Digital Commons Network^™

Continuous Authentication To Devices In Field Of View Of A User Wearing An Xr Headset, Justin Eltoft

Defensive Publications Series

While wearing a head-mounted device (HMD), a user may want to access another device. However, providing biometric or other authentication input to such devices can be cumbersome for users that are wearing the HMD. This disclosure describes techniques to automatically provide user authentication on other user devices when a user is using a HMD. The user is determined to be authenticated to the HMD and remains authenticated as long as sensors on the HMD indicate that the headset is being worn by the user. When the user looks at another device, the HMD detects information displayed by the other device …

Enhancing The Accuracy And Performance Of Eye Tracking In Head-Mounted Displays, Jason Spencer

Defensive Publications Series

Eye tracking on head-mounted displays (HMDs) is computationally intensive and requires multiple illuminators. The wide gaze angles at which eye-tracking cameras are positioned on HMDs make it difficult to obtain optimally good views of the eye. Further, it is difficult to determine the optical axis of the eye with high accuracy since the human physique does not always conform perfectly with the geometric shapes used to model it. This disclosure describes techniques that can establish the optical axis of the eye by leveraging the refracted view of the pupil under general illumination to infer the shape and position of the …

Augmented Reality Glasses With Point To Screen-Share Gesture For Video Calls, Omar Estrada

Defensive Publications Series

Sharing screen content during a video call is a cumbersome, multi-step procedure that requires user action to initiate sharing, specify the window or screen area to share, and verify that the selected area is correctly shared. This disclosure describes techniques to simplify the sharing of on-screen content during video calls by leveraging camera-equipped smart glasses. Per the techniques, users wearing smart glasses can share on-screen content to others in a video call by simply pointing to the content with their finger, making content-sharing simple and intuitive. When the user's finger appears in the field-of-view, it is detected and a ‘point-to-share’ …

Product Documentation Updates Using Artificial Intelligence, Kayce Basques, Meggin Kearney

Defensive Publications Series

Keeping product documentation in synchronization with a product as the product is updated requires significant manual effort and can be prone to human error. This disclosure describes techniques to automatically update documentation when changes are made to a product or system covered by the documentation. Per the techniques, embeddings are generated for individual documents (or sections thereof) in the documentation corpus. As the product or system is updated, the corresponding changes are recorded, e.g., in an updated codebase for a software product, design and/or hardware specifications for a hardware product, etc. New embeddings are generated for the updated information based …

Method And System For Managing Micropayments Leveraging Blockchain Technology, Daos, And Stablecoins, Nandit Khosa

Defensive Publications Series

The present disclosure provides a method and system for processing micropayments to address the inefficiencies and high costs associated with traditional payment systems. The method involves creating Decentralized Autonomous Organizations (DAOs) for each individual or user that joins the network. Blockchain technology underpins the creation and operation of DAOs.Each DAO issues stablecoin tokens, which represent a stable value of assets or services, for the user to perform payment transactions. Whenever a user wishes to make a micropayment, the user sends the required number of stablecoin tokens to a smart contract. The smart contract automatically executes the transaction by transferring the …

Local Search Query Augmentation For Improved Online Retrieval Performance, Huy Thong Nguyen

Defensive Publications Series

This document describes a query augmentation technique designed to enhance machine learning performance in local search online retrieval. Online retrieval tasks in local search involve retrieving relevant information such as review snippets, images/videos, points of interest, merchant posts, and short videos in response to a user's query. The challenge lies in the need for substantial training data to effectively train machine learning models for these diverse retrieval tasks. This document details a solution that leverages the structure of local search queries and large language models to generate augmented training data, leading to improved retrieval performance.

Regenerative Voice Coil

Defensive Publications Series

In implementations of the disclosure, the elastic energy is recovered from a spring of a VCM. There may be a low mechanical damping and friction of the VCM design that reduces the energy waste while using the VCM regenerative mode as a magnetic damper. The recovered energy can be stored temporarily and used to drive the actuator again when needed (short term energy recovery and storage). An energy recovery circuit, such as a rectifier circuit, can be retrofitted to the existing VCM driver or integrated in a new VCM driver. The recovered energy can be sent back to the battery …

Spiral Under Interlocked Armor In Unbonded Flexible Pipe Of The Api 17j Type, Baker Hughes Company

Defensive Publications Series

Typical structures of unbonded flexible pipes all revolve around a common sequence of layers.

By changing the typical sequence and placing a flat metallic spiral back-up pressure armor layer) under the interlocked pressure armor, it has been identified that this reduces the nub to nub contact travel distance on the interlocked pressure armor, allowing for higher normal operating pressure before the onset of fretting fatigue and the risk of failure of the reinforcements as a result.

