Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Thursday 13 August

Robotics

High-Bandwidth Biomimetic Finger for Tactile-Transparent Remote Texture Sensing

High-fidelity tactile feedback is essential for robotic teleoperation, enabling precise manipulation and critical decision-making. While biomimetic fingertip sensors can capture surface-texture features, how their design shapes the tactile transparency of rendered feedback remains poorly understood. This paper presents a biomimetic fingertip replicating the human finger's multilayer mechanical gradient and fingerprint morphology, with an embedded high-sensitivity inertial measurement unit capturing texture-induced vibrations for remote vibrotactile rendering. Three variants are compared with the human fingertip through temporal and spectral analyses and a user study spanning three perceptual dimensions, establishing a transmission chain from fingertip design through signal characteristics to tactile transparency. The multilayer mechanical gradient yields the clearest improvements in signal intensity and texture-feature representation, whereas a stiffer skin layer amplifies vibration intensity at the expense of feature representation. The perceptual dimensions draw on distinct signal attributes: roughness on energy scaling, granularity on spectral shape, and repetitivity on characteristic-peak representation. These findings offer design principles for application-specific fingertips in robotic teleoperation.
Read the full abstract

Sound

SceneTTS-Bench: A Benchmark for Scene-Level TTS in Drama Dubbing

Text-to-speech systems are increasingly used for drama dubbing, yet evaluation protocols remain sentence-level, leaving critical scene-level behaviors insufficiently measured. We present SceneTTS-Bench, a benchmark that evaluates TTS along three dimensions: timbre consistency across character turns, emotional expressiveness on high-tension utterances, and rhythm coherence under segmented long-form synthesis. The corpus comprises real-world and generated drama scripts totaling 160 bilingual scenes and approximately 10,300 utterances, with real-world scripts serving as the primary source (100 scenes) and generated scripts as a supplementary source (60 scenes), demonstrating the framework's extensibility through synthetic data augmentation. A backend-agnostic Canonical Intermediate Representation ensures fair cross-system comparison. Three automatic pipelines produce per-utterance diagnostics: Speaker Consistency Score for timbre-drift detection, Under-Acting Ratio for under-acting identification, and Rate Discontinuity Ratio for rate-discontinuity quantification. Experiments on four TTS systems confirm that each system exhibits distinct weaknesses and that scene-level rankings diverge substantially from sentence-level metrics. Benchmark resources are publicly available at https://piedpiperg.github.io/scenetts-bench/ .
Read the full abstract

All authors Yizhong Geng, Yanliang Li, Jinghan Yang, Tianhan Jiang, Yingming Gao, Ya Li

Information Retrieval

When Does Permutation Instability Generalize? Independent-View Validation for Listwise LLM Reranking

Listwise language-model rerankers often disagree across equivalent candidate permutations. Finite instability diagnostics are therefore used to motivate additional sampling, aggregation, or selective computation. But an association with a validation statistic that reuses the probe views need not isolate predictive information about unseen permutations. Shared measurements can induce classical part-whole association. We study how this affects claims that a finite-view instability score predicts unseen permutations. We derive the exact finite-view decomposition and prospectively compare zero, one, and two reused views, including a fully disjoint four-view target. The study covers two pinned 7B model families and two recommendation datasets, with controlled lists for signed offline analysis and untouched retriever lists for target-free replication. On the four controlled blocks, fully disjoint correlations are weak or heterogeneous (-0.061 to 0.281), whereas reusing both probe views yields 0.600 to 0.718; all paired contrasts are large (0.436 to 0.661) and Holm-significant. The overlap effect is positive in all four untouched-list blocks. Increasing the probe from two to four views clearly improves disjoint reliability in only one block. Moreover, the probe predicts aggregation-movement magnitude (Spearman rho = 0.142 to 0.426) but not stable signed target benefit, and 7 of 12 fixed-fraction probe-routing points are strictly dominated at measured cost. Thus, when the intended estimand is predictive information about unseen perturbation behavior, validation targets must be observation-disjoint from the probe to isolate that information; signed utility and cost-sensitive decisions remain separate questions.
Read the full abstract

Information Retrieval

Which Reranking Conclusions Survive the Answer Interface? A Prospective Finite-Orbit Audit

