Search

Early and optimal identification of cardiac anomalies, especially Myocardial infarction (MCI) can aid the individual in obtaining prompt medical attention to mitigate the severity. Electrocardiogram (ECG) is a simple non-invasive physiological signal modality, that can be used to examine the electrical activity of heart tissue. Existing methods for MCI detection mostly rely on the temporal, frequency, and spatial domain analysis of the ECG signals. These conventional techniques lack in effective identification of cardiac cycle inter-dependency during diagnosis. Hence, there is an emerging need for incorporating the underlying connectivity of the intra-sessional cardiac cycles for improved anomaly detection. This article proposes a novel framework for ECG signal analysis and classification using persistent homological features through Cech Complex generation with homotopy equivalence check, by taking the above-mentioned emerging needs into account. Homological features like persistent birth-death rates, betti curves, and persistent entropy provide transparency of the regional and cardiac cycle connectivity when combined with Machine Learning (ML) models. The proposed framework is assessed using publicly available datasets (MIT-BIH and PTB), and the performance metrics of machine learning models indicate its efficacy in classifying Normal Sinus Rhythm (NSR), MCI, and non-MCI subjects, achieving a 2.8% mean improvement in AUC (area under the ROC curve) over existing approaches.

Recommender systems create enormous value for businesses and their consumers. They increase revenue for businesses while improving the consumer experience by recommending relevant products amidst huge product base. Product bundling is an exciting development in the field of product recommendations. It aims at generating new bundles and recommending exciting and relevant bundles to their consumers. Unlike traditional recommender systems that recommend single items to consumers, product bundling aims at targeting a bundle, or a set of items, to the consumers. While bundle recommendation has attracted significant research interest recently, extant literature on bundle generation is scarce. Moreover, metrics to identify if a bundle is popular or not is not well studied. In this work, we aim to fulfill this gap by introducing new bundle popularity metrics based on sales, consumer experience and item diversity in a bundle. We use these metrics in the methodology proposed in this paper to generate new bundles for mobile games using content aware and context aware embeddings. We use opensource Steam Games dataset for our analysis. Our experiments indicate that we can generate new bundles that can outperform the existing bundles on the popularity metrics by 32% - 44%. Our experiments are computationally efficient and the proposed methodology is generic that can be extended to other bundling problems e.g. product bundling, music bundling.

The evolution of the Web3 ecosystem has been hindered by fragmented liquidity and limited interoperability across Layer 1 (L1) and Layer 2 (L2) blockchains, which leads to inefficiencies and elevated costs. Omnichain Web addresses these challenges by introducing a comprehensive framework to unify decentralized networks through its core components: OmniRollups, Proof Network, Ragno Network, and Builder Marketplace. This ecosystem enables seamless cross-chain asset settlement, interoperability, and user-friendly decentralized application (dApp) development, driven by innovative technologies such as modular proof networks and trusted execution environments (TEEs). By integrating advanced zero-knowledge proof systems and compatibility with AI agents, Omnichain Web empowers intent-driven and autonomous functionalities, streamlining liquidity management and user interactions across blockchains. Furthermore, its decentralized marketplace for L1 infrastructure reduces operational overhead and promotes scalable, secure, and efficient cross-chain protocols. As a pioneering solution, Omnichain Web seamlessly connects Web2 and Web3, enabling a holistic and interconnected digital economy.

In social robot navigation, traditional metrics like proxemics and behavior naturalness emphasize human comfort and adherence to social norms but often fail to capture an agent's autonomy and adaptability in dynamic environments. This paper introduces human empowerment, an information-theoretic concept that measures a human's ability to influence their future states and observe those changes, as a complementary metric for evaluating social compliance. This metric reveals how robot navigation policies can indirectly impact human empowerment. We present a framework that integrates human empowerment into the evaluation of social performance in navigation tasks. Through numerical simulations, we demonstrate that human empowerment as a metric not only aligns with intuitive social behavior, but also shows statistically significant differences across various robot navigation policies. These results provide a deeper understanding of how different policies affect social compliance, highlighting the potential of human empowerment as a complementary metric for future research in social navigation., Comment: 9 pages, 8 figures, 2 tables, Accepted to 20th edition of the IEEE/ACM International Conference on Human-Robot Interaction (HRI)

This paper introduces Agency-Driven Labor Theory as a new theoretical framework for understanding human work in AI-augmented environments. While traditional labor theories have focused primarily on task execution and labor time, ADLT proposes that human labor value is increasingly derived from agency - the capacity to make informed judgments, provide strategic direction, and design operational frameworks for AI systems. The paper presents a mathematical framework expressing labor value as a function of agency quality, direction effectiveness, and outcomes, providing a quantifiable approach to analyzing human value creation in AI-augmented workplaces. Drawing on recent work in organizational economics and knowledge worker productivity, ADLT explains how human workers create value by orchestrating complex systems that combine human and artificial intelligence. The theory has significant implications for job design, compensation structures, professional development, and labor market dynamics. Through applications across various sectors, the paper demonstrates how ADLT can guide organizations in managing the transition to AI-augmented operations while maximizing human value creation. The framework provides practical tools for policymakers and educational institutions as they prepare workers for a labor market where value creation increasingly centers on agency and direction rather than execution.

Transition metal dichalcogenide moir\'e homobilayers have emerged as a platform in which magnetism, strong correlations, and topology are intertwined. In a large magnetic field, the energetic alignment of states with different spin in these systems is dictated by both strong Zeeman splitting and the structure of the Hofstadter's butterfly spectrum, yet the latter has been difficult to probe experimentally. Here we conduct local thermodynamic measurements of twisted WSe$_2$ homobilayers that reveal a cascade of magnetic phase transitions. We understand these transitions as the filling of individual Hofstadter subbands, allowing us to extract the structure and connectivity of the Hofstadter spectrum of a single spin. The onset of magnetic transitions is independent of twist angle, indicating that the exchange interactions of the component layers are only weakly modified by the moir\'e potential. In contrast, the magnetic transitions are associated with stark changes in the insulating states at commensurate filling. Our work achieves a spin-resolved measurement of Hofstadter's butterfly despite overlapping states, and it disentangles the role of material and moir\'e effects on the nature of the correlated ground states.

