and open-data repositories often contain columns whose values refer to the same entity but use different syntactic representations. To address this challenge, recent approaches discover semantically joinable columns but face a fundamental trade-off: methods that perform value-level comparisons accurately identify joinable columns but scale poorly to columns with high cardinality; column-level methods that encode an entire column into a single embedding are efficient but do not capture the fine-grained value alignment that determines whether a join is possible. We present MosaicJoin, a value-level semantic join discovery method that balances this trade-off. MosaicJoin achieves scalability through a novel sketching strategy that approximates the joinability of a column pair without having to compare all values. At query time, MosaicJoin scores each candidate sketch using a joinability score at a cost bounded by the sketch size, making retrieval efficient even for high-cardinality columns. A query subsampling operator further reduces online search time with provable accuracy guarantees, enabling robust retrieval for large query columns. Extensive experiments show that MosaicJoin outperforms previously published methods across all benchmarks while running up to 66 times faster than other value-level methods. MosaicJoin requires no training or fine-tuning, and it scales robustly to query columns containing up to 57K values and data lake columns containing up to 1M values. --- ### Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms Authors: Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan, Ezharuddin Jubaer, Sumaiya Karim Katha, Armun Alam, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman Published: 2026-07-23 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.21780v1 Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into their constituent documents is difficult, especially for low-resource languages. We introduce Khondo (Bangla for split/segment), the first benchmark for document packet splitting on Bangladeshi government forms. Unlike prior English and OCR-text-based datasets, Khondo is bilingual (Bangla--English) and vision-native; where models operate directly on page images. It spans five concatenation schemes, from sequential to fully shuffled, across 14 administrative domains, with ground-truth boundaries, domain types, and page order. Zero-shot evaluation of MLLMs shows they cluster pages into their source documents fairly well but struggle in restoring the original page order once shuffled. To isolate what drives this difficulty, we run two controlled analyses, varying the prompt instruction and then the packet language. Both primarily affect ordering rather than clustering: (a) explicit page-order instructions are necessary but insufficient, and (b) English packets are ordered more reliably than Bangla, making page arrangement the dominant challenge and language a secondary but consistent factor. Khondo establishes page-order reconstruction as a key open problem in vision-based, low-resource document understanding, and provides a controlled benchmark for measuring progress toward solving it. Our dataset and code is available at https://huggingface.co/datasets/Mausul/khondo --- ### Graph-Theoretic Neural Network Fragmentation with Covariant Direct Molecular Force Learning: Enabling Coupled-Cluster Accuracy AIMD for Fluxional Systems Authors: Xiao Zhu, Srinivasan S. Iyengar Published: 2026-07-23 Categories: physics.chem-ph, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2607.21779v1 Accurate ab initio molecular dynamics (AIMD) simulations of complex, fluxional chemical systems are severely limited by the high computational scaling of correlated electronic structure methods. To overcome this bottleneck, we present a robust, graph-theoretic molecular fragmentation framework integrated with machine learning to directly model post-Hartree-Fock nuclear forces at coupled cluster accuracy. Bypassing the limitations of automatic differentiation on learned energy surfaces that may struggle with link-atom Jacobians, our approach directly predicts nuclear force vectors. By projecting these vectors onto fragment-fixed principal axes of inertia, we establish co-variant descriptors that naturally preserve rotational, translational, and permutational invariance. The methodology achieves exceptional high parameter efficiency through a vector-valued training protocol that reduces trainable parameters by over an order of magnitude, while an unsupervised mini-batch k-means space tessellation algorithm constructs highly representative training databases using only 10% to 20% of reference configurations. We rigorously validated this framework on the highly fluxional solvated Zundel cation H_{13}O_6^+ ). Our fully machine-learning-predicted AIMD trajectories successfully reproduced complex dynamical signatures and key structural characteristics, including radial distribution functions and the velocity autocorrelation power spectrum. Ultimately, this scalable, systematically improvable framework bridges the gap between high-level correlated wavefunction theories and long-timescale reactive sampling, laying the foundation for advanced, LLM-inspired transfer learning in modern chemical dynamics simulations. --- ### AI-Integrated Scientific Inquiry: A Practice-Centered Vision for Science Education Authors: Arne Bewersdorff, Matias Rojas, Xiaoming Zhai Published: 2026-07-23 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.21777v1 Artificial intelligence (AI) has become part of scientific inquiry. Scientists use AI to observe and measure phenomena, to identify patterns in data, and to build models. As AI moves into scientific inquiry, it gains relevance for science education: students should learn how AI is changing scientific practices, ideally by engaging in AI-integrated scientific inquiry themselves. How to design such instruction, grounded in authentic scientific practice rather than taught as a standalone topic, remains an open question. In our vision, which we describe in this article, AI is treated as a set of scientific instruments that students use within the scientific practices described by the Next Generation Science Standards. Each instrument is a genuine scientific tool, pedagogically bounded: its controls are simplified while its core scientific function is preserved. The approach has two