Rerankers are increasingly evaluated through downstream language-model answers. This raises a retrieval-measurement question: if only the reader's answer interface changes, should we reach the same conclusion about BM25 versus BGE-v2-m3? We prospectively audit their claim-paired effect on RAGuard and FEVER with four readers. Retrieval policies, evidence, claims, and context depth remain fixed while semantic-to-label binding, A/B versus X/Y vocabulary, and option order form eight task-equivalent interfaces. We ask whether the estimated retrieval-policy effect, its ordering, or selection value changes. None of the six confirmatory settings showed statistically certified interface variation above the prespecified 0.015 materiality threshold, and none showed a certified reversal of the BM25-BGE ordering. Selector disagreement reaches 33.5% in one environment, yet none of eight environments establishes the prespecified material held-out value difference. These results do not support broad replicated instability, but they do not prove universal invariance: five settings remain too uncertain to satisfy the prespecified higher-order equivalence condition. They show why retrieval evaluations should separate policy level, interface stability, policy ordering, and selection value. When stability is unverified, a uniform average over the enumerated interfaces with explicit variation bounds avoids privileging one interface.
Read the full abstract

Computation and Language

PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models

Diffusion language models (dLLMs), such as LLaDA and Dream, have become competitive with autoregressive (AR) LLMs in generation quality while supporting native parallel decoding. A standard acceleration strategy is block-wise decoding, where each forward pass predicts a block of length B and commits high-confidence tokens. Confidence-threshold commitment adapts which tokens are accepted, but a fixed B still constrains the prediction scope. Existing horizon policies use manually chosen sizes, volatility statistics, or candidate-boundary scores. We instead use the model's own per-step confidence: in-window confidence typically follows a context-dependent cliff, providing a direct signal for adapting the look-ahead horizon. In this work, we propose PACE-dLLM, which refits this parametric cliff periodically in closed form, sets the next horizon at a shared confidence anchor, and retains confidence-threshold token commitment. Under a saturated-yield abstraction with iid, policy-independent monotone profiles, the oracle horizon is the smallest attaining maximal per-pass yield and improves the asymptotic forward-pass rate when fixed blocks undershoot it with positive probability. On four reasoning and code benchmarks across two open-source dLLM backbones, PACE-dLLM achieves the best average accuracy among the evaluated decoders on both backbones, with average throughput speedups of 5.23x on LLaDA and 3.06x on Dream (up to 8.52x on LLaDA MATH) over the unaccelerated semi-AR baseline, advancing the quality-throughput Pareto frontier.
Read the full abstract

All authors Xiaocheng Lu, Shuhan Guo, Ziyue Ma, Jie Zhang, Jian Liu, Jingcai Guo, Haoxuan Che, Song Guo

Data Structures and Algorithms

Approximate Counting of $k$-Paths in $O^*(2^k)$ Time

We resolve the conjecture of Koutis and Williams that $k$-paths can be approximately counted in $O^*(2^k)$ time. For a simple directed graph with $n$ vertices and $m$ arcs, our randomized algorithm returns a $(1\pm\varepsilon)$-approximation with failure probability at most $\delta$ in $O^*(2^k\varepsilon^{-2}\log(1/\delta))$ time.
Read the full abstract

Machine Learning

Can You Delete a Year of Market Data? Machine Unlearning Against Exact Retraining Oracles

When a data license expires, deleting stored records does not remove influence encoded in a trained forecaster. Machine unlearning seeks to remove this influence without retraining. We benchmark temporal unlearning with 3,200 paired references trained on all data and oracles retrained without the requested period. The grid covers five architectures, four rolling folds, five deletable years, and three experimental deletion levels on an S&P 500 volatility panel. The 2020 COVID crisis year produces the largest memorization gap for every architecture. Removing it improves all three deployable models in every fold, with the largest improvement in the 2022 bear market, while the two non-deployable models respond inconsistently. The target for approximate unlearning is the oracle, not low predictive accuracy on the deleted period. In one Transformer cell, an oracle that never trained on 2020 still predicts it at an information coefficient of 0.51, compared with 0.55 for the reference; pushing predictions toward noise reduces test skill. Across twelve deployable architecture-method pairs, only TSMixer with the hinge method remains near the oracle in every fold, closing 74-118% of the reference-to-oracle gap without a measurable loss of test skill. Method rankings vary across architectures and rolling windows. Audit separation rises with prior memorization but can remain small after exact deletion. The window-level loss comparison reaches at most 0.69, and treating stock-level windows as independent inflates the absolute t-statistic by a median factor of 1.9. These results call for an explicit deletion scope, oracle validation for the relevant architecture and window, and power-aware auditing.
Read the full abstract