We present a class of stochastic processes in which the large deviation functions of time-integrated observables exhibit singularities that relate to dynamical phase transitions of trajectories. These illustrative examples include Brownian motion with a death rate or in the presence of an absorbing wall, for which we consider a set of empirical observables such as the net displacement, local time, residence time, and area under the trajectory. Using a backward Fokker-Planck approach, we derive the large deviation functions of these observables, and demonstrate how singularities emerge from a competition between survival and diffusion. Furthermore, we analyse this scenario using an alternative approach with tilted operators, showing that at the singular point, the effective dynamics undergoes an abrupt transition. Extending this approach, we show that similar transitions may generically arise in Markov chains with transient states. This scenario is robust and generalizable for non-Markovian dynamics and for many-body systems, potentially leading to multiple dynamical phase transitions., Comment: 21 pages, 21 figures. For a supplemental Mathematica notebook (Ref[84]), see https://drive.google.com/file/d/1cAcXngt6wE7GCo0u-ltjShSmXtswgKPO/view?usp=sharing

Recent advancements have underscored the potential of large language model (LLM)-based agents in financial decision-making. Despite this progress, the field currently encounters two main challenges: (1) the lack of a comprehensive LLM agent framework adaptable to a variety of financial tasks, and (2) the absence of standardized benchmarks and consistent datasets for assessing agent performance. To tackle these issues, we introduce \textsc{InvestorBench}, the first benchmark specifically designed for evaluating LLM-based agents in diverse financial decision-making contexts. InvestorBench enhances the versatility of LLM-enabled agents by providing a comprehensive suite of tasks applicable to different financial products, including single equities like stocks, cryptocurrencies and exchange-traded funds (ETFs). Additionally, we assess the reasoning and decision-making capabilities of our agent framework using thirteen different LLMs as backbone models, across various market environments and tasks. Furthermore, we have curated a diverse collection of open-source, multi-modal datasets and developed a comprehensive suite of environments for financial decision-making. This establishes a highly accessible platform for evaluating financial agents' performance across various scenarios.

A potential difference of 1.3 Giga-Volts (GV) was inferred across a thundercloud using data from the GRAPES-3 muon telescope (G3MT). This was the first-ever estimation of gigavolt potential in thunderstorms, confirming prediction of C.T.R. Wilson almost a century ago. To infer the thundercloud potential required acceleration of muons in atmospheric electric field to be incorporated in the Monte Carlo simulation software CORSIKA. The G3MT records over 4 billion muons daily that are grouped into 169 directions covering 2.3 sr sky. This enabled changes as small as 0.1% in the muon flux on minute timescale, caused by thunderstorms to be accurately measured. But that requires high statistics simulation of muon fluxes in thunderstorm electric fields. The CORSIKA offers a choice of several generators for low- (FLUKA, GHEISHA, and UrQMD) and high-energy (SIBYLL, EPOS-LHC, and QGSJETII) hadronic interactions. Since it is unclear which combination of the low- and high-energy generators provides the correct description of hadronic interactions, all nine combinations of generators were explored, and they yielded thundercloud potentials ranging from 1.3 GV to 1.6 GV for the event recorded on 1 December 2014. The result of SIBYLL-FLUKA combination yielded the lowest electric potential of 1.3 GV was reported. Furthermore, another seven major thunderstorm events recorded between April 2011 and December 2020 were analyzed to measure the dependence of their thundercloud potential on the hadronic interaction generators. It is observed that the low-energy generators produce larger variation ($\sim$14%) in thundercloud potential than the high-energy generators ($\sim$8%). This probably reflects the fact that the GeV muons are predominantly produced in low-energy ($<$80 GeV) interactions, which effectively magnifies the differences in the meson production cross-sections among the low-energy generators.

This pilot study presents a novel, automated, and scalable methodology for detecting and evaluating subsurface defect-prone regions in concrete slabs using Impact Echo (IE) signal analysis. The approach integrates advanced signal processing, clustering, and visual analytics to identify subsurface anomalies. A unique adaptive thresholding method tailors frequency-based defect identification to the distinct material properties of each slab. The methodology generates frequency maps, binary masks, and k-means cluster maps to automatically classify defect and non-defect regions. Key visualizations, including 3D surface plots, cluster maps, and contour plots, are employed to analyze spatial frequency distributions and highlight structural anomalies. The study utilizes a labeled dataset constructed at the Federal Highway Administration (FHWA) Advanced Sensing Technology Nondestructive Evaluation Laboratory. Evaluations involve ground-truth masking, comparing the generated defect maps with top-view binary masks derived from the information provided by the FHWA. The performance metrics, specifically F1-scores and AUC-ROC, achieve values of up to 0.95 and 0.83, respectively. The results demonstrate the robustness of the methodology, consistently identifying defect-prone areas with minimal false positives and few missed defects. Adaptive frequency thresholding ensures flexibility in addressing variations across slabs, providing a scalable framework for detecting structural anomalies. Additionally, the methodology is adaptable to other frequency-based signals due to its generalizable thresholding mechanism and holds potential for integrating multimodal sensor fusion. This automated and scalable pipeline minimizes manual intervention, ensuring accurate and efficient defect detection, further advancing Non-Destructive Evaluation (NDE) techniques., Comment: Accepted by IEEE Big Data 2024

Dual-function radar communication (DFRC) systems incorporate both radar and communication functions by sharing spectrum, hardware and RF signal processing chains. Future technologies, such as 6G, are envisioned to support multiple communication platforms along with radar sensing, thus leading to high dynamism and competition for the available resources. In such settings, whenever communication takes precedence, a likely scenario is dynamically changing RF chain and antenna availability for sensing. This necessitates real-time beam redesign to cover the field-of-view (FOV), solving which is intractable via computationally expensive optimization approaches. We propose that classic windowing techniques are still relevant and much more practical than optimization methods in such dynamic scenarios. Specifically, parametrized windows can be used in a strategic way to adapt to varying resource availability while sustaining sensing performance., Comment: 6 pages, 6 figures