aims: engaging students in authentic scientific inquiry, and building an understanding of how AI is used in science and where it can mislead (discipline-based AI literacy, DAIL). In the article, we focus on the investigative core of inquiry, namely observing, analyzing, and modeling, and describe one exemplary AI instrument for each: computer vision for observing, clustering for analyzing, and generative modeling for modeling. We argue that every AI instrument in science education should carry a distinct reflection point that prompts critical evaluation of the AI instrument itself. Finally, we describe how agentic AI, operating across the whole inquiry rather than a single practice, could be represented, arguing that students should first build a foundational understanding of scientific inquiry and AI instruments before relying on agentic AI. --- ### Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Authors: Othmane Harraq, Tamer Aldwairi Published: 2026-07-23 Categories: cs.LG, cs.CR, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2607.21776v1 Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries that current image-based detectors consistently fail to identify. Unlike face-swap ma- nipulation, TF synthesis has no underlying real video from which to inherit physiological characteristics, making re- mote photoplethysmography (rPPG) a uniquely motivated detection modality for this forgery category. We propose a detection framework that extracts per-video rPPG wave- forms via RhythmFormer and trains a suite of lightweight classifiers to distinguish real from synthesized physiologi- cal signals. Evaluated on the TF subset of Celeb-DF++ un- der a strict subject-independent protocol, where test identi- ties are completely separated from training identities, our 1D ResNet achieves an AUC of 0.806 and EER of 27.8%, placing it within 2.4 points of the best published general- purpose detector (Effort, ICML 2025) while operating ex- clusively on the physiological channel. We document a con- trolled reproduction study of DeepFakesON-Phys, the rep- resentative prior rPPG detector, demonstrating degrada- tion from AUC 0.999 on legacy face-swap data to 0.622 on the TF subset of Celeb-DF++. We further show that detec- tion difficulty is strongly method-dependent: AUC ranges from 0.985 (Real3DPortrait) to 0.690 (IP-LAP) across the seven TF generators, with the ranking remaining perfectly stable across all evaluation protocols. This spread reflects an interpretable physiological property of each generator rather than evaluation noise, and constitutes the primary theoretical contribution of the work. --- ### Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders Authors: Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino, Jhoan Stevan Mosquera Ortiz, Nicolás Lozano Mazuera, Gilber Alexis Corrales Gallego Published: 2026-07-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.21774v1 Large language models may infer demographic attributes from subtle linguistic cues even when those attributes are not explicitly stated. This pilot study examines whether Qwen2.5-7B-Instruct internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts. We use Natural Language Autoencoders (NLA) to verbalize residual-stream activations from layer 20 across four positional quartiles per prompt. Our dataset contains 30 prompts arranged as 15 matched Spanish-English pairs, spanning explicit Colombian cues, implicit Colombian cues, and neutral controls. We report descriptive rates and qualitative evidence rather than statistically powered effects, focusing on whether latent nationality or stereotype representations appear before they are verbalized in the model output. This work connects activation-level interpretability with bias evaluation for underrepresented Spanish varieties. --- ### Smart predict-then-robustly-optimize Authors: Aakil Caunhye, Xuefei Lu, Belen Martin-Barragan Published: 2026-07-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2607.21773v1 In this paper, we propose and study a robust variant of the smart predict-then-optimize approach that accounts for prediction shifts due to disturbance in the covariate feature space. While traditional integrated-learning-and-optimization models assume that side information is perfectly revealed, empirical data-driven features are frequently corrupted or noisy at the time of decision-making, leading to fragile operational policies. To bridge this gap, we integrate principles of robust optimization directly into the predictive-prescriptive pipeline via a smart predict-then-robustly optimize loss and establish a computationally tractable convex surrogate, designed to hedge against worst-case feature perturbations. On the theoretical front, we formalize the structural validity of this surrogate by proving its approximation error probability decays exponentially according to a sub-Gaussian concentration profile. Furthermore, we establish that under mild assumptions, the surrogate is Fisher consistent with high probability. We also prove necessary conditions under which our framework outperforms standard smart predict-then-optimize and maintain its superiority even when the standard method is equipped with regularized upstream predictions. Numerical experiments validate that our robust framework consistently yields significant performance improvements over standard methods, both in out-of-sample terms and in training stability. --- ### Reliability-Aware Bayesian Optimization of 1310 nm PCSELs with FDTD Verification Authors: Jinglin Yu, Feiyang Wu, Longying Wen, Chongxian Yuan, Renjie Li, Zhaoyu Zhang Published: 2026-07-23 Categories: physics.optics, cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2607.21772v1 Near 1310 nm photonic-crystal surface-emitting lasers (PCSELs) are attractive narrow-beam sources for optical communication and sensing, but their final design refinement is costly. Small geometry changes simultaneously shift the band-edge resonance, cavity leakage, far-field divergence, and the numerical stability of a high-$Q$ decay fit, while every full-wave trial requires a time-domain simulation. We couple a commercial finite-difference time-domain solver to a reliability-aware Bayesian optimization (BO) loop over eight local design variables. Each completed simulation updates the surrogate used to choose the next geometry. Candidate ranking combines wavelength