Data Structures and Algorithms

An $\widetilde{O}\left(n^2 \right)$-Time Sampler for Zero-Field Ferromagnetic Ising Models

We give an approximate sampler for ferromagnetic Ising models with no field on arbitrary graphs that runs in time $\widetilde O(m+n)+\widetilde O_\beta(n^2\log^2 (1 / \varepsilon))$, where $n$ and $m$ are the numbers of vertices and edges, respectively, and $\varepsilon$ is the approximation error. Our approach combines Benczúr–Karger cut sparsification with a new mixing time analysis of the Glauber dynamics for the random-cluster model. The mixing time analysis features a new monotone edge-count Poincaré inequality.
Read the full abstract

Logic in Computer Science

Pushout Attachments and Conditional Complexity of Executable Models

We represent the modular enlargement of an executable model by a pushout of finite typed presentations. Adhesivity preserves the original model and recovers the shared interface, while chosen pushouts make linking functorial and coproducts describe parallel attachments. A semantic comparison gives a precise criterion for behavioral persistence. Effective linking also bounds conditional prefix complexity; under the stated canonicalization and invariance assumptions, attachment and extension codes yield the same profiles of loss against complexity, up to additive constants, and share an exact scalar envelope. The result separates syntax, semantics, ideal complexity, and concrete coding cost, and shows that a preference for modularity can arise only through restrictions on the permitted attachments.
Read the full abstract

Machine Learning · Cross-listed from eess.SP

Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures

Cross subject emotion decoding from electroencephalography EEG requires representations that accommodate individual variability while preserving spatial spectral structure for interpretation. This study introduces EmoDiPyraTrans, a differential graph Transformer that integrates adaptive graph recurrence, differential attention, pyramid fusion and distribution regularization over sequential relative power spectral density graphs. Across SEED, FACED, MAHNOB HCI, DEAP and DREAMER, the model achieved the highest participant mean accuracy and positive class F1 among the evaluated methods, with accuracy and F1 both reaching 0.928 on SEED. On DEP EEG, positive versus neutral accuracy reached 0.802 within healthy controls and 0.704 within participants with depression, compared with 0.591 under healthy to depression transfer and 0.581 with mixed population development. Complementary SEED analyses identified distributed spatial weighting and an alpha centred spectral preference, while configurations averaging six channels retained near full performance. These findings link generalization assessment with model derived candidate signatures to support interpretable EEG emotion decoding, with code available at https://github.com/hdy6438/EmoDiPyraTrans.
Read the full abstract

All authors Dongyi He, Bin Jiang, Xiangkai Wang, Yun Zhao, Hongjie Yan, Wai Ting Siok, Nizhuan Wang

Machine Learning

Machine Unlearning for Speech Question Answering in Large Audio-Language Models

Large Audio-Language Models (LALMs) have recently shown strong capabilities in speech understanding and question answering (QA), but they also inherit privacy risks from large-scale training data, including the unintended memorization of sensitive information. In this work, we study machine unlearning for speech QA in LALMs, a setting that is more challenging than prior work on text-based Large Language Models (LLMs) or Automatic Speech Recognition (ASR) due to the tight coupling between acoustic perception and factual knowledge. We present and evaluate multiple unlearning strategies, including gradient ascent, task arithmetic, and alignment-based fine-tuning methods that enforce safe refusal responses, to remove private knowledge while still preserving performance on core capabilities. Through extensive experiments on speech QA datasets, we show that these unlearning methods can reduce the privacy leakage rate by up to 80% while maintaining near-neutral performance on non-private speech QA and general speech understanding benchmarks.
Read the full abstract

Multiagent Systems

Multi-dimensional Bias in Modeling Multi-dimensional Preferences: Evaluating the Ability of Synthetic Agents to Replace Human Participants in Conjoint Experiments

Despite growing interest in using LLMs to add robustness or reduce data-collection costs in survey experiments, their efficacy in conjoint design—an increasingly popular method in political science—remains underexplored. This paper addresses that gap by investigating whether synthetic agents can reproduce the multi-dimensional human preference patterns that conjoint is designed to capture. It replicates published conjoint studies and compares the results generated by synthetic agents with original human data along three dimensions: representational correspondence, inferential correspondence, and procedural stability. Our analysis evaluates the alignment of choice distributions as well as the statistical and substantive similarity of estimates, and the results are uneven across these dimensions and studies replicated. This implies that the validity of synthetic participants should be considered claim-dependent and hierarchical. Reproducing a figure or obtaining strong sign agreement is evidence of similar aggregate outputs, but not enough to support replacing human respondents. Our results suggest that the discipline as a whole must first map this innovation's boundaries across various levels before considering synthetic agents a robust substitute for human samples.
Read the full abstract