Symmetry plays a central role in the sciences, machine learning, and statistics. While statistical tests for the presence of distributional invariance with respect to groups have a long history, tests for conditional symmetry in the form of equivariance or conditional invariance are absent from the literature. This work initiates the study of nonparametric randomization tests for symmetry (invariance or equivariance) of a conditional distribution under the action of a specified locally compact group. We develop a general framework for randomization tests with finite-sample Type I error control and, using kernel methods, implement tests with finite-sample power lower bounds. We also describe and implement approximate versions of the tests, which are asymptotically consistent. We study their properties empirically on synthetic examples, and on applications to testing for symmetry in two problems from high-energy particle physics., Comment: Theorems 2.2 and 4.1 appeared in arXiv:2307.15834, which is superseded by this article

Cypher, the query language for Neo4j graph databases, plays a critical role in enabling graph-based analytics and data exploration. While substantial research has been dedicated to natural language to SQL query generation (Text2SQL), the analogous problem for graph databases referred to as Text2Cypher remains underexplored. In this work, we introduce SynthCypher, a fully synthetic and automated data generation pipeline designed to address this gap. SynthCypher employs a novel LLMSupervised Generation-Verification framework, ensuring syntactically and semantically correct Cypher queries across diverse domains and query complexities. Using this pipeline, we create SynthCypher Dataset, a large-scale benchmark containing 29.8k Text2Cypher instances. Fine-tuning open-source large language models (LLMs), including LLaMa-3.1- 8B, Mistral-7B, and QWEN-7B, on SynthCypher yields significant performance improvements of up to 40% on the Text2Cypher test set and 30% on the SPIDER benchmark adapted for graph databases. This work demonstrates that high-quality synthetic data can effectively advance the state-of-the-art in Text2Cypher tasks.

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively expensive and may involve some constraints, such as a limited budget for agent-environment interactions and restricted exploration in certain regions of the state space. Examples include selecting candidates for medical trials and training agents in complex navigation environments. This problem necessitates the study of active reinforcement learning strategies that collect minimal additional experience trajectories by reusing existing offline data previously collected by some unknown behavior policy. In this work, we propose an active reinforcement learning method capable of collecting trajectories that can augment existing offline data. With extensive experimentation, we demonstrate that our proposed method reduces additional online interaction with the environment by up to 75% over competitive baselines across various continuous control environments such as Gym-MuJoCo locomotion environments as well as Maze2d, AntMaze, CARLA and IsaacSimGo1. To the best of our knowledge, this is the first work that addresses the active learning problem in the context of sequential decision-making and reinforcement learning., Comment: AAAI 2025

Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significant advances in automating aspects of scientific reasoning, simulation, and experimentation, we still lack integrated AI systems capable of performing autonomous long-term scientific research and discovery. This paper examines the current state of AI for scientific discovery, highlighting recent progress in large language models and other AI techniques applied to scientific tasks. We then outline key challenges and promising research directions toward developing more comprehensive AI systems for scientific discovery, including the need for science-focused AI agents, improved benchmarks and evaluation metrics, multimodal scientific representations, and unified frameworks combining reasoning, theorem proving, and data-driven modeling. Addressing these challenges could lead to transformative AI tools to accelerate progress across disciplines towards scientific discovery., Comment: AAAI 2025

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension failure. For example, when a model misinterprets a text and produces a response that reinforces a stereotype, it becomes difficult to determine whether the issue arises from inherent bias or from a misunderstanding of the given content. In this paper, we conduct a multi-faceted evaluation that distinctly disentangles bias from flaws within the reading comprehension task. We propose a targeted stereotype mitigation framework that implicitly mitigates observed stereotypes in generative models through instruction-tuning on general-purpose datasets. We reduce stereotypical outputs by over 60% across multiple dimensions -- including nationality, age, gender, disability, and physical appearance -- by addressing comprehension-based failures, and without relying on explicit debiasing techniques. We evaluate several state-of-the-art generative models to demonstrate the effectiveness of our approach while maintaining the overall utility. Our findings highlight the need to critically disentangle the concept of `bias' from other types of errors to build more targeted and effective mitigation strategies. CONTENT WARNING: Some examples contain offensive stereotypes.

License plate recognition (LPR) involves automated systems that utilize cameras and computer vision to read vehicle license plates. Such plates collected through LPR can then be compared against databases to identify stolen vehicles, uninsured drivers, crime suspects, and more. The LPR system plays a significant role in saving time for institutions such as the police force. In the past, LPR relied heavily on Optical Character Recognition (OCR), which has been widely explored to recognize characters in images. Usually, collected plate images suffer from various limitations, including noise, blurring, weather conditions, and close characters, making the recognition complex. Existing LPR methods still require significant improvement, especially for distorted images. To fill this gap, we propose utilizing visual language models (VLMs) such as OpenAI GPT4o, Google Gemini 1.5, Google PaliGemma (Pathways Language and Image model + Gemma model), Meta Llama 3.2, Anthropic Claude 3.5 Sonnet, LLaVA, NVIDIA VILA, and moondream2 to recognize such unclear plates with close characters. This paper evaluates the VLM's capability to address the aforementioned problems. Additionally, we introduce ``VehiclePaliGemma'', a fine-tuned Open-sourced PaliGemma VLM designed to recognize plates under challenging conditions. We compared our proposed VehiclePaliGemma with state-of-the-art methods and other VLMs using a dataset of Malaysian license plates collected under complex conditions. The results indicate that VehiclePaliGemma achieved superior performance with an accuracy of 87.6\%. Moreover, it is able to predict the car's plate at a speed of 7 frames per second using A100-80GB GPU. Finally, we explored the multitasking capability of VehiclePaliGemma model to accurately identify plates containing multiple cars of various models and colors, with plates positioned and oriented in different directions., Comment: 33 pages, 9 figures