and beam-quality requirements with a reliability-adjusted metric $Q_{\mathrm{eff}}$ derived from the solver-reported relative fit-error estimate $dQ/Q$. Across three 80-evaluation runs from the same reference model, BO produced 5--15 candidates per run that passed the joint filter. Designs reconstructed from fresh model copies retained $Q_{\mathrm{eff}}=4.33\times10^6$--$7.76\times10^6$, a 60--108-fold increase over the baseline metric, at 1308.23--1310.90~nm with approximately $0.84^{\circ}$ divergence. Under equal budgets, BO gave the highest mean strict-filter yield (9.0 candidates), compared with differential evolution (7.0) and Latin-hypercube sampling (1.5), although the controls occasionally matched the peak $Q_{\mathrm{eff}}$. Field maps, resonance spectra, and local perturbations further identify an index-related wavelength handle and a hole-size-related leakage handle. The resulting FDTD budget produces a pool of wavelength-compatible, narrow-beam, and reproducible high-$Q$ PCSEL candidates without trusting a single optimistic decay fit. --- ### Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks Authors: Michael Kouremetis, Ads Dawson, Raja Sekhar Rao Dheekonda, Brian Greunke Published: 2026-07-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.21763v1 Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 frontier models from 7 providers on 23 Cybench capture-the-flag (CTF) challenges under three prompt conditions (no anti-cheat, standard, severe). All 1,518 task traces were individually audited through a four-stage pipeline combining LLM-as-a-judge classification, programmatic verification, judge-verifier reconciliation, and human review. We find cheating is far more pervasive than previously estimated: under baseline conditions, 37.1% of passes involved cheating, 21 of 22 models cheated, and scores were inflated by up to 5x. Anti-cheat prompts reduce cheat propensity from 33.0% (baseline) to 17.8% (standard) to 8.5% (severe) without degrading, and sometimes improving, solve rates. However, even under the most restrictive prompt condition, eight models still produced cheated passes, four showed backfire effects, and cheating escalated from web search toward infrastructure probing. We introduce the "solve rate" metric (clean passes only) to distinguish genuine capability from cheated outcomes, and argue it should be standard practice in any evaluation where cheating vectors are available. Anti-cheat prompts are an effective and essentially free first layer of defense, but they are not a substitute for environmental controls. --- ### Encoding orders and trees in real-valued functions Authors: G Conant, C Terry Published: 2026-07-23 Categories: math.CO, cs.LG, math.LO arXiv: https://arxiv.org/abs/2607.21761v1 We prove function-theoretic analogues of a quantitative result of Hodges on extracting the order property from a sufficiently large 2-tree coded in a binary relation. Similar analogues for functions were previously obtained by Daskalakis and Golowich and by Anderson and Benedikt. These results are from statistical learning theory, where 2-trees are captured by sequential fat-shattering dimension, and the order property is controlled by various notions of "thresholds". Our first main result (Theorem 1.11) focuses on extracting a less restrictive kind of threshold from a tree, and yields significantly better bounds compared to what can be obtained from earlier results focusing on more restrictive versions. Part of the motivation for Theorem 1.11 lies in a companion paper, where this theorem is used to obtain efficient bounds in quantitative regularity lemmas for "stable functions". Here will use Theorem 1.11 to reprove a result of Anderson and Benedikt in a stronger form and with improved bounds. We also use Theorem 1.11 to prove an at most double-exponential bound on dual sequential fat-shattering, which resolves an open problem. In our second main result (Theorem 1.14), we give a new proof of a result of Daskalakis and Golowich on extracting "tight thresholds" from large sequential fat-shattering dimension, with improved bounds. This resolves another open problem related to correcting the proof of a result claimed by Jung, Kim, and Tewari. --- ### Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing Authors: Shenzhe Zhu, Haoqian Zhang, Xu Yang, Jingyu Tang, Yi Nian, Xiaoxue Du, Shu Yang, Alex Pentland, Joachim Baumann, Jiaxin Pei Published: 2026-07-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.21758v1 Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing. --- ### Co-design of LLM-based preference agents: participation may drive overtrust Authors: Michael J. Fell Published: 2026-07-23 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.21757v1 Large language models are increasingly used to simulate human preferences in research and practical applications, raising concerns about validation, misrepresentation, and exclusion. Co-designing agents with the people they represent is a promising way to address these concerns, but participation may also mask the problems it appears to solve. This paper explores that tension through a primarily qualitative study in which 12 participants co-designed personal preference agents in the domain of household energy, via a background survey, co-design interview, and validation survey. Participants engaged readily and mostly came to see their agents as representing them well. Independent validation, however, revealed mixed human-agent alignment, with agent responses markedly more homogeneous, decisive, and abstract than the human sample. I argue that participation and process transparency can act as an "overtrust engine" that promotes trust while concealing systematic misalignment with potential structural consequences at scale. I develop this as a core mechanism in participatory preference agent design, treating individual alignment not as a fixed state but as an enacted process. --- ### Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting Authors: Denis Mayr Lima Martins, Gottfried Vossen Published: 2026-07-23 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2607.21756v1 Large Language Models (LLMs) are increasingly used in database-backed applications to classify tuples, filter records using semantic predicates, extract structured attributes, and enrich query results. Yet the prompt that start these computations are typically stored