All authors Ho Ting Hung, Nachiket Midha, Victor Y. Wu, Yiwen Zhang

Computation and Language

Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict

Low-resource languages without an adequate training corpus often use a related, higher-resource language as a scaffold for comprehension. Still, there is a need to develop rigorous evaluation methods to identify when models fail in cross lingual low-resource environments. Using the legal domain as a backdrop, three models (Llama3, Hex-1, Sarvam) were tested on the ability to classify legal complaints written in a low resource Dravidian language (Tulu). Transliterating queries across Dravidian scripts allowed models to gain a preliminary understanding of speakers' complaints without the use of wide scale training, though the level of comprehension was heavily script dependent (with Kannada - another relatively low-resource language - producing the strongest positive trend). Retrieving from a corpus of Kannada legal papers across a RAG framework caused mixed results. Some models had a weak positive trend in comprehension under certain conditions, but when models failed, it was often across two axes: fact substitution (fixating on specific passage excerpts that skewed reasoning) and confabulation (hallucination that had no basis in either query or corpus). Within low resource domains, results identify the model's parsing of information and subsequent reasoning as the source of reasoning failure, rather than corpus contents. Script-dependent comprehension and RAG robustness also seem to travel together. This is further supported by the reasoning-trace analysis and a statistical-honesty framework deployed - techniques that are more broadly applicable to low-resource multilingual RAG evaluation.
Read the full abstract

Multiagent Systems · Cross-listed from physics.soc-ph

Measuring Collective Semantic Change in Populations of Language Model Agents

Collective semantic change in populations of language model agents is a measurable dynamical phenomenon. We present a passive longitudinal instrument called Kopterix that observes the semantic state of an agent population as a sequence of bounded observations under a protocol defined before the observations begin. Each observation divides the sampled feed by post age into surface, mid-stream, and residue layers, which makes semantic differences across content age measurable alongside run-to-run change. We validate the instrument on Moltbook, an agent-native social platform, over a two-month window of scheduled observations, with the periodicity check extended across approximately four months. At the lexical level, rarefied entropy resolves an April-May difference in the evenness of the stored top 200 unigram distributions, and adjacent states are lexically closer than states paired after timestamp shuffling. At the geometric level, grand mean centering exposes the scale of a common embedding direction, and scheduled shuffle checks support a recurring excess in the mid-stream to residue separation relative to the shuffled reference. At the temporal level, detrended scalar quantities and centered layer centroids lose much of their similarity over several hours, and a weaker positive component declines across longer separations with no strong weekly recurrence. Several attractive apparent structures failed their controls, and each reading is limited to the level its controls support. The design applies wherever a population of agents produces a timestamped language environment that can be observed repeatedly and divided by content age.
Read the full abstract

Computation and Language

A Multi-Framework Comparison of Outline Stages in Long-Form Generation with LLMs

Long-form generation exposes fundamental limitations of large language models. Even 70B-parameter models exhibit length collapse at 16k-token outputs, and multi-chapter stories frequently trigger the attribute drift characteristic of the “lost-in-the-middle” effect. The “outline-first, write-later” paradigm has gained wide adoption, yet existing research evaluates the final writing rather than the outline itself, conflating two evaluation objects that should be decoupled. We construct a unified head-to-head benchmark covering 7 representative long-form generation frameworks across 3 generation granularities – single-chapter, multi-chapter, and whole-book – and propose an anchor-based LLM-as-a-judge protocol that directly assesses outlines against the source text on a 5-point anchored scale. Across 21 framework-granularity cells, no single framework dominates; performance depends on the match between a framework's intrinsic output form and the target granularity. SuperWriter ranks first in the length-constrained single-chapter mode, but this advantage degrades in whole-book mode. The outline-side ranking correlates only moderately with the writing-side ranking, supporting the outline–writing decoupling principle. Compute constraints limit the writing-side evaluation to a subset of cases; follow-up experiments will expand the sample size and add cross-model evaluators to enable stronger statistical inference.
Read the full abstract