Analytic Hierarchy Process Based Interpretable Decision-Making Structure Of Gpt In Unified Developer Efficiency Modeling, Fuming Guo, Biju Abraham

Defensive Publications Series

The present disclosure relates to a method and a system for Analytic Hierarchy Process (AHP) based interpretable decision-making structure of Generative Pre-trained Transformer (GPT) in unified developer efficiency modeling. The method includes receiving and preprocessing a plurality of metrics from one or more data sources. The method further generates pairwise comparison scores for each metric of the plurality of metrics. Additionally, an AHP comparison matrix is constructed based on the generated comparison scores. The method further includes performing a consistency check on the comparison matrix to confirm the reliability of the pairwise comparisons. When inconsistencies are identified, the method includes …

Decoupled Polynomial Graph Filters For Enhanced Adaptability In Gnns

Defensive Publications Series

Graph Neural Networks (GNNs) are powerful tools for learning on graph-structured data, often designed with an underlying assumption of homophily—that connected nodes share similar characteristics. This assumption, however, limits their effectiveness on heterophilic datasets where connected nodes tend to differ. We introduce a novel GNN architecture, Decoupled Polynomial Graph Filter GCN (DPGF-GCN), specifically designed to operate effectively across varying levels of graph homophily. Our approach leverages learnable polynomial graph filters but uniquely decouples the learning of feature transformation weights from the hop-wise aggregation coefficients. This design enhances model expressivity for heterophilic settings while maintaining robustness on homophilic graphs and mitigating …

Adaptgraph: Adaptive Graph Augmentation Via Consistency-Diversity Balancing For Homophilic And Heterophilic Graphs

Defensive Publications Series

Current graph topology augmentation methods are mostly static and heavily rely on the assumption of homophily, where connected nodes are presumed to share the same labels by default. Due to the complexity of real-world graphs, the underlying assumption is often disrupted, thus performance declines, demonstrating their limited adaptability. Although learnable methods flexibly change augmentation strategies based on data, ignorance of balancing consistency and diversity leads to suboptimal performance. This gap highlights the need for universally applicable graph augmentation strategies that ensure these two aspects, thereby enhancing model robustness. To address these challenges, we propose the ADAPTGRAPH framework as an adaptive …

Graphfocus: Adaptive Training Strategies To Counter Over- Globalization In Graph Transformers

Defensive Publications Series

As Transformers become more popular for graph machine learning, a significant issue has recently been observed. Their global attention mechanisms tend to overemphasize distant vertices, leading to the phenomenon of "over-globalising." This phenomenon often results in the dilution of essential local information, particularly in graphs where local neighbourhoods carry significant predictive power. Existing methods often struggle with rigidity in their local processing, where tightly coupled operations limit flexibility and adaptability in diverse graph structures. Additionally, these methods can overlook critical structural nuances, resulting in an incomplete integration of local and global contexts. This paper addresses these issues by proposing GraphFocus, …

Unizyme A Unified Protein Cleavage Site Predictor Enhanced With Enzyme Active-Site Knowledge

Defensive Publications Series

Enzyme-catalyzed protein cleavage is essential for many biological functions. Accurate predic tion of cleavage sites can facilitate various appli cations such as drug development, enzyme de sign, and a deeper understanding of biologica mechanisms. However, most existing models are restricted to an individual enzyme, which ne glects shared knowledge of enzymes and fails generalize to novel enzymes. Thus, we introduce a unified protein cleavage site predictor named UniZyme, which can generalize across diverse enzymes. To enhance the enzyme encoding for the protein cleavage site prediction, UniZyme em ploys a novel biochemically-informed model ar chitecture along with active-site knowledge of pro …

Trustworthy Distributed Traffic Prediction Through Gnn

Defensive Publications Series

Traffic prediction is of great importance for the development of intelligent transportation system (ITS), including travel time estimation (TTE), route recovery and road condition analysis. Most previous works model both road network and vehicle trajectory by learn ing their spatio-temporal characteristics to conduct traffic prediction. Among them, graph neural networ (GNN) has become a popular option for graph-structured traffic data. How ever, there are still two key issues for trustworthy distributed traffic prediction in real-world location-based services, i.e., data sparsity and privacy protection. In this thesis, we aim to solve the above two issues through GNN. For the first issue …

Structural Bias In Three-Dimensional Autoregressive Generative Machine Learning Of Organic Molecules