Data de-identification makes it possible to glean insights from data while preserving user privacy. The use of Trusted Execution Environments (TEEs) allow for the execution of de-identification applications on the cloud without the need for a user to trust the third-party application provider. In this paper, we present \textit{SPIDEr - Secure Pipeline for Information De-Identification with End-to-End Encryption}, our implementation of an end-to-end encrypted data de-identification pipeline. SPIDEr supports classical anonymisation techniques such as suppression, pseudonymisation, generalisation, and aggregation, as well as techniques that offer a formal privacy guarantee such as k-anonymisation and differential privacy. To enable scalability and improve performance on constrained TEE hardware, we enable batch processing of data for differential privacy computations. We present our design of the control flows for end-to-end secure execution of de-identification operations within a TEE. As part of the control flow for running SPIDEr within the TEE, we perform attestation, a process that verifies that the software binaries were properly instantiated on a known, trusted platform., Comment: 3 pages, 2 figures

Bankart lesions, or anterior-inferior glenoid labral tears, are diagnostically challenging on standard MRIs due to their subtle imaging features-often necessitating invasive MRI arthrograms (MRAs). This study develops deep learning (DL) models to detect Bankart lesions on both standard MRIs and MRAs, aiming to improve diagnostic accuracy and reduce reliance on MRAs. We curated a dataset of 586 shoulder MRIs (335 standard, 251 MRAs) from 558 patients who underwent arthroscopy. Ground truth labels were derived from intraoperative findings, the gold standard for Bankart lesion diagnosis. Separate DL models for MRAs and standard MRIs were trained using the Swin Transformer architecture, pre-trained on a public knee MRI dataset. Predictions from sagittal, axial, and coronal views were ensembled to optimize performance. The models were evaluated on a 20% hold-out test set (117 MRIs: 46 MRAs, 71 standard MRIs). Bankart lesions were identified in 31.9% of MRAs and 8.6% of standard MRIs. The models achieved AUCs of 0.87 (86% accuracy, 83% sensitivity, 86% specificity) and 0.90 (85% accuracy, 82% sensitivity, 86% specificity) on standard MRIs and MRAs, respectively. These results match or surpass radiologist performance on our dataset and reported literature metrics. Notably, our model's performance on non-invasive standard MRIs matched or surpassed the radiologists interpreting MRAs. This study demonstrates the feasibility of using DL to address the diagnostic challenges posed by subtle pathologies like Bankart lesions. Our models demonstrate potential to improve diagnostic confidence, reduce reliance on invasive imaging, and enhance accessibility to care., Comment: Accepted for presentation at SPIE Medical Imaging 2025: Computer-Aided Diagnosis. The manuscript is expected to appear in the conference proceedings

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.

Proper use of personal protective equipment (PPE) can save the lives of industry workers and it is a widely used application of computer vision in the large manufacturing industries. However, most of the applications deployed generate a lot of false alarms (violations) because they tend to generalize the requirements of PPE across the industry and tasks. The key to resolving this issue is to understand the action being performed by the worker and customize the inference for the specific PPE requirements of that action. In this paper, we propose a system that employs activity recognition models to first understand the action being performed and then use object detection techniques to check for violations. This leads to a 23% improvement in the F1-score compared to the PPE-based approach on our test dataset of 109 videos.

The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs) for web interaction tasks. Many existing benchmarks suffer from fragmentation and inconsistent evaluation methodologies, making it challenging to achieve reliable comparisons and reproducible results. BrowserGym aims to solve this by providing a unified, gym-like environment with well-defined observation and action spaces, facilitating standardized evaluation across diverse benchmarks. Combined with AgentLab, a complementary framework that aids in agent creation, testing, and analysis, BrowserGym offers flexibility for integrating new benchmarks while ensuring consistent evaluation and comprehensive experiment management. This standardized approach seeks to reduce the time and complexity of developing web agents, supporting more reliable comparisons and facilitating in-depth analysis of agent behaviors, and could result in more adaptable, capable agents, ultimately accelerating innovation in LLM-driven automation. As a supporting evidence, we conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across all benchmarks currently available in BrowserGym. Among other findings, our results highlight a large discrepancy between OpenAI and Anthropic's latests models, with Claude-3.5-Sonnet leading the way on almost all benchmarks, except on vision-related tasks where GPT-4o is superior. Despite these advancements, our results emphasize that building robust and efficient web agents remains a significant challenge, due to the inherent complexity of real-world web environments and the limitations of current models.

In product search, the retrieval of candidate products before re-ranking is more critical and challenging than other search like web search, especially for tail queries, which have a complex and specific search intent. In this paper, we present a hybrid system for e-commerce search deployed at Walmart that combines traditional inverted index and embedding-based neural retrieval to better answer user tail queries. Our system significantly improved the relevance of the search engine, measured by both offline and online evaluations. The improvements were achieved through a combination of different approaches. We present a new technique to train the neural model at scale. and describe how the system was deployed in production with little impact on response time. We highlight multiple learnings and practical tricks that were used in the deployment of this system., Comment: 9 page, 2 figures, 10 tables, KDD 2022

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io ., Comment: The project is hosted at https://bigdocs.github.io

Document comparison typically relies on optical character recognition (OCR) as its core technology. However, OCR requires the selection of appropriate language models for each document and the performance of multilingual or hybrid models remains limited. To overcome these challenges, we propose text change detection (TCD) using an image comparison model tailored for multilingual documents. Unlike OCR-based approaches, our method employs word-level text image-to-image comparison to detect changes. Our model generates bidirectional change segmentation maps between the source and target documents. To enhance performance without requiring explicit text alignment or scaling preprocessing, we employ correlations among multi-scale attention features. We also construct a benchmark dataset comprising actual printed and scanned word pairs in various languages to evaluate our model. We validate our approach using our benchmark dataset and public benchmarks Distorted Document Images and the LRDE Document Binarization Dataset. We compare our model against state-of-the-art semantic segmentation and change detection models, as well as to conventional OCR-based models., Comment: 15pages, 11figures 6tables, wacv2025 accepted