Computation and Language

Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment

This study examines whether LLM-generated replies remain semantically consistent when the underlying LLM changes. Using messages from real collaborative conversations, we compared the semantic similarity of generated replies across LLMs under two conditions: with and without preceding chat history. Results show that model choice and conversational context both affect response similarity and alignment with human replies. These findings indicate that prompting and conversational context alone may not be sufficient to preserve response consistency across LLMs, highlighting the need for infrastructure and design strategies that can maintain stable and comparable responses amid the rapid and continuous evolution of LLMs.
Read the full abstract

Artificial Intelligence

Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability

Manufacturing knowledge graphs that integrate data from heterogeneous industrial systems face a trust deficit: consumers cannot determine whether queried data is valid, whether it was valid when a decision was made, where it originated, or how it was acted upon. We argue that four trust capabilities – SHACL validation, PROV-O provenance, domain-aware bi-temporal versioning, and graph-native decision objects – compose through shared correlation identifiers to produce emergent trust properties that no single capability delivers alone. We present a composable trust infrastructure that integrates these four capabilities into a unified RDF architecture. Capabilities compose through shared entity URIs, ingestion activity identifiers, and temporal correlation keys, enabling compound queries spanning all four dimensions. An experimental ablation confirms that removing any single capability causes exactly three of six composition queries to fail, demonstrating that all four are equally load-bearing. Analysis of higher-order compositions reveals four emergent three-way properties and one irreducible four-way property (full-chain auditability, 31ms execution). The infrastructure is validated on a testbed integrating eleven industrial sources – OPC UA, TIA Portal, eClass, AAS, ISA-95, ISA-18.2, SAP S/4HANA, Teamcenter, Opcenter EX, Insights Hub, and SCM – under an 89-class ISA-95-aligned ontology. The unified graph contains 8,743 triples across five named graphs, stitched by 81 owl:sameAs identity edges. Evaluation uses simulated but structurally realistic data from purpose-built emulators; data structures and cross-system linkage patterns are representative of real industrial installations.
Read the full abstract

Artificial Intelligence

Retrieval-grounded robot program generation and simulation-based correction via Model Context Protocol

Flexible manufacturing requires industrial robots to be reprogrammed rapidly as product variants change. This paper presents a language-model-based workflow that generates, validates, and iteratively corrects ABB RAPID robot programs from natural language task descriptions. A dual-stream retrieval-augmented generation (RAG) pipeline grounds code generation in verified technical documentation and production templates, reducing domain-specific errors produced by ungrounded language models. A custom Model Context Protocol (MCP) server connects the language-model client directly to ABB RobotStudio for automated code upload, simulation execution, and diagnostic feedback. The evaluation combines a 30-query retrieval benchmark, scoped code-generation checks, and RobotStudio case studies in a simulated pickand- place manufacturing cell. The simulation loop exposes execution failures that static and semantic checks alone cannot catch, including suction release-height errors, unreachable placement targets, and configuration-dependent recovery motions. The results show how RAG and MCP can connect grounded code generation with executable feedback from industrial robot simulation software, while reducing but not eliminating expert setup and final supervision.
Read the full abstract

All authors Zhichao Zhou, Siyuan Chen, Omkar Salunkhe, Ebru Turanoglu Bekar, Johan Stahre, Anders Skoogh

Computation and Language

When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotators

LLMs have been increasingly used to catch data quality issues automatically, but we know very little about how consistent these judgments actually are. This study tests an LLM on two e-commerce data quality tasks, entity matching and brand mislabeling, against rule based baselines and human verified ground truth, under both zero-shot and few-shot prompting. On entity matching while using the Abt Buy benchmark (2,194 labeled pairs), a simple rule based baseline (F1=0.950) performed about as well as LLM zero shot prompting (F1=0.948). Moreover, a few-shot prompt revision that looked effective on a small validation sample reduced full-scale performance to F1=0.914. This showed that small sample prompt evaluation can be misleading. On brand mislabeling detection, using 500 Amazon product listings with synthetically injected labeling errors, the LLM clearly outperformed a naive rule based baseline (F1=0.833 vs 0.721), because it could draw on background knowledge of brand product relationships that a simple rule could not access. Testing consistency across repeated runs (200 pairs, 5 runs at temperature 0.7) showed the model agreeing with itself 99.7% of the time on average, with 99% of pairs giving identical answers across all 5 runs. Using majority voting across these runs only improved F1 by 0.005, at 5 times the inference cost. These results suggest that the value of using an LLM over traditional methods depends heavily on the task. LLMs offer little advantage when strong lexical signals already exist, but a clear advantage when the task requires background knowledge, all while remaining highly consistent across repeated queries.
Read the full abstract

