Abstract: A user device may obtain sensor data related to a physical environment. The user device may process the sensor data to determine that a potential threat exists in the physical environment and a threat score associated with the potential threat. The user device may determine that the threat score satisfies a threat score threshold. The user device may obtain, based on determining that the threat score satisfies the threat score threshold, additional information related to the physical environment. The user device may generate, based on the additional information related to the physical environment and at least one of the sensor data, information indicating the potential threat in the physical environment, or the threat score associated with the potential threat, threat determination information associated with the physical environment. The user device may perform, based on the threat determination information associated with the physical environment, one or more actions.

Abstract: A user device may obtain sensor data related to a physical environment. The user device may process the sensor data to determine that a potential threat exists in the physical environment and a threat score associated with the potential threat. The user device may determine that the threat score satisfies a threat score threshold. The user device may obtain, based on determining that the threat score satisfies the threat score threshold, additional information related to the physical environment. The user device may generate, based on the additional information related to the physical environment and at least one of the sensor data, information indicating the potential threat in the physical environment, or the threat score associated with the potential threat, threat determination information associated with the physical environment. The user device may perform, based on the threat determination information associated with the physical environment, one or more actions.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating non-fungible tokens (NFTs) representing digital assets. In various embodiments, a server generates a first NFT comprising one or more hash values. Each hash value of the one or more hash values corresponds with at least one cryptographically verifiable asset of one or more cryptographically verifiable assets. The server further receives a first request to obtain a first portion of the first NFT for a user and determines a first value of the first NFT based on a crypto-value of each of the one or more cryptographically verifiable assets. The server generates a second NFT comprising a first NFT hash value, wherein a second value of the second NFT matches the first portion of the first value and issues the second NFT to the user.

Abstract: A system may include processor(s), and memory in communication with the processor(s) and storing instructions configured to cause the system to orient webpage content based on user attention. The system may determine a user has navigated to a webpage. The system may generate an attention level based on received user feature(s) associated with activity of the user on the webpage. Responsive to determining the attention level exceeds a predetermined threshold, the system may identify a duration associated with the attention level, transmit an offer to one or more entities to submit predetermined content based on the duration, receive predetermined content from the one or more entities, identify, based on a predetermined amount of predetermined content space, selected content of the received predetermined content for placement on the webpage, and cause a GUI of the user device to display the selected content.

Abstract: Methods and systems are described herein for generating updated sets of attributes that would turn a negative decision of an automated system into a positive decision. A received set of attributes associated with a negative decision of an automated system may be used to generate a latent representation of that set of attributes. A machine learning model may then be used to output a change value (an alpha value). The alpha value may represent a minimum change needed to be made to the set of attributes to change the negative decision to a positive decision. The alpha value may then be applied to the latent representation to generate an updated latent representation, which may then be decoded into an updated set of attributes that would generate a positive decision from the automated system.

Abstract: A system may receive user interface information that indicates an image, associated with a web page, that depicts an object for which a counterfeit estimation is to be determined, text associated with the web page, or an entity identifier that identifies an entity associated with the web page and the object. The system may determine a first estimation that the object is counterfeit based on performing an image analysis of the image, a second estimation that the object is counterfeit based on performing text analysis of the text, or a third estimation that the object is counterfeit based on performing an entity analysis of the entity. The system may determine the counterfeit estimation based on the first estimation, the second estimation, or the third estimation. The counterfeit estimation may indicate a likelihood that the object is counterfeit. The system may transmit information that identifies the counterfeit estimation.

Abstract: Disclosed embodiments may include a method and system for automated incremental payments. The system may identify recurring charges from historical account data. Based on the recurring charges and an incremental period, the system may calculate an incremental amount and expected amount. At each iteration of the incremental period, the incremental amount may be assigned to a savings bucket. The value of the savings bucket may be subtracted from an actual account balance to calculate a reduced account balance. The system may generate and transmit a graphical user interface to a user device showing the reduced account balance. The system may receive current data containing a charge that corresponds to the recurring charges. The system may reduce the value of the savings bucket by the amount of the current data charge. If the current data charge is different from the expected amount, the system may adjust the incremental amount accordingly.

Abstract: A system may include processor(s), and memory in communication with the processor(s) and storing instructions configured to cause the system to orient webpage content based on user attention. The system may determine a user has navigated to a webpage. The system may generate an attention level based on received user feature(s) associated with activity of the user on the webpage. Responsive to determining the attention level exceeds a predetermined threshold, the system may identify a duration associated with the attention level, transmit an offer to one or more entities to submit predetermined content based on the duration, receive predetermined content from the one or more entities, identify, based on a predetermined amount of predetermined content space, selected content of the received predetermined content for placement on the webpage, and cause a GUI of the user device to display the selected content.

Abstract: Methods and systems are described herein for generating recommendations for counterfactual explanations to computer alerts that are automatically detected by a machine learning algorithm. The methods and systems use an artificial neural network architecture that trains a hybrid classifier and autoencoder. For example, one model (or artificial neural network), which is a classifier, is trained to make predictions. A second model (or artificial neural network), which is an autoencoder, is trained to reconstruct its inputs. As the second model is trained to reconstruct its inputs means, the second model is implicitly trained to determine what in-sample data looks like. By combining these networks and train them jointly, the system generates predictions (e.g., counterfactual explanations) that are in-sample.