In this paper, we study infinite-horizon linear-quadratic uncertain differential games with an output feedback information structure. We assume linear time-invariant nominal dynamics influenced by deterministic external disturbances, and players' risk preferences are expressed by a soft-constrained quadratic cost criterion over an infinite horizon. We demonstrate that the conditions available in the literature for the existence of a soft-constrained output feedback Nash equilibrium (SCONE) are too stringent to satisfy, even in low-dimensional games. To address this issue, using ideas from suboptimal control, we introduce the concept of a soft-constrained output feedback guaranteed cost equilibrium (SCOGCE). At an SCOGCE, the players' worst-case costs are upper-bounded by a specified cost profile while maintaining an equilibrium property. We show that SCOGCE strategies form a larger class of equilibrium strategies; that is, whenever an SCONE exists, it is also an SCOGCE. We demonstrate that sufficient conditions for the existence of SCOGCE are related to the solvability of a set of coupled bi-linear matrix inequalities. Using semi-definite programming relaxations, we provide linear matrix inequality-based iterative algorithms for the synthesis of SCOGCE strategies. Finally, we illustrate the performance of SCOGCE controllers with numerical examples., Comment: accepted at Journal of Optimization Theory and Applications

Accurate diagnosis of gait impairments is often hindered by subjective or costly assessment methods, with current solutions requiring either expensive multi-camera equipment or relying on subjective clinical observation. There is a critical need for accessible, objective tools that can aid in gait assessment while preserving patient privacy. In this work, we present a mobile phone-based, privacy-preserving artificial intelligence (AI) system for classifying gait impairments and introduce a novel dataset of 743 videos capturing seven distinct gait patterns. The dataset consists of frontal and sagittal views of trained subjects simulating normal gait and six types of pathological gait (circumduction, Trendelenburg, antalgic, crouch, Parkinsonian, and vaulting), recorded using standard mobile phone cameras. Our system achieved 86.5% accuracy using combined frontal and sagittal views, with sagittal views generally outperforming frontal views except for specific gait patterns like Circumduction. Model feature importance analysis revealed that frequency-domain features and entropy measures were critical for classifcation performance, specifically lower limb keypoints proved most important for classification, aligning with clinical understanding of gait assessment. These findings demonstrate that mobile phone-based systems can effectively classify diverse gait patterns while preserving privacy through on-device processing. The high accuracy achieved using simulated gait data suggests their potential for rapid prototyping of gait analysis systems, though clinical validation with patient data remains necessary. This work represents a significant step toward accessible, objective gait assessment tools for clinical, community, and tele-rehabilitation settings, Comment: 21 pages, 4 Figures, 4 Tables, Submitted to PLOS Digital Health

Effective code retrieval plays a crucial role in advancing code generation, bug fixing, and software maintenance, particularly as software systems increase in complexity. While current code embedding models have demonstrated promise in retrieving code snippets for small-scale, well-defined tasks, they often underperform in more demanding real-world applications such as bug localization within GitHub repositories. We hypothesize that a key issue is their reliance on noisy and inconsistent datasets for training, which impedes their ability to generalize to more complex retrieval scenarios. To address these limitations, we introduce CoRNStack, a large-scale, high-quality contrastive training dataset for code that spans multiple programming languages. This dataset is curated using consistency filtering to eliminate noisy positives and is further enriched with mined hard negatives, thereby facilitating more effective learning. We demonstrate that contrastive training of embedding models using CoRNStack leads to state-of-the-art performance across a variety of code retrieval tasks. Furthermore, the dataset can be leveraged for training code reranking models, a largely underexplored area compared to text reranking. Our finetuned code reranking model significantly improves the ranking quality over the retrieved results. Finally, by employing our code retriever and reranker together, we demonstrate significant improvements in function localization for GitHub issues, an important component of real-world software development.

Fully supervised continual learning methods have shown improved attack traffic detection in a closed-world learning setting. However, obtaining fully annotated data is an arduous task in the security domain. Further, our research finds that after training a classifier on two days of network traffic, the performance decay of attack class detection over time (computed using the area under the time on precision-recall AUC of the attack class) drops from 0.985 to 0.506 on testing with three days of new test samples. In this work, we focus on label scarcity and open-world learning (OWL) settings to improve the attack class detection of the continual learning-based network intrusion detection (NID). We formulate OWL for NID as a semi-supervised continual learning-based method, dubbed SOUL, to achieve the classifier performance on par with fully supervised models while using limited annotated data. The proposed method is motivated by our empirical observation that using gradient projection memory (constructed using buffer memory samples) can significantly improve the detection performance of the attack (minority) class when trained using partially labeled data. Further, using the classifier's confidence in conjunction with buffer memory, SOUL generates high-confidence labels whenever it encounters OWL tasks closer to seen tasks, thus acting as a label generator. Interestingly, SOUL efficiently utilizes samples in the buffer memory for sample replay to avoid catastrophic forgetting, construct the projection memory, and assist in generating labels for unseen tasks. The proposed method is evaluated on four standard network intrusion detection datasets, and the performance results are closer to the fully supervised baselines using at most 20% labeled data while reducing the data annotation effort in the range of 11 to 45% for unseen data.

We show that electron crystals compete closely with non-Abelian fractional Chern insulators in the half-full second moir\'e band of twisted bilayer MoTe$_2$. Depending on the twist angle and microscopic model, these crystals can have non-zero or zero Chern numbers. The latter relies on cancellation between contributions from the full first miniband (+1) and the half-full second miniband (-1). For this reason, we call it an anti-topological crystal. Surprisingly, it occurs despite the lowest two non-interacting bands in a given valley having the same Chern number of +1. The anti-topological crystal is a novel type of electron crystal that may appear in systems with multiple Chern bands at filling factors $n > 1$.

Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike diffusion models, AR models enable more efficient and controllable generation with faster inference times, making them especially suitable for data-intensive domains. Traditional 3D generative models using AR approaches often rely on ``next-token" predictions at the voxel or point level. While effective for certain applications, these methods can be restrictive and computationally expensive when dealing with large-scale 3D data. To tackle these challenges, we introduce 3D-WAG, an AR model for 3D implicit distance fields that can perform unconditional shape generation, class-conditioned and also text-conditioned shape generation. Our key idea is to encode shapes as multi-scale wavelet token maps and use a Transformer to predict the ``next higher-resolution token map" in an autoregressive manner. By redefining 3D AR generation task as ``next-scale" prediction, we reduce the computational cost of generation compared to traditional ``next-token" prediction models, while preserving essential geometric details of 3D shapes in a more structured and hierarchical manner. We evaluate 3D-WAG to showcase its benefit by quantitative and qualitative comparisons with state-of-the-art methods on widely used benchmarks. Our results show 3D-WAG achieves superior performance in key metrics like Coverage and MMD, generating high-fidelity 3D shapes that closely match the real data distribution.