Hardware Architecture

FPGA Lifecycle Management for RISC-V Systems

FPGA lifecycle management remains tied to proprietary toolchains and host architectures, leaving RISC-V without a vendor-neutral model for scalable bitstream deployment. A host-agnostic control-plane architecture is presented that shifts lifecycle management to the operating-system layer by leveraging standard Linux capabilities, thereby decoupling deployment from specific ISAs and vendor stacks. This enables Linux-capable RISC-V processors to serve as control hosts in heterogeneous FPGA systems. Prototyped on a Zynq-7000 SoC and generalizable to RISC-V platforms, the architecture provides a portable foundation for fleet-scale FPGA management.
Read the full abstract

Artificial Intelligence · Cross-listed from quant-ph

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous studies find that well-tuned classical models remain competitive, and that apparent quantum gains may be artefacts of classical dimensionality reduction and implicit regularisation rather than genuine quantum effects. We ask not whether a quantum model can post a high accuracy, but how quantum the advantage really is. We present a unified, reproducible QML-IDS benchmark evaluating hybrid variational quantum circuits and quantum-kernel SVMs against five honestly-tuned classical baselines across four standard NIDS datasets (NSL-KDD, UNSW-NB15, CICIDS2017, NF-ToN-IoT-v2) under one leakage-controlled protocol, with an equal-budget feature view, imbalance- and calibration-aware metrics with significance testing, and a simulated NISQ noise sweep. We introduce a quantum-attribution audit (parameter-matched classical controls, a random-feature kernel, and a regularisation sweep) that quantifies how much of any gain is genuinely attributable to the quantum component. Tuned classical models (Random Forest, XGBoost) match or exceed the quantum models on aggregate detection on every dataset, and the audit attributes this to classical preprocessing and regularisation rather than quantum effects. Two advantages survive false-discovery-rate correction: the quantum-kernel SVM out-ranks its direct classical surrogate (a random-feature kernel) on AUPRC and ROC-AUC, and a small four-qubit hybrid out-detects the best classical baseline at the 1% false-positive operating point on the distribution-shifted NSL-KDD task (p = 0.005, BH q = 0.030). Code, seeds, and splits are released; our contribution stands whether quantum wins, ties, or loses.
Read the full abstract

All authors Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Shahid Munir Shah, Asher Ali, Hamzah Siddiqui

Machine Learning

Iterative Refinement Diffusion for Super-Resolved Data Assimilation of Multiscale Physical Systems

Recovering high-resolution states from sparse, low-resolution observations is a central challenge in scientific machine learning and data assimilation. Classical data assimilation exploits temporal information through forecast-analysis cycles, but often requires repeated access to expensive high-resolution forecast models. Generative super-resolution can recover unresolved structure from coarse observations, but is commonly used as a one-shot mapping that does not fully exploit constraints from past states. We introduce Iterative Refinement (IR), a learned data assimilation framework that combines these perspectives. Instead of performing a single coarse-to-fine reconstruction, IR decomposes the task into resolution-wise forecast-analysis operations across a multiresolution hierarchy. At each stage, a shared neural operator with resolution-dependent spectral mode slicing provides a dynamical prior, while a shared conditional diffusion corrector uses the current coarser-resolution state to produce a refined posterior at the next finer resolution. We evaluate IR on one-dimensional stochastically forced Burgers dynamics and two-dimensional Kraichnan turbulence. On the challenging 256x256 Kraichnan benchmark, IR achieves an RMSE of 0.184 and an SSIM of 0.836, outperforming spectral upsampling, one-shot diffusion super-resolution, enhanced deep super-resolution, and an autoregressive forecaster. On the more constrained Burgers testbed, IR remains competitive with one-shot diffusion, which achieves the lowest RMSE. These results show that one-shot generative reconstruction can be effective for simpler settings, while hierarchical forecast-analysis refinement becomes advantageous in strongly multiscale and underdetermined regimes. Overall, IR combines temporal priors, generative correction, and multiresolution reconstruction for learned data assimilation in complex physical systems.
Read the full abstract