outside the DBMS in unstructured formats, making them invisible to query execution, metadata management, and optimization. Drawing on Stonebraker's QUEL as a Data Type and the principles of reflective programming, this paper introduces PromptDB, a database system that treats prompts as tuple-level database values. PromptDB provides a logical PROMPT datatype whose values store a template, bindings to tuple attributes, model metadata, and task metadata. Relations may contain PROMPT attributes directly in base tables, or expose them through views over joined tuples. Users query prompt-valued attributes through generated evaluation views, while the system internally renders, rewrites, optimizes, and executes prompts through an EVAL operator. Making prompts database-visible creates a new optimization space. The key idea is to bring query-optimizer thinking to prompts: just as query optimizers exploit database metadata to rewrite SQL plans, PromptDB exploits database metadata to rewrite prompts. We evaluate PromptDB on synthetic and real-world data workloads across different tasks. The results show how database-guided rewriting improves output validity and yields favorable cost-quality trade-offs compared with static, manually written prompts. --- ### Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection Authors: Debarshi Kundu, Swaroop Ghosh, Vasant Honavar Published: 2026-07-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21752v1 Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive approaches---including SBM-Transformer, Dynamic Mask Attention, and NSA---typically require additional learnable parameters, custom gradient estimators, or specialized CUDA kernels. We show that classical data compression provides an effective masking signal with \textbf{no additional parameters}. By computing per-block gzip compression ratios, we identify non-redundant content blocks and route long-range attention selectively through them. Intuitively, blocks that gzip cannot compress contain information not predictable from local repetition, making them natural long-range attention targets. Because the compression profile is input-dependent, the resulting sparse mask adapts dynamically to content without learned parameters, auxiliary losses, or custom kernels. On PG-19 byte-level language modeling at 92M parameters with 8K context, our method achieves 1.71 bits-per-byte (BPB), outperforming dense attention (2.89), BigBird (2.34), Longformer (3.21), and a reimplemented SBM-Transformer (3.38)---the only learned-mask baseline---by up to 1.67 BPB while adding no parameters. The advantage grows with sequence length, with the gap over BigBird widening from 0.05 BPB at 4K context to 0.63 BPB at 8K, while convergence is 3.3$\times$ faster. --- ### Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery Authors: Khalid El-Darymli, Christoph H. Gierull, Katerina Biron, Weimin Huang Published: 2026-07-23 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.21745v1 Radar cross-section (RCS) modeling is foundational to advancing the utility and sensitivity of spaceborne radar systems. This study introduces a deep sigma-point process (DSPP) model for predicting RCS in synthetic aperture radar (SAR) imagery using a RADARSAT-2 dataset containing 208,191 verified ships. The DSPP model not only strives for predictive accuracy but also characterizes the uncertainty inherent in the intricate relationships among radar signals, ship parameters, and environmental conditions. Unlike traditional approaches that rely on deterministic equations with static parameters, the DSPP uses a hierarchical Gaussian process framework with Bayesian inference to capture variability and uncertainty in RCS predictions. By generating predictive distributions rather than single estimates, the model accounts for the complex dynamics governing radar returns. Using a Matern kernel with automatic relevance determination, the DSPP identifies and ranks critical features across radar, operational, and environmental domains, thereby supporting transparency and interpretability. Performance evaluations demonstrate the model's superiority over linear regression baselines, with a 20.83 percent reduction in root mean squared error, a 25.89 percent increase in R-squared, and a 44.4 percent reduction in both the residual interquartile range and median absolute deviation on the test data. By providing calibrated uncertainty bounds, the DSPP enhances prediction reliability and supports robust decision-making. This work represents a shift toward probabilistic models that incorporate the inherent uncertainty of complex phenomena. By transitioning from fixed equations to distributions over outcomes, the DSPP fosters a deeper understanding of RCS behavior and enables systems to operate effectively in dynamic environments. --- ### What AI Red-Team Evaluations Can and Cannot Prove Authors: Bandana Kaur Published: 2026-07-23 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.21735v2 Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget, derive it in closed form for the benchmark null result, and use it to locate that boundary exactly. We find that above a calculable harm rate, a benchmark of modest size certifies a category to a stated evidentiary standard, and a clean sheet is then the stronger of the two possible observations, outweighing a single reproduced failure. Below that rate, no passive benchmark of feasible size provides the specified evidence of safety under the fixed scoring rule and approximately independent trial structure. The crossing between the two regimes has a closed form. The bound is not specific to benchmarks: written in terms of a procedure's hypothesis conditioned elicitation rates, it covers adaptive and automated red teaming as well, and shows that discrimination between the hypotheses rather than attack success is what determines evidential worth. Auditing eight evaluation suites against the boundary, we find that current benchmarks are adequate for high-frequency harm categories and several orders of magnitude short for rare, catastrophic ones. Safety benchmarks are not uninformative. They are informative about a specific and computable set of propositions, and the discipline they need is to state which. --- ### RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory Authors: Zahra Yousefijamarani, Alaa Alameldeen Published: 2026-07-23 