Transformers exhibit in-context learning (ICL): the ability to use novel information presented in the context without additional weight updates. Recent work shows that ICL emerges when models are trained on a sufficiently diverse set of tasks and the transition from memorization to generalization is sharp with increasing task diversity. One interpretation is that a network's limited capacity to memorize favors generalization. Here, we examine the mechanistic underpinnings of this transition using a small transformer applied to a synthetic ICL task. Using theory and experiment, we show that the sub-circuits that memorize and generalize can be viewed as largely independent. The relative rates at which these sub-circuits learn explains the transition from memorization to generalization, rather than capacity constraints. We uncover a memorization scaling law, which determines the task diversity threshold at which the network generalizes. The theory quantitatively explains a variety of other ICL-related phenomena, including the long-tailed distribution of when ICL is acquired, the bimodal behavior of solutions close to the task diversity threshold, the influence of contextual and data distributional statistics on ICL, and the transient nature of ICL.

The widespread dissemination of hate speech, harassment, harmful and sexual content, and violence across websites and media platforms presents substantial challenges and provokes widespread concern among different sectors of society. Governments, educators, and parents are often at odds with media platforms about how to regulate, control, and limit the spread of such content. Technologies for detecting and censoring the media contents are a key solution to addressing these challenges. Techniques from natural language processing and computer vision have been used widely to automatically identify and filter out sensitive content such as offensive languages, violence, nudity, and addiction in both text, images, and videos, enabling platforms to enforce content policies at scale. However, existing methods still have limitations in achieving high detection accuracy with fewer false positives and false negatives. Therefore, more sophisticated algorithms for understanding the context of both text and image may open rooms for improvement in content censorship to build a more efficient censorship system. In this paper, we evaluate existing LLM-based content moderation solutions such as OpenAI moderation model and Llama-Guard3 and study their capabilities to detect sensitive contents. Additionally, we explore recent LLMs such as GPT, Gemini, and Llama in identifying inappropriate contents across media outlets. Various textual and visual datasets like X tweets, Amazon reviews, news articles, human photos, cartoons, sketches, and violence videos have been utilized for evaluation and comparison. The results demonstrate that LLMs outperform traditional techniques by achieving higher accuracy and lower false positive and false negative rates. This highlights the potential to integrate LLMs into websites, social media platforms, and video-sharing services for regulatory and content moderation purposes., Comment: 55 pages, 16 figures

The remaining useful life (RUL) estimation is an important metric that helps in condition-based maintenance. Damage data obtained from the diagnostics techniques are often noisy and the RUL estimated from the data is less reliable. Estimating the probabilistic RUL by quantifying the uncertainty in the predictive model parameters using the noisy data increases confidence in the predicted values. Uncertainty quantification methods generate statistical samples for the model parameters, that represent the uncertainty, by evaluating the predictive model several times. The computational time for solving a physics-based predictive model is significant, which makes the statistical techniques to be computationally expensive. It is essential to reduce the computational time to estimate the RUL in a feasible time. In this work, real-time probabilistic RUL estimation is demonstrated in adhesively bonded joints using the Sequential Monte Carlo (SMC) sampling method and cloud-based computations. The SMC sampling method is an alternative to traditional MCMC methods, which enables generating the statistical parameter samples in parallel. The parallel computational capabilities of the SMC methods are exploited by running the SMC simulation on multiple cloud calls. This approach is demonstrated by estimating fatigue RUL in the adhesively bonded joint. The accuracy of probabilistic RUL estimated by SMC is validated by comparing it with RUL estimated by the MCMC and the experimental values. The SMC simulation is run on the cloud and the computational speedup of the SMC is demonstrated.

Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implications of real-world user data. To mitigate this gap, in this work, we focus on user frustration in a deployed TOD system, assessing the feasibility of out-of-the-box solutions for user frustration detection. Specifically, we compare the performance of our deployed keyword-based approach, open-source approaches to sentiment analysis, dialog breakdown detection methods, and emerging in-context learning LLM-based detection. Our analysis highlights the limitations of open-source methods for real-world frustration detection, while demonstrating the superior performance of the LLM-based approach, achieving a 16\% relative improvement in F1 score on an internal benchmark. Finally, we analyze advantages and limitations of our methods and provide an insight into user frustration detection task for industry practitioners.

The compositional asymmetry of Janus micro- and nanoparticles gives unprecedented opportunities to manipulate such composite particles with different stimuli to achieve enhanced optical, magnetic and photothermal responses, which can be exploited for sensing, phototherapy, and nanoscale robotic applications. This perspective overviews recent advances in optical manipulation of plasmonic Janus particles and their implications for biomedical applications. In particular, a brief summary of optical, plasmonic, and magnetic manipulation of Janus particles of various compositions are presented. Moreover, the potentials of plasmonic and magnetic Janus particles for targeted drug delivery, photothermal therapy, enhanced hyperthermia, and neuromodulation are briefly discussed. Finally, a perspective on the rational design and applications of this particular family of asymmetric particles is forwarded.