Defensive Publications Series

A diverse range of generative machine learn ing models for the design of novel molecules and materials have been proposed in recent years. Models that are able to generate three dimensional structures are particularly suitable for quantum chemistry workflows, enabling di rect property prediction. The performance of generative models is typically assessed based on their ability to produce high rates of novel, valid, and unique molecules. However, equally important is the ability of generative models to learn the prevalence of functional groups and certain chemical moieties in the underly ing training data, that is, to faithfully repro duce the chemical …

Probabilistic Graph Circuits Deep Generative Models For Tractable Probabilistic Inference Over Graphs

Defensive Publications Series

Deep generative models (DGMs) have recently demonstrated remarkable success in capturing complex probability distributions over graphs. Al though their excellent performance is attributed to powerful and scalable deep neural networks, it is, at the same time, exactly the presence of these highly non-linear transformations that makes DGMs intractable. Indeed, despite representing probability distributions, intractable DGMs deny probabilistic foundations by their inability to answer even the most basic inference queries with out approximations or design choices specific to a very narrow range of queries. To address this limitation, we propose probabilistic graph circuits (PGCs), a framework of tractable DGMs that provide …

Offline Model-Based Optimization Comprehensive Review

Defensive Publications Series

Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is prohibitively expensive or infeasible, with applications spanning protein engineering, material discovery, neural architecture search, and beyond. The main difficulty lies in accurately estimating the objective landscape beyond the available data, where extrapolations are fraught with significant epistemic uncertainty. This uncertainty can lead to objective hacking (reward hacking)—exploiting model inaccuracies in unseen regions—or other spurious optimizations that yield misleadingly high performance estimates outside the training distribution. Recent advances …

Molground: A Benchmark For Molecular Grounding

Defensive Publications Series

Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic level insights. However, the referential aspect—linking molecular concepts to specific structural components—remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model’s referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular under standing within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, compris ing 79k QA pairs, and developed a multi-agent grounding prototype as proof …

E(3)-Equivariant Models Cannot Learn Chirality Field-Based Molecular Generation

Defensive Publications Series

Obtaining the desired effect of drugs is highly dependent on their molecular geometries. Thus, the current prevailing paradigm focuses on 3D point-cloud atom representations, utilizing graph neural network (GNN) parametrizations, with rotational symmetries baked in via E(3) invariant layers. We prove that such models must necessarily disregard chirality, a geometric property of the molecules that cannot be superimposed on their mirror image by rotation and translation. Chi rality plays a key role in determining drug safety and potency. To address this glaring issue, we introduce a novel field-based representation, proposing refer ence rotations that replace rotational symmetry constraints. The proposed …

Ensuring Ai-Generated Code Compliance And Security, Tushar Goel, Philippe Ombredanne

Defensive Publications Series

This publication describes a method for the automated analysis of AI-generated code to detect potential software license violations and known security vulnerabilities prior to integration into commercial products. By leveraging datasets such as purldb and vulnerablecode from AboutCode, this approach enables the systematic evaluation of code produced by Large Language Models (LLMs), ensuring alignment with both legal compliance standards and security best practices. The system resolves risks associated with third-party dependencies and embedded code snippets by cross-referencing license constraints and vulnerability disclosures, providing developers with actionable insights to maintain secure and compliant software artifacts.

Cur-Gad: Calibrated Uncertainty And Risk Control For Graph Anomaly Detection

Defensive Publications Series

Graph Anomaly Detection (GAD) is critical in security-sensitive domains, yet faces reliability challenges: mis-calibrated confidence estimation (underconfidence in normal nodes, overconfidence in anomalies), adversarial vulnerability of derived confidence score under structural perturbations, and limited efficacy of conventional calibration methods for sparse anomaly patterns. Thus we propose CUR-GAD, a framework integrating statistical risk control into GAD via two innovations: (1) A Dual- Threshold Conformal Risk Control mechanism that provides theoretically guaranteed bounds for both False Negative Rate (FNR) and False Positive Rate (FPR) through providing prediction sets; (2) A Subgraph-aware Spectral Calibrator (SASC) that optimizes node representations through adaptive spectral filtering …

Hybrid Spectral-Spatial Learning For Robust Graph Anomaly Detection

Defensive Publications Series

Anomaly detection on graph data has garnered significant interest from both the academia and industry. In recent years, fueled by the rapid development of Graph Neural Networks (GNNs), various GNNs-based anomaly detection methods have been proposed and achieved good results. However, GNNs-based methods often assume that connected nodes have similar classes and features (homophily), leading to issues of class inconsistency and semantic inconsistency in graph anomaly detection, particularly when this assumption is violated. Existing methods have yet to adequately address these issues simultaneously, thereby limiting the detection performance of the model. Therefore, an anomaly detection method that consists of one …

Refining Multi-Relational Graph Anomaly Detection With Learned Structures And Scalable Meta-Path Aggregation