Abstract: Methods and systems are described herein for generating recommendations for counterfactual explanations to computer alerts that are automatically detected by a machine learning algorithm. The methods and systems use an artificial neural network architecture that trains a hybrid classifier and autoencoder. For example, one model (or artificial neural network), which is a classifier, is trained to make predictions. A second model (or artificial neural network), which is an autoencoder, is trained to reconstruct its inputs. As the second model is trained to reconstruct its inputs means, the second model is implicitly trained to determine what in-sample data looks like. By combining these networks and train them jointly, the system generates predictions (e.g., counterfactual explanations) that are in-sample.

Abstract: A tool for chamfering cleaved tips of optical fibers. The tool including conical bores of relatively smooth and hard material terminate at a cylindrical bore that is slightly larger than the fiber core maximum diameter and a fiber centering bore that is slightly larger than the fiber coating maximum diameter. The tool provided such that when a cleaved fiber tip is inserted into the centering bore the sharp edge falls upon the chamfering surface that, when rotated relative to the fiber, gently grinds the edge to the chamfer angle. Chamfering cannot occur on the core face due to the absence of tool surface at this dimension.

Abstract: A tool for chamfering cleaved tips of optical fibers. The tool including conical bores of relatively smooth and hard material terminate at a cylindrical bore that is slightly larger than the fiber core maximum diameter and a fiber centering bore that is slightly larger than the fiber coating maximum diameter. The tool provided such that when a cleaved fiber tip is inserted into the centering bore the sharp edge falls upon the chamfer that, when rotated relative to the fiber, gently grinds the edge to the chamfer angle. Chamfering cannot occur on the core face due to the absence of tool surface at this dimension.

Abstract: Providing updated build parameters to an additive manufacturing machine to improve quality of a part manufactured by the machine. Sensor data is received from the additive manufacturing machine during manufacture of the part using a first set of build parameters. The first set of build parameters is received. An evaluation parameter is determined based on the first set of build parameters and the received sensor data. Thermal data is generated based on a thermal model of the part derived from the first set of build parameters. A first algorithm is applied to the received sensor data, the determined evaluation parameter, and the generated thermal data to produce a second set of build parameters, the first algorithm being trained to improve the evaluation parameter. The second set of build parameters is output to the additive manufacturing machine to produce a second part.

Abstract: According to some embodiments, system and methods are provided, comprising calculating a region of competence for a data-driven model; executing a physics-driven model when the calculated region of competence for the data-driven model falls outside of a threshold region of competence; and calibrating the physics-driven model as a function of a discrepancy between physics-driven model and actual field data when a stopping criterion has not been met. Numerous other aspects are provided.

Abstract: Herein is disclosed an inlet liner for use within an injection port of a capillary gas chromatograph. The inlet liner can include a first fused quartz tube and a second fused quartz tube aligned along a common longitudinal axis; the outside surface of the first fused quartz tube affixed to the inside surface of the second fused quartz tube. In certain instances, the tubers are affixed at two points along the longitudinal axis thereby defining a hermetically sealed volume between the outside surface of the first quartz tube and the inside surface of the second fused quartz tube, wherein the hermetically sealed volume entrains a reactive surface.

Abstract: A tool for chamfering cleaved tips of optical fibers. The tool including conical bores of relatively smooth and hard material terminate at a cylindrical bore that is slightly larger than the fiber core maximum diameter and a fiber centering bore that is slightly larger than the fiber coating maximum diameter. The tool provided such that when a cleaved fiber tip is inserted into the centering bore the sharp edge falls upon the chamfer that, when rotated relative to the fiber, gently grinds the edge to the chamfer angle. Chamfering cannot occur on the core face due to the absence of tool surface at this dimension.

Abstract: Herein is disclosed an inlet liner for use within an injection port of a capillary gas chromatograph. The inlet liner can include a first fused quartz tube and a second fused quartz tube aligned along a common longitudinal axis; the outside surface of the first fused quartz tube affixed to the inside surface of the second fused quartz tube. In certain instances, the tubers are affixed at two points along the longitudinal axis thereby defining a hermetically sealed volume between the outside surface of the first quartz tube and the inside surface of the second fused quartz tube, wherein the hermetically sealed volume entrains a reactive surface.

Abstract: In at least some implementations, a user supportable surface, includes a floor having a playing surface and a plurality of openings through the playing surface of the floor and a support on which the floor is supported above the ground to define at least part of an air chamber in communication with the openings. The support and floor arranged to support one or more people on the floor. Air flow may be directed or provided through the openings to provide a flow of air at the playing surface.

Abstract: Fiber optic end faces produced by laser ablation, as opposed to “cleave” or mechanical polish, offer advantages in some severe environment applications such as laser surgery and delivery of extremely high energy density. The “laser polished” fiber faces are more resistant to physical damage as well as less prone to damage other structures, owing to a lack of sharp, fragile edges and laser polished faces may be formed on fibers in planes and curvatures normal to the fiber axis or off normal, as desired.

Abstract: Carbon fiber sheet materials having improved dimensional stability and ease of handling are provided. The sheet materials include a carbon fiber network and an adhesive polymeric material adhered to at least one surface of the carbon fiber network. The invention further provides methods of making the carbon fiber sheet materials, as well as electrodes and electrical energy storage devices which include the carbon fiber sheet material as a component thereof.