Abstract: A multi-API security policy that covers multiple API calls of a transaction is dynamically enforced at runtime, without access to the specification or code of the APIs. Calls made to APIs of the transaction are logged, and the logs are read. Data objects used by the APIs are identified. Specific data labels are assigned to specific fields of the data objects, consistently identifying data fields of specific types. Linkages are identified between specific ones of the multiple APIs, based on the consistent identification of specific types of data fields. An API call graph is constructed, identifying a sequence of API calls made during the transaction. The call graph is used to enforce the security policy, by tracking the flow of execution of the multi-API transaction at runtime, and detecting actions that violate the security policy. Security actions are taken responsive to the detected actions that violate the policy.

Abstract: A method of playing media content in a telecommunication network is disclosed. The method involves uploading media content on a server (100) by a caller device (400). The method further includes selecting at least one callee device (500) from a contact list of the device (400) via a predefined application (300). Further, the method includes forwarding the content from the server to a selected callee device (500). The method is followed by outputting the content by the application (300) on the selected device (500). The content is selected by the device (400), and the content is output at least one of when the selected device (500) is receiving a call from the device (400) or the selected device (500) is commencing the call to the device (400), the content being played on the selected device (500) by capturing ring signal via a ring signal capturing module (250).

Abstract: A request to perform a write operation at a memory device is received. Current wordline start voltage (WLSV) information associated with a particular memory segment of the plurality of memory segments is retrieved. The write operation is performed on the particular memory segment. In a firmware record in a memory sub-system controller, information is stored indicative of a last written memory page associated with the particular memory segment on which the write operation is performed. The firmware record is managed in view of the information indicative of the last written memory page associated with the performed write operation. Each entry of the firmware record comprises one or more identifying indicia associated with a respective memory segment, at least one of the identifying indicia being a wordline start voltage (WLSV) associated with the respective memory segment.

Abstract: Software architectures relating to machine learning (e.g., relating to classifying sequential text data. Unlabeled sequential text data may be produced by a variety of sources such as text messages, email messages, message chats, social media applications, and web pages. Classifying such data may be difficult due to the freeform and unlabeled nature of text data from these sources. Thus, techniques for training a machine learning algorithm to classify unlabeled text data in freeform format. Training is based on generation of labelling functions from lexical databases, applying the labelling functions to unlabeled text data in an unsupervised manner, and generating trained classifiers that accurately classify the unlabeled text data. The trained classifiers may then be implemented classify text data accessed from the variety of sources. The present techniques provide high-quality and efficient labeling of unlabeled text data in freeform formats.

Abstract: Systems and methods are disclosed for detecting crosswalk locations. Crosswalk locations can be detected by determining at least two painted lines on a road surface, and then combining the at least two painted lines on the road surface into a grouping of related elements. The grouping of related elements can be classified into a crosswalk (or in some embodiments a type of crosswalk) based on attributes of the grouping of related elements, where the attributes of the grouping of the elements includes a distance between the at least two painted lines, and an orientation of the grouping of related elements on the road surface.

Abstract: This disclosure describes architectures and techniques to provide information to a user about items with which the user interacts. In some instances, a user may utilize a wearable device that is configured to interact with one or more components of an information discovery system to obtain information about items in the user's environment.

Abstract: Generating user-specific polygraphs for network activity, including: gathering information describing network activity associated with a user and generating, based on the information, a user-specific polygraph that includes one or more destinations associated with the network activity.

Abstract: A method for convolution in a convolutional neural network (CNN) is provided that includes accessing a coefficient value of a filter corresponding to an input feature map of a convolution layer of the CNN, and performing a block multiply accumulation operation on a block of data elements of the input feature map, the block of data elements corresponding to the coefficient value, wherein, for each data element of the block of data elements, a value of the data element is multiplied by the coefficient value and a result of the multiply is added to a corresponding data element in a corresponding output block of data elements comprised in an output feature map.

Abstract: The present invention relates to a polyethylene composition comprising a base resin comprising a low molecular weight ethylene polymer component and a high molecular weight ethylene polymer component, wherein the high molecular weight ethylene polymer component has a higher weight average molecular weight than the low molecular weight ethylene polymer component, wherein the base resin has a density of at least 958.0 kg/m3, and the polyethylene composition a melt flow rate MFR2 (190° C., 2.16 kg) of from 0.50 to 0.80 g/10 min and a molecular weight distribution being the ratio of the weight average molecular weight and the number average molecular weight, Mw/Mn, of from 10.0 to 15.0, a process for producing said polyethylene composition, an article comprising said polyethylene composition and the use of said polyethylene composition for the production of a film.

Abstract: Methods and systems for compressing a matrix are described. The matrix, having a plurality of rows formed by a respective plurality of vectors, is partitioned into a plurality of submatrices, each submatrix containing sub-vectors from a respective group of one or more contiguous columns of the matrix. For each given submatrix, the sub-vectors are clustered into a plurality of clusters. For each given cluster, a centroid and a variance are computed and stored, based on the sub-vectors belonging to the given cluster. A mapping relating each vector to a respective cluster in each submatrix is stored. The stored centroids, stored variances and stored mapping form a set of compressed data for reconstruction of the matrix.