Defensive Publications Series

Graph Neural Networks (GNNs) have recently achieved remarkable success in various learning tasks involving graph-structured data. However, their application to multi-relational graph anomaly detection problems on real-world datasets presents several challenges that significantly hinder performance: the structural noise and inconsistencies inherent in real-world graph data, difficulties in aggregating information across multiple relation types, and the imbalanced class labels. To address these limitations, we introduce a graph structure learning layer designed to refine the original, noisy graph structure, enhancing the representation of node relationships. This enables our model to effectively handle inconsistencies and structural noise present in the original graph data …

Detail-Controllable Real-Time Contrast Enhancement, Chengliang Jhou, Chunlei Zhu, Bojian Li

Defensive Publications Series

Insufficient contrast can make it difficult to view an image or certain portions of the image. While existing software offers contrast enhancements to ease viewing, simultaneous enhancement of both contours and texture detail is difficult. This disclosure describes contrast-enhancement techniques controllable by a single parameter. The techniques enable a user to easily trade off texture detail against contour enhancement. A simple user interface such as a slider is provided that enables users to quickly adjust display results for different scenarios, such as reinforcing contours for textual material or emphasizing textures for fibered (e.g., paper, textile) material. Regardless of the value …

Low-Frequency Noise Reduction From Mipi C-Phy Interfaces, Sayed Mobin, Xu Wang

Defensive Publications Series

This disclosure describes techniques for improved routing of high speed C-PHY signal traces and the placement of power conversion components on a logic board of a camera system. Per techniques of this disclosure, low frequency power supply noise coupling into high speed MIPI C-PHY signals is reduced or eliminated by placing the power converter components at a minimum distance from the MIPI C-PHY high speed channels. Additionally, the ground (GND) return of the power supplies is improved for better noise reduction. In some implementations, the wide (high frequency) and ultra-wide (low frequency) channels are swapped. The low frequency coupled noise …

Extending Mipi C-Phy Channel Length By Using A Micro-Coaxial Cable And Micro-Coaxial Connector, Sayed Mobin, Xu Wang

Defensive Publications Series

This disclosure describes techniques to passively improve channel length constraints in camera systems. Per techniques of this disclosure, a micro-coaxial cable is utilized in the camera module subsystem to enable extension of the Mobile Industry Processor Interface (MIPI) C-PHY channel length. The camera module is connected to the main logic board (MLB) by using a micro-coaxial cable and a micro-coaxial connector. The camera module subsystem further includes an interposer board that is utilized to connect the camera side flexible printed circuit (FPC). The interposer board includes a micro-coaxial connector to enable the MLB side connection and a B2B connector to …

Bayesian Methodology To Model Field Failures Using Precise Operating Time, Ravi Teja Chikkam, Sean C Pegado, Colin Joseph Lacy

Defensive Publications Series

Field failures of products are frequently modeled using a constant failure rate assumption along with biased device usage times. This methodology provides convenience but may be inaccurate due to the failure rate assumptions and unavailability of precise device usage data. Techniques described herein provide for computing the precise device usage time along with assuming varying failure rates to better estimate field failures.

Constraint-Aware Spatial Planning For Connective Pathways In Structured Environments, Julian Freiberger

Defensive Publications Series

This disclosure presents a modular approach for constraint-aware spatial planning of connective pathways within structured environments. It addresses the challenge of defining viable trajectories for routed transmission elements—such as signal and power transmission lines, fluidic tubing, hydraulic piping, pneumatic and other conduit systems, or vacuum lines—while meeting spatial, physical, and design-related constraints.

The system abstracts the configuration space into a segmented spatial representation, builds a dynamic relationship model to enable contextual navigation, and applies multi-criteria evaluation to identify compliant connection traversals. A flexible optimization layer adapts routes to accommodate real-world constraints, supports user-defined preferences, and enables bundling and spatial adaptation …

Stego Networks Identification Fragment (Snif), Maria Smith, Ervin Lopez

Defensive Publications Series

The present disclosure provides a method for detecting secret messages, encoded in a Non-Fungible Token (NFT) using steganography. Multiple characteristics such as pixel information, noise, frequency, entropy, and color palette of the NFT are analyzed parallelly and a confidence score is calculated. Based on the confidence score, it is determined whether any secret message encoded in the NFT or not.

Pharmaceutical Composition Of Vismodegib Capsules 150 Mg, Anonymous

Defensive Publications Series

A stabilized pharmaceutical composition comprising Vismodegib or a pharmaceutically acceptable salt thereof and at least one pharmaceutically acceptable excipient, wherein said composition simultaneously achieves desired dissolution profile, stability and bioavailability.