All authors Mrigank Dhingra, Ramchandran Muthukumar, Rebecca Willett, Omer San

Machine Learning

Generative Learning of Separatrices

The identification and reconstruction of the boundaries separating basins of attraction in multistable, multidimensional dynamical systems presents a fundamental challenge in computational dynamics. These structures govern transition pathways and other important large timescale behavior, yet they remain typically under-sampled since their neighborhood does not get routinely visited during direct simulations. Traditional computational approaches face computational limitations in high-dimensional systems and require a priori knowledge of the dynamical system and its equations. Simplistic sampling methods such as random or uniform sampling of the phase space typically fail to quantitatively approximate separatrices and their structure altogether. We introduce and implement a framework that combines supervised classification with generative modeling to address this challenge. Our approach first trains neural network classifiers on uniformly or randomly sampled initial conditions labeled by their corresponding basins of attraction in the system of interest. Using uncertainty metrics of the trained classifier to quantify decision boundaries, the method then identifies these high uncertainty regions and boundaries of the classifier as preliminary approximate separatrices. Subsequently, score-based generative models are trained specifically on samples from high-uncertainty regions, ultimately generating densities of samples consistent with the empirical density of samples on or close to the manifold that constitutes the separatrix between basins in the sampled region. This approach leverages the complementary strengths of (a) discriminative models for global phase space partitioning and (b) generative models for detailed geometric sampling, resulting in a systematic, iterative, data-driven framework that produces empirically consistent reconstructions of (approximate) separatrix manifolds.
Read the full abstract

All authors Ellis R. Crabtree, Dimitris G. Giovanis, Anastasia Georgiou, George Datseris, Ioannis G. Kevrekidis

Software Engineering

PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns

Pandas has emerged as the de facto library for data processing and machine learning, widely used for tasks, such as data loading, transformation, and analysis. Despite its ubiquity, there has been limited systematic investigation into how Pandas is used in real-world projects and how typical workflows are composed in practice. To address this gap, we introduce PandasCorpus, a dataset curated from GitHub repositories that captures real-world Pandas workflows at scale. In this work, a workflow refers to Pandas-based code contained in Jupyter notebooks, a prevalent medium for writing, executing, and sharing data analysis code. The dataset comprises 139k notebooks from approximately 100k repositories and captures more than 4M Pandas API calls spanning 136 distinct operations. Beyond dataset construction, we characterize workflows using structural and Pandas-specific features and analyze notebook evolution between 2015 and 2025. Our study examines code executability, notebook size, and recurring sequences of Pandas operations, providing empirical insights into how Pandas is used in practice. The resulting corpus offers a reusable resource for studying data analysis workflows, Pandas usage patterns, and library-aware code composition. Both the dataset and the extraction pipeline are publicly available via GitHub and Zenodo.
Read the full abstract

Computer Vision

PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models

We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning. In each problem, a model must identify which of four options shows a pair of polycube components that can be combined to form a target solid. The benchmark contains 120 problems across four geometry families, and each problem has three different presentation formats using either a single image or multiple images. The random guessing baseline is 25%. Across the three presentations (360 presented problems per model), GPT-5.6 Sol with max effort attains 50.0% accuracy (95% problem-cluster CI 43.3-56.7%) at a mean cost of \$0.951 per presented problem, Claude Fable 5 with max effort attains 39.4% (33.1-46.1%) at \$0.701, and Gemini 3.1 Pro Preview with thinking level high attains 27.5% (22.8-32.5%), near the 25% random guessing baseline, at \$0.350. The observed accuracy spread across geometry families is larger than across presentation formats. We present a problem development and evaluation protocol, cost and token accounting, and release the 120 problems.
Read the full abstract

Computer Vision

From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation

Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from visual context. However, semantic-only conditioning and creation-only training do not explicitly supervise the local structure needed for precise, temporally consistent editing. We therefore formulate depth and surface-normal prediction as image-form denoising targets, using these dense tasks as structured visual supervision within the same creation interface. Our framework decouples semantic interpretation from spatially aligned visual injection while sharing one multimodal diffusion transformer (MMDiT) backbone across all tasks. Mutual Context Attention (MCA), a paired-video data-construction procedure, and a progressive training curriculum then connect the learned structural cues to temporally localized editing and reference-conditioned creation. A single checkpoint obtains the highest overall score in the reported comparison of unified systems (4.15); adding dense supervision improves OpenVE Overall from 3.98 to 4.06 and Local Add from 3.92 to 4.18. These results support a deliberately bounded conclusion: perception-oriented dense supervision transfers useful structural knowledge to downstream creation, especially editing locality and preservation; we do not claim superiority as a standalone dense predictor.
Read the full abstract

All authors Zhefan Rao, Bin Zou, Xuanhua He, Chong Hou Choi, Yanheng Li, Rui Liu, Haoxuan Che, Qifeng Chen