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2607.21731v1 Transformers are widely used across many domains, including natural language processing, computer vision, web search, and DNA sequence analysis. Given their broad applicability, improving the performance of transformer models is critical. However, the high volume of data movement between processing units and memory during attention operations significantly limits their efficiency. Processing-In-Memory (PIM) mitigates this issue by performing computations directly inside memory. While prior work has proposed PIM-based transformer implementations, they suffer from costly inter-bank communication, and struggle to scale due to the limited capacity of memory banks. As a result, attention-related data must be split across banks, diminishing the potential benefits of PIM. In this work, we propose RED-PIM, an algorithm-architecture co-design that reduces attention latency by minimizing inter-bank data movement from O(N^2) to O(N) and shrinking intermediate attention matrices from N x N to d x d. By reorganizing matrix operations, performing computations locally, and employing an optimized data transfer strategy, RED-PIM significantly reduces computation cost and interconnect traffic. Compared to baseline PIM implementation, RED-PIM achieves inference time reductions ranging from 16.05% to 99.99% (geometric mean of 66.42%), with the largest gains on longer sequences. On real-world datasets, RED-PIM improves performance by 99.60% for long documents and 13.44% for shorter ones, while maintaining or improving accuracy. These results demonstrate RED-PIM's effectiveness for scalable and efficient transformer inference. --- ### Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints Authors: Liqiang Jing, Xiong Zhou, Siddharth Varia, Neha Anna John, Xinya Du, Vassilis N. Ioannidis Published: 2026-07-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.21722v1 While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks largely focus on symbolic mathematical or scientific problems and simple vision-centric tasks, offering limited assessment of complex visual reasoning and logical consistency, a critical requirement for reliable reasoning systems. We introduce ConVBench, a complex vision-centric reasoning benchmark in which each image is paired with two logically equivalent questions across six categories: action and state, complex counting, spatial reasoning, causal and intent understanding, commonsense reasoning, and temporal perception. To complement this benchmark, we define two evaluation metrics, logical consistency and robust accuracy, that jointly assess both the correctness and consistency of model responses. We further present ConVLM, which improves LVLM reasoning through Group Relative Policy Optimization (GRPO)-based reinforcement learning with a novel consistency reward. This method leverages automatically generated logically equivalent question-answer pairs and a dual-reward design combining accuracy- and consistency-based signals, encouraging agreement between paired responses. The framework functions effectively with or without strict answer supervision. --- ### Priors learned from legacy reconstructions inherit undetectable overconfidence Authors: Ali Siahkoohi, Sina Alemohammad Published: 2026-07-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.21721v4 Where truths are scarce (e.g., seismic and medical imaging), learned priors in ill-posed inverse problems are trained on archives of legacy reconstructions---i.e., an older method's outputs---and their reported uncertainty is taken as data-driven. We show that this prior is, in the population limit, exactly the regularizer that produced its archive of posterior samples, advanced one expectation--maximization step toward the truth. While the step improves the regularizer on the directions the measurements resolve, it leaves the regularizer's assumption on the operator's blind subspace unchanged. An archive of single-best reconstructions collapses the blind interval to zero width. Neither error is detectable in practice, as truths differing only on the blind subspace share the data law, and simulation-based calibration is neutral by construction. We identify from the operator alone which directions the measurements do not inform, and, given a handful of ground-truth models, build intervals there that contain the truth as often as they claim to. We validate these findings on a two-dimensional example with closed-form predictions and in controlled experiments on seismic-imaging and groundwater-flow operators, against priors trained on the truth. --- ### Prior laundering: learned priors with inherited, undetectable overconfidence Authors: Ali Siahkoohi, Sina Alemohammad Published: 2026-07-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.21721v2 Learned generative priors now supply the regularization in ill-posed imaging inverse problems, and the uncertainty read from their posterior samples is taken as evidence earned from data. When examples of the true image are scarce, as in seismic and medical imaging, the widely adopted recourse is to train such a prior not on truths but on an archive of past reconstructions---prior laundering. We show that the uncertainty it then reports can be overconfident, and that no measurement-side check can reveal it. On the directions a forward operator leaves unresolved, this prior reports not what the data support but the assumption built into the older reconstruction method. More specifically, when the archive holds posterior samples, its population law---averaged over the measurements---is exactly the old regularizer advanced a single expectation--maximization step, frozen on the operator's blind subspace. The freeze leaves no signature in the data. Two truths differing only there induce identical data laws, so no goodness-of-fit test separates them, and self-consistency diagnostics, simulation-based calibration among them, pass whatever the prior believes. In the more realistic case, where the archive keeps a single-best reconstruction rather than posterior samples, the blind credible interval collapses to zero width. We prove these statements and demonstrate the inherited overconfidence on deployed seismic and groundwater imaging against a truth-trained control. We recommend reporting which directions the operator resolves---separating the confidence the data support