Point cloud representation has gained traction due to its efficient memory usage and simplicity in acquisition, manipulation, and storage. However, as point cloud sizes increase, effective down-sampling becomes essential to address the computational requirements of downstream tasks. Classical approaches, such as furthest point sampling (FPS), perform well on benchmarks but rely on heuristics and overlook geometric features, like curvature, during down-sampling. In this paper, We introduce a reinforcement learning-based sampling algorithm that enhances FPS by integrating curvature information. Our approach ranks points by combining FPS-derived soft ranks with curvature scores computed by a deep neural network, allowing us to replace a proportion of low-curvature points in the FPS set with high-curvature points from the unselected set. Existing differentiable sampling techniques often suffer from training instability, hindering their integration into end-to-end learning frameworks. By contrast, our method achieves stable end-to-end learning, consistently outperforming baseline models across multiple downstream geometry processing tasks. We provide comprehensive ablation studies, with both qualitative and quantitative insights into the effect of each feature on performance. Our algorithm establishes state-of-the-art results for classification, segmentation and shape completion, showcasing its robustness and adaptability., Comment: 19 pages, 5 figures

The proliferation of AI techniques for image generation, coupled with their increasing accessibility, has raised significant concerns about the potential misuse of these images to spread misinformation. Recent AI-generated image detection (AGID) methods include CNNDetection, NPR, DM Image Detection, Fake Image Detection, DIRE, LASTED, GAN Image Detection, AIDE, SSP, DRCT, RINE, OCC-CLIP, De-Fake, and Deep Fake Detection. However, we argue that the current state-of-the-art AGID techniques are inadequate for effectively detecting contemporary AI-generated images and advocate for a comprehensive reevaluation of these methods. We introduce the Visual Counter Turing Test (VCT^2), a benchmark comprising ~130K images generated by contemporary text-to-image models (Stable Diffusion 2.1, Stable Diffusion XL, Stable Diffusion 3, DALL-E 3, and Midjourney 6). VCT^2 includes two sets of prompts sourced from tweets by the New York Times Twitter account and captions from the MS COCO dataset. We also evaluate the performance of the aforementioned AGID techniques on the VCT$^2$ benchmark, highlighting their ineffectiveness in detecting AI-generated images. As image-generative AI models continue to evolve, the need for a quantifiable framework to evaluate these models becomes increasingly critical. To meet this need, we propose the Visual AI Index (V_AI), which assesses generated images from various visual perspectives, including texture complexity and object coherence, setting a new standard for evaluating image-generative AI models. To foster research in this domain, we make our https://huggingface.co/datasets/anonymous1233/COCO_AI and https://huggingface.co/datasets/anonymous1233/twitter_AI datasets publicly available., Comment: 13 pages, 9 figures

Preserving topological structures is important in real-world applications, particularly in sensitive domains such as healthcare and medicine, where the correctness of human anatomy is critical. However, most existing image editing models focus on manipulating intensity and texture features, often overlooking object geometry within images. To address this issue, this paper introduces a novel method, Topology-Preserved Image Editing with text instructions (TPIE), that for the first time ensures the topology and geometry remaining intact in edited images through text-guided generative diffusion models. More specifically, our method treats newly generated samples as deformable variations of a given input template, allowing for controllable and structure-preserving edits. Our proposed TPIE framework consists of two key modules: (i) an autoencoder-based registration network that learns latent representations of object transformations, parameterized by velocity fields, from pairwise training images; and (ii) a novel latent conditional geometric diffusion (LCDG) model efficiently capturing the data distribution of learned transformation features conditioned on custom-defined text instructions. We validate TPIE on a diverse set of 2D and 3D images and compare them with state-of-the-art image editing approaches. Experimental results show that our method outperforms other baselines in generating more realistic images with well-preserved topology. Our code will be made publicly available on Github.

This study investigates the interplay of visual and textual features in online discussions about cannabis edibles and their impact on user engagement. Leveraging the CLIP model, we analyzed 42,743 images from Facebook (March 1 to August 31, 2021), with a focus on detecting food-related visuals and examining the influence of image attributes such as colorfulness and brightness on user interaction. For textual analysis, we utilized the BART model as a denoising autoencoder to classify ten topics derived from structural topic modeling, exploring their relationship with user engagement. Linear regression analysis identified significant positive correlations between food-related visuals (e.g., fruit, candy, and bakery) and user engagement scores, as well as between engagement and text topics such as cannabis legalization. In contrast, negative associations were observed with image colorfulness and certain textual themes. These findings offer actionable insights for policymakers and regulatory bodies in designing warning labels and marketing regulations to address potential risks associated with recreational cannabis edibles., Comment: This project was initiated in September 2023

The goal of this paper is to assess whether there is any correlation between police salaries and crime rates. Using public data sources that contain Baltimore Crime Rates and Baltimore Police Department (BPD) salary information from 2011 to 2021, our research uses a variety of techniques to capture and measure any correlation between the two. Based on that correlation, the paper then uses established social theories to make recommendations on how this data can potentially be used by State Leadership. Our initial results show a negative correlation between salary/compensation levels and crime rates.

Important advances have recently been made in the search for materials with complex multi-phase landscapes that host photoinduced metastable collective states with exotic functionalities. In almost all cases so far, the desired phases are accessed by exploiting light-matter interactions via the imaginary part of the dielectric function through above-bandgap or resonant mode excitation. Nonresonant Raman excitation of coherent modes has been experimentally observed and proposed for dynamic material control, but the resulting atomic excursion has been limited to perturbative levels. Here, we demonstrate that it is possible to overcome this challenge by employing nonresonant ultrashort pulses with low photon energies well below the bandgap. Using mid-infrared pulses, we induce ferroelectric reversal in lithium niobate and phase switching in tin selenide and characterize the large-amplitude mode displacements through femtosecond Raman scattering, second harmonic generation, and x-ray diffraction. This approach, validated by first-principle calculations, defines a novel method for synthesizing hidden phases with unique functional properties and manipulating complex energy landscapes at reduced energy consumption and ultrafast speeds., Comment: 5 figures

Recent advancements in session-based recommendation models using deep learning techniques have demonstrated significant performance improvements. While they can enhance model sophistication and improve the relevance of recommendations, they also make it challenging to implement a scalable real-time solution. To addressing this challenge, we propose GRAINRec: a Graph and Attention Integrated session-based recommendation model that generates recommendations in real-time. Our scope of work is item recommendations in online retail where a session is defined as an ordered sequence of digital guest actions, such as page views or adds to cart. The proposed model generates recommendations by considering the importance of all items in the session together, letting us predict relevant recommendations dynamically as the session evolves. We also propose a heuristic approach to implement real-time inferencing that meets Target platform's service level agreement (SLA). The proposed architecture lets us predict relevant recommendations dynamically as the session evolves, rather than relying on pre-computed recommendations for each item. Evaluation results of the proposed model show an average improvement of 1.5% across all offline evaluation metrics. A/B tests done over a 2 week duration showed an increase of 10% in click through rate and 9% increase in attributable demand. Extensive ablation studies are also done to understand our model performance for different parameters., Comment: Accepted to the 2024 IEEE International Conference on Big Data (IEEE BigData 2024)