Computation and Language

Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews

This study analyses LLMs in imbalanced binary classification, using study screening in systematic reviews as the application domain. An experiment was conducted in five reviews, comparing individual and batch processing, with and without prevalence metadata. The results indicate a limited influence of the prevalence metadata, with no evidence that it improves performance. In contrast, batch processing produced larger behavioral changes that varied according to the prevalence of the class. The aggregate and item-level analyses did not always coincide. Therefore, batch processing should be evaluated not only in terms of cost, but also in relation to its effects on decision-making behavior.
Read the full abstract

Cryptography and Security

Not Discrete Enough: On the Inherent Insecurity of dTPMs for Measured Boot

Measured Boot, a mechanism enabled through Trusted Platform Modules (TPMs), is commonly used for passwordless protection of data-at-rest, aiming to protect data when the device is lost or stolen. Microsoft's standpoint is neutral on which way a TPM should be implemented: Firmware-based TPMs (fTPMs) are viewed as more economical but less secure. Despite the inherent susceptibility to bus sniffing attacks, discrete TPMs (dTPMs) are still seen as the gold standard, as many deliver better on-paper tamper resistance. It is often argued that attacks against the bus can be mitigated by bus encryption and, ideally, mutual authentication between the CPU and TPM. This position paper aims to emphasize another inherent, difficult-to-mitigate attack against dTPMs that was originally shown against a TPM 1.1 over 20 years ago: We demonstrate that even brief physical access to a TPM 2.0 and the ability to boot from an attacker-controlled system enable an attacker to reset and replay arbitrary measurements, thereby allowing an attacker to unseal, for example, a disk encryption key solely protected by the TPM. While there have been attacks against fTPMs, too, we argue that their practical attack surface is fundamentally smaller. Bus protection techniques can be used to protect dTPMs, but only guard against passive attacks. After all, we argue that, from a security standpoint, firmware TPMs, or any TPM internal to the SoC, are superior to discrete (external) ones. Lastly, in order for dTPM-based setups to provide meaningful protection of sealed secrets, configurations must require a user-provided PIN or password along with the Measured Boot configuration.
Read the full abstract

Cryptography and Security

AccretionLink: On-Device Auditing of Exposure-Control Attacks on Attribute Inference

Exposure control lets an adversary rank authentic public posts to strengthen private-attribute inference without altering content. AccretionLink defines confidentiality and integrity games for this attack, models bounded selection odds through partial identification, and constructs dependence-aware time-uniform e-processes. On 52 held-out synthetic profiles, odds-four selection reduced aggregate negative log likelihood at every horizon. At eight posts the advantage was 0.01595 nats (95% CI [0.00890, 0.02336]), three of four target effects survived Holm adjustment, and label-blind model-guided selection caused 6/109 high-confidence false reversals. On 142 PAN15 test profiles, exploratory selection produced a 0.01227-nat advantage but no reversal. A separate TF-IDF selector retained a 0.01470-nat advantage against the unchanged G5 target, while matched identity shuffling did not reproduce it. Pixel 10 encoded all 1,622 held-out posts once with a fallback-free Tensor G5 graph. A P-256 checkpoint authenticated the selected-replay, actual-model, native-report, and operation digests; local KeyInfo identified the signing key as StrongBox-backed.
Read the full abstract

Machine Learning

Unraveling the Size Determination Mechanism of Nanocrystal Synthesis via Interpretable Neural Networks

Deep learning models of nanocrystal synthesis enable the prediction of size and shape by encoding precursors and reaction conditions. However, their black-box nature hinders gaining deep insights into the underlying synthetic mechanisms. Here, we develop the Nanocrystal Equation Learner (NanoEQL), a fully white-box neural network to unravel the size determination mechanisms of nanocrystal synthesis. Building on the EQL architecture, eight operators are introduced to replace standard activation functions to fit the mathematical equations in nanocrystal synthesis. Among these operators, three smoothed operators address the gradient explosion of singular operators at zero. To evaluate the weights of different precursors, we develop a temperature-gated attention pooling strategy that encodes concentration-driven and reactivity-driven chemical synthesis mechanisms into the temperature gate. The NanoEQL model illustrates that the final nanocrystal size can be described by a linear equation composed of three scalars representing nanocrystallization capability (-Zp), growth capability (Zrea), and external input potential (-Zops). These interpretable scalars not only advance the rational design of nanocrystal synthesis but also establish a generalizable paradigm for deciphering chemical reaction mechanisms through white-box machine learning.
Read the full abstract