from belief inherited through the pipeline. --- ### A Defense of the Quadratic Model Authors: Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham Kakade, Alex Damian Published: 2026-07-23 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2607.21716v1 Due to the complexity of neural network loss landscapes, optimization theory is forced to rely on idealized models, and there is generally a tradeoff between how theoretically tractable the model is, and how accurately it describes the true optimization dynamics. In this work, we stress test the simplest possible model of optimization -- the quadratic model -- and show that it can be surprisingly predictive in an LLM setting with 150M parameters and 3B training tokens. Specifically, we show that Taylor expanding the model and the loss function at intermediate checkpoints through training can accurately predict the optimization dynamics over windows that can last up to 10\% of training. Having established this agreement, we then turn to analyzing the structure of these local quadratic optimization problems through two lenses: the Hessian spectrum and local stability. Using Lanczos quadrature with extremely deep probes, we are able to estimate the Hessian spectrum deep into the tail, and we find a surprising amount of structure in both the eigenvalues and eigenvectors, which depends on the batch size, preconditioner, and training time. We also empirically test local linear stability at intermediate checkpoints and compare it to theoretical predictions to demonstrate that optimization in LLMs typically occurs at a stochastic edge of stability, whose nature is also determined by batch size. Our results indicate the quadratic model may be a theoretically tractable proxy for pretraining optimization dynamics. --- ### An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning Authors: Maximilian Dax, Theo Heimel, Gilles Louppe Published: 2026-07-23 Categories: cs.LG, astro-ph.CO, astro-ph.GA, hep-ex, hep-ph, stat.ML arXiv: https://arxiv.org/abs/2607.21702v2 Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and the inversion of detector effects. We provide an overview of the Bayesian and frequentist statistical frameworks, describe how machine-learning-based SBI methods, such as neural posterior estimation and neural likelihood estimation, can be used for parameter estimation within these frameworks, and show that the same methods can also be applied to Empirical Bayes or unfolding tasks. We also discuss how to validate inference results and the limitations of SBI with machine learning. --- ### An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning Authors: Maximilian Dax, Theo Heimel, Gilles Louppe Published: 2026-07-23 Categories: cs.LG, astro-ph.CO, astro-ph.GA, hep-ex, hep-ph, stat.ML arXiv: https://arxiv.org/abs/2607.21702v1 Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and the inversion of detector effects. We provide an overview of the Bayesian and frequentist statistical frameworks, describe how machine-learning-based SBI methods, such as neural posterior estimation and neural likelihood estimation, can be used for parameter estimation within these frameworks, and show that the same methods can also be applied to Empirical Bayes or unfolding tasks. We also discuss how to validate inference results and the limitations of SBI with machine learning. --- ### Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On Authors: Yong Liu, Xiaolong Fu, Zihang Xu, Wen Xue, Xueheng Li, Lin Song, Yuan Zhang, Chuyang Zhao, Haoyang Huang, Nan Duan, Yipeng Sun, Yan Li et al. Published: 2026-07-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.21694v1 We present Oxygen-TryOn, a unified foundation model for any-item virtual try-on. Rather than repurposing a general-purpose image editor, Oxygen-TryOn is fashion-native, built for try-on through a dedicated data engine and try-on-specific training. Given one or more reference items (clean product shots or in-the-wild worn-on photos) and a single target subject image, it synthesizes a photorealistic image of the subject wearing the items across virtually any fashion category. Prior systems handle a single garment category in a studio setting, and recent multi-reference methods remain garment-centric; in contrast, Oxygen-TryOn supports diverse items and scenarios, including full- and half-body views, a variable number of references, and free multi-item composition, while faithfully preserving both subject identity and item appearance. Instead of mask-based inpainting, we reformulate try-on as a multi-reference, understanding-driven generation task. We build a data engine that collects, manufactures, annotates, and filters high-quality try-on data at scale, and design a three-stage recipe of continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). The RL stage uses a hybrid reward combining an in-house try-on reward model with a proprietary, rubric-guided general-purpose model, jointly supervising fine-grained consistency and instruction-level quality. It also follows general editing instructions (e.g., pose changes) in the same pass. Across public benchmarks and our in-house Oxygen-TryOn Bench, it achieves state-of-the-art consistency and realism on single-item try-on and leads on multi-item try-on, matching or surpassing both leading proprietary systems (Nano Banana Pro, GPT-Image-2, Seedream5 Lite) and open-source models (FLUX.2). --- ### Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets Authors: James E. Allchin Published: 2026-07-23 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.21692v4 Pruning a long context means committing to the blocks a model will keep, and the usual selector is distilled from a dense teacher's attention. That assumes attention shows which context the answer depends on. We test the assumption on retrieval tasks where the evidence is known exactly, by masking context and measuring whether the answer changes. Attention and causal dependence disagree. Teachers attend to outdated facts that the answer does not depend on, and they attend differently across training runs that use the same evidence. Selectors trained on that attention copy both failures. On a multi-hop retrieval task, a selector distilled from attention routes at 36% to 98% depending on the training run. The same selector trained on causal evidence sets reaches 99% or better on every run. Dense accuracy does