Large-scale 3D generative models require substantial computational resources yet often fall short in capturing fine details and complex geometries at high resolutions. We attribute this limitation to the inefficiency of current representations, which lack the compactness required to model the generative models effectively. To address this, we introduce a novel approach called Wavelet Latent Diffusion, or WaLa, that encodes 3D shapes into wavelet-based, compact latent encodings. Specifically, we compress a $256^3$ signed distance field into a $12^3 \times 4$ latent grid, achieving an impressive 2427x compression ratio with minimal loss of detail. This high level of compression allows our method to efficiently train large-scale generative networks without increasing the inference time. Our models, both conditional and unconditional, contain approximately one billion parameters and successfully generate high-quality 3D shapes at $256^3$ resolution. Moreover, WaLa offers rapid inference, producing shapes within two to four seconds depending on the condition, despite the model's scale. We demonstrate state-of-the-art performance across multiple datasets, with significant improvements in generation quality, diversity, and computational efficiency. We open-source our code and, to the best of our knowledge, release the largest pretrained 3D generative models across different modalities.

Vision Transformers and U-Net architectures have been widely adopted in the implementation of Diffusion Models. However, each architecture presents specific challenges while realizing them on-device. Vision Transformers require positional embedding to maintain correspondence between the tokens processed by the transformer, although they offer the advantage of using fixed-size, reusable repetitive blocks following tokenization. The U-Net architecture lacks these attributes, as it utilizes variable-sized intermediate blocks for down-convolution and up-convolution in the noise estimation backbone for the diffusion process. To address these issues, we propose an architecture that utilizes a fixed-size, reusable transformer block as a core structure, making it more suitable for hardware implementation. Our architecture is characterized by low complexity, token-free design, absence of positional embeddings, uniformity, and scalability, making it highly suitable for deployment on mobile and resource-constrained devices. The proposed model exhibit competitive and consistent performance across both unconditional and conditional image generation tasks. The model achieved a state-of-the-art FID score of 1.6 on unconditional image generation with the CelebA., Comment: 8 pages

This paper aims to make a mark in the future of sustainable robotics, where efficient algorithms are required to carry out tasks like environmental monitoring and precision agriculture efficiently. We proposed a hybrid algorithm that combines Artificial Bee Colony (ABC) with Levy flight to optimize adaptive sensor placement alongside an important notion of hotspots from domain knowledge experts. By enhancing exploration and exploitation, our approach significantly improves the identification of critical hotspots. This algorithm also finds its usecases for broader search and rescue operations applications, demonstrating its potential in optimization problems across various domains.

Dose prediction is an area of ongoing research that facilitates radiotherapy planning. Most commercial models utilise imaging data and intense computing resources. This study aimed to predict the dose-volume of rectum and bladder from volumes of target, at-risk structure organs and their overlap regions using machine learning. Dose-volume information of 94 patients with prostate cancer planned for 6000cGy in 20 fractions was exported from the treatment planning system as text files and mined to create a training dataset. Several statistical modelling, machine learning methods, and a new fuzzy rule-based prediction (FRBP) model were explored and validated on an independent dataset of 39 patients. The median absolute error was 2.0%-3.7% for bladder and 1.7-2.4% for rectum in the 4000-6420cGy range. For 5300cGy, 5600cGy and 6000cGy, the median difference was less than 2.5% for rectum and 3.8% for bladder. The FRBP model produced errors of 1.2%, 1.3%, 0.9% and 1.6%, 1.2%, 0.1% for the rectum and bladder respectively at these dose levels. These findings indicate feasibility of obtaining accurate predictions of the clinically important dose-volume parameters for rectum and bladder using just the volumes of these structures.

Agricultural landscapes are quite complex, especially in the Global South where fields are smaller, and agricultural practices are more varied. In this paper we report on our progress in digitizing the agricultural landscape (natural and man-made) in our study region of India. We use high resolution imagery and a UNet style segmentation model to generate the first of its kind national-scale multi-class panoptic segmentation output. Through this work we have been able to identify individual fields across 151.7M hectares, and delineating key features such as water resources and vegetation. We share how this output was validated by our team and externally by downstream users, including some sample use cases that can lead to targeted data driven decision making. We believe this dataset will contribute towards digitizing agriculture by generating the foundational baselayer., Comment: 34 pages, 7 tables, 15 figs

The unpredictability of random numbers is fundamental to both digital security and applications that fairly distribute resources. However, existing random number generators have limitations-the generation processes cannot be fully traced, audited, and certified to be unpredictable. The algorithmic steps used in pseudorandom number generators are auditable, but they cannot guarantee that their outputs were a priori unpredictable given knowledge of the initial seed. Device-independent quantum random number generators can ensure that the source of randomness was unknown beforehand, but the steps used to extract the randomness are vulnerable to tampering. Here, for the first time, we demonstrate a fully traceable random number generation protocol based on device-independent techniques. Our protocol extracts randomness from unpredictable non-local quantum correlations, and uses distributed intertwined hash chains to cryptographically trace and verify the extraction process. This protocol is at the heart of a public traceable and certifiable quantum randomness beacon that we have launched. Over the first 40 days of operation, we completed the protocol 7434 out of 7454 attempts -- a success rate of 99.7%. Each time the protocol succeeded, the beacon emitted a pulse of 512 bits of traceable randomness. The bits are certified to be uniform with error times actual success probability bounded by $2^{-64}$. The generation of certifiable and traceable randomness represents one of the first public services that operates with an entanglement-derived advantage over comparable classical approaches., Comment: 40 pages, 4 main figures, 10 supplementary figures