not tell the teachers apart. Masking the frozen teacher recovers the causal sets of these tasks without annotations. Frozen pretrained models show the same conflict, and selectors supervised with known evidence labels beat attention-based eviction through 32B when context must be pruned before the question arrives. --- ### Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets Authors: James E. Allchin Published: 2026-07-23 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.21692v3 Pruning a long context means committing to the blocks a model will keep, and the usual selector is distilled from a dense teacher's attention. That assumes attention shows which context the answer depends on. We test the assumption on retrieval tasks where the evidence is known exactly, by masking context and measuring whether the answer changes. Attention and causal dependence disagree, and selectors inherit the disagreement: teachers attend to outdated facts that answer-preserving restrictions drop, and attend differently across training runs that use the same evidence. In a two-step reference task, a selector distilled from attention routes at 36% to 98% depending on the training run, the same selector trained on causal evidence sets reaches 99% or better on every one, and dense accuracy does not say which teacher you have. On the topologies our estimator covers, the causal sets need no annotation: masking alone recovers them from the frozen teacher. Pretrained models show the same conflict. Qwen2.5-3B attends more to an outdated fact than its replacement on 58% of the examples it answers correctly (48% past a first-token attention sink), a causal router lifts Gemma-2-9B from 56% to 98%, and no readout we test recovers a two-hop chain that all three tested models solve. On our teachers a one-pass cross-layer trace supervises chains as well as the annotated sets, so the readout fails rather than the weights; interventions alone separate current from obsolete evidence, survive redundancy, and stay stable across training runs. --- ### Explainable quantum-compressed machine learning for complex fluid flows Authors: Xiao Xue, Maida Wang, Mingyang Gao, Minh Chung, Peter V. Coveney Published: 2026-07-23 Categories: physics.flu-dyn, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2607.21688v1 Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear flows, whereas expressive deep surrogates match high-fidelity simulations only through massive parameterisations that turn the learned dynamics into a black box. Here, we introduce quantum-compressed machine learning (QCML), which resolves this tension by compressing the latent propagator of a flow surrogate from $524{,}288$ trainable parameters to no more than $8$. This parameter reduction brings the learned dynamical law to the parameter scale of a physical constitutive relation rather than a black-box neural network, making the surrogate directly interpretable and controllable without sacrificing expressivity. The compression is realised by a structured quantum circuit whose unitary propagator constrains the latent spectrum to the unit circle exactly and by construction, replacing exponential error growth with linear accumulation over autoregressive rollouts. Classical regularisation only approximates this constraint: even a quantum-inspired classical baseline penalised towards unitarity collapses within one Lyapunov time on turbulent channel flow, whereas QCML remains stable over the full rollout. Shared phase and coupling angles parameterising the circuit correspond directly to modal frequencies and inter-mode interactions, giving the learned dynamics a physical interpretation in spectral space. On two patient-specific cardiovascular benchmarks, the structured QCML propagator matches the predictive accuracy of its classical counterpart on surface pressure spectra, pressure drop, and wall shear stress. These results establish QCML as a working component of scientific machine learning and a concrete contribution towards practical quantum advantage in real-world prediction. --- ### Persistent Computational State: A Session-Centric Runtime for Generative World Models Authors: Zhen Lin Published: 2026-07-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21686v1 Generative world models are increasingly driven as simulators: a planner forks a state, rolls out futures, backtracks, and returns to a visited viewpoint. Recent benchmarks establish that current video world models fail this usage, and attribute it to the model, prescribing new architectures and training objectives. We show this attribution is incomplete, and for an important class of models simply wrong. Snapshotting the state the runtime already holds -- an observation plus RNG state, a memory bank, or a windowed KV context, by architecture -- and restoring it after a genuine excursion reproduces the never-left continuation byte-identically on all three; corrupting only the RNG degrades it. The capability was never missing: request-centric serving discarded it, inheriting from language-model serving the assumption that runtime state is recomputable -- but world-model state carries a non-recomputable kernel. We define Persistent Computational State (PCS), the minimal non-recomputable state that must survive across requests, show it can be discovered by measurement, and build a session-centric runtime over it. Checkpoint and restore cost 0.012 ms against a 1.85 s generation step; resident sessions become host- rather than device-bounded (measured to 1,024); and world memory must be evicted by relevance to the return, not recency -- the inverse of LLM practice. --- ### Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark Authors: Samuel M. Okoe-Mensah Published: 2026-07-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.21685v3 A systematic review begins with someone reading thousands of abstracts to identify the few that are relevant, and classifiers are used to prioritise that reading. Their inputs are often augmented with Medical Subject Headings (MeSH), assigned either by expert indexers weeks or months after publication or by automatic tools at once. We did not identify prior work comparing the two directly as classifier features, or asking whether that comparison's outcome depends on how the classifier is evaluated. Using the Cohen et al. (2006) drug-class benchmark, we compare expert assignment against one mechanical procedure, substring matching against a MeSH vocabulary drawn from the benchmark, across a bag-of-words logistic regression classifier (seven reruns) and BiomedBERT (five seeds) on three topics. Under the canonical 5-fold full-corpus design the bag-of-words gap on Statins is +0.096 WSS@95%. Stratified subsampling to matched corpus size (n=803) reduces it by roughly two thirds, to +0.033, with a bootstrap interval that includes zero; 10-fold cross-validation at full corpus size reduces it by roughly four fifths, to +0.021. BiomedBERT under canonical evaluation gives +0.020, a difference of 0.001 from the bag-of-words 10-fold result. An empirical power analysis on a single canonical run per topic indicates that a Statins-sized effect at the per-fold variances of the other two topics would not have been detectable at that design (MDE 0.254 for Opioids, 0.384 for ADHD); at the pooled fold count of the multi-run protocol the bound depends on an effective sample size the design does not determine. The results bound the specific lexical matcher tested rather than automatic MeSH indexing in general. More broadly, benchmark conclusions about feature sources can change substantially under reasonable changes to the evaluation design. --- ### Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark Authors: Samuel M. Okoe-Mensah Published: 2026-07-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.21685v2 A systematic review begins with someone reading thousands of abstracts to identify the few that are relevant, and classifiers are used to prioritise that reading. Their inputs are often augmented with Medical Subject Headings (MeSH), assigned either by expert indexers weeks or months after publication or by automatic tools at once. To our knowledge the two have not been compared directly as classifier features, and no previous work has asked whether that comparison's outcome depends on how the classifier is evaluated. Using the Cohen et al. (2006) drug-class benchmark on three topics, we characterise a bag-of-words logistic regression classifier (seven reruns) and BiomedBERT (five seeds), then examine how the Statins result changes under alternative designs. Under the canonical 5-fold full-corpus design, the bag-of-words expert-vs-auto gap on Statins is +0.096 WSS@95%. Matching the corpus size to the smaller topics (n = 803) reduces it to +0.033 (95% bootstrap CI includes zero), and 10-fold cross-validation at full size to +0.021 (CI narrowly excludes zero). Under canonical evaluation BiomedBERT gives +0.020, within sampling noise of the bag-of-words 10-fold result. A power analysis indicates a Statins-sized effect would not have been detectable at the Opioids or ADHD variance, so those nulls are design-limited rather than informative. A representation asymmetry remains: 15.1% of Statins inputs exceed BiomedBERT's 512-token limit when expert MeSH terms are appended, so truncation may contribute to the smaller transformer gap, although this cannot be separated from training volume here. In screening pipelines using transformers or 10-fold bag-of-words, the gap on the topics tested is about 0.02 WSS@95%, with CIs spanning zero on at least one bound. More broadly, benchmark conclusions about feature sources can change substantially under reasonable changes to the evaluation design. --- ### CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting Authors: Awsaf Tausif Adib, Md. Shahria Sarker Shuvo, Md. Estehaar Ahmed Emon, Mustafa Kamal, Fuad Rahman, Shafin Rahman, Nabeel Mohammed Published: 2026-07-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21681v1 Accurately modeling cross-variate dependencies remains a key challenge in multivariate time series forecasting, particularly in the presence of strong periodic patterns. Many existing approaches rely on attention-based mechanisms that incur quadratic complexity and scale poorly with increasing numbers of variates. Recent attention-free aggregation models address this issue through linear-complexity core-based interactions, but they do not explicitly leverage the global periodic structure present in the data. To overcome this limitation, we propose CARNet, a Cycle-Conditioned Core Aggregation and Redistribution framework that integrates global recurrent cycle information into efficient core based interaction modeling via Multihead Core Aggregation. Extensive experiments on multiple real-world multivariate forecasting benchmarks demonstrate that CARNet consistently outperforms strong transformer and non-attention baselines across diverse prediction horizons while preserving linear-complexity modeling of cross-variate dependencies. --- ### Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA Authors: Takato Yasuno Published: 2026-07-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21680v1 Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the naked eye. Expert diagnosis relies on tacit knowledge built over years of practice. We address the challenge of automating this latent causal reasoning by proposing a Damage Cause Encoder that classifies 10-class damage causes from visible damage descriptions $S_i$ for use in autonomous bridge diagnostic agents. Our approach chains three components: (i)Knowledge Triple Extraction---a large language model extracts causal triples of the form (damage $\xrightarrow{\mathtt{caused\_by}}$ cause) from 15--35 diagnostic PDF manuals and indexes them in a FAISS vector store; (ii)Retrieval-Augmented Context---at training and inference time, relevant causal triples $\mathcal{C}_i$ are retrieved and concatenated with $S_i$, converting implicit domain knowledge into explicit Encoder context; (iii)Systematic Fine-tuning Comparison---we conduct a rigorous comparison of LoRA, QLoRA, and QA-LoRA on a fixed Golden Testset (116 stratified samples), demonstrating that QLoRA achieves the optimal trade-off: identical test accuracy (87.07%) to full-precision LoRA, 11% faster inference, 72% lower GPU memory, and superior generalization across diverse unseen inputs. A controlled Golden Testset---stratified, deduplicated, and difficulty-tagged---is introduced as a reusable benchmark contribution. QLoRA further outperforms LoRA by 13 percentage points on a 100-sample diverse evaluation spanning all 10 damage cause classes.These findings enable memory-efficient, high-accuracy diagnostic agents on consumer-grade hardware for edge deployment. ---