Abstract: Three-dimensional multi-layer composite structures prepared by additive manufacturing techniques, as well as methods of preparing the structures by additive manufacturing techniques, wherein a multi-layer structure has layers of at least two different thicknesses and a precision thickness are disclosed herein. In some embodiments, a method includes forming a coarse feedstock layer having a coarse feedstock layer thickness, solidifying a portion of the coarse feedstock layer to form a solidified coarse feedstock layer having a solidified coarse feedstock layer thickness, before or after forming the solidified coarse feedstock layer, forming at least one fine feedstock layer having a fine feedstock layer thickness that is less than the coarse feedstock layer thickness, and solidifying a portion of the at least one fine feedstock layer to form the at least one solidified fine feedstock layer having a solidified fine feedstock layer thickness that is less than the solidified coarse feedstock layer thickness.

Abstract: An apparatus, method, and computer program product are provided for the improved and automatic prediction and modeling of one or more channels and relevant conditions through which resources may be directed to users in an environment where resource demand, utility, and perceived value vary over time. Some example implementations employ predictive, machine-learning modeling to facilitate the use of multiple disparate and unrelated data sets to extrapolate and otherwise predict the future needs for certain resources and identify the channels and conditions that may be employed to meet such future needs. An apparatus, method, system, and computer program product are provided for improved generating, adjusting, and/or facilitating approval of a resource offer set. Some example implementations employ one or more predictive models.

Abstract: Disclosed are various techniques for wireless communication. In an aspect, a user equipment (UE) measures, during a measurement period that spans multiple measurement opportunities, multiple positioning reference signal (PRS) instances, each PRS instance occupying a different measurement opportunity, to produce a plurality of positioning measurements. A PRS instance can be a PRS resource, a PRS resource set, a PRS frequency layer, a transmission/reception point, or combinations thereof. For each PRS instance measured, the UE determines whether the PRS instance was punctured. Upon a determination that the PRS instance was punctured, the UE discards at least a portion of the positioning measurement and modifies the measurement period, e.g., by restarting the measurement period or extending the measurement period in order to take a measurement of another PRS instance.

Abstract: In one embodiment, the device obtains telemetry data for traffic between endpoints in a plurality of local networks and an online application, the telemetry data including local interface data regarding local interfaces used by the endpoints to access the online application and data indicative of which points of presence (PoPs) were traversed by the traffic. The device identifies sessions of the online application in which an application experience metric was degraded. The device determines a root cause of the application experience metric being degraded for the sessions by assessing the telemetry data associated with the sessions. The device provides the root cause to a user interface for presentation.

Abstract: In some implementations, a mobile device may perform a plurality of signal strength measurements of a radio frequency (RF) signal transmitted by a satellite, wherein performing the plurality of signal strength measurements occurs over a period of time during which the mobile device is subject to a movement. The mobile device may determine, for each signal strength measurement of the plurality of signal strength measurements, a respective orientation of the mobile device corresponding to when the respective signal strength measurement was performed. The mobile device may determine a target orientation for the satellite-based communications based at least in part on a value of a particular signal strength measurement of the plurality of signal strength measurements and the respective orientation of the mobile device corresponding to the particular signal strength measurement. The mobile device may provide guidance for rotating the mobile device to the target orientation.

Abstract: To facilitate a handover of mobile devices from 5th Generation New Radio (5G) networks to 4th Generation (4G) networks, an accessibility and mobility management function (AMF) of the 5G network core inactivates a data session in which the mobile device is assigned an Internet protocol version 6 (IPv6) address when the mobile device is to be assigned an IP version 4 (IPv4) address in the 4G network. The AMF generates a modified context of the mobile device that omits the IPv6 address of the device. The inactivation of the IPv6 session causes the mobile device to initiate a new data session with the 4G core network, in which the device will be assigned an IPv4 address for use on the 4G network. The modified context is used by the 4G network to configure communications for the mobile device without interrupting network service to the mobile device.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit, to a network node, UE capability information associated with at least one machine learning component. The UE may receive, from the network node and based on the UE capability information, configuration information corresponding to the at least one machine learning component. The UE may generate a first machine learning output based on the machine learning component. The UE may perform a communication task based on the first machine learning output. Numerous other aspects are described.

Abstract: Techniques for generating formatting tags for textual content obtained from a source electronic document are disclosed. A system parses a digital file to obtain information about characters in an electronic document. The system applies tags to text generated based on the textual content of the electronic document by creating segments of textually-consecutive characters and applying corresponding text formatting style tags to the segments. The system further identifies segments of text overlapping bounding boxes in the electronic document. The system generates textual content including a segment of text and a corresponding hyperlink associated with the segment of text. The system further generates textual content by selectively applying line breaks from the source electronic document in the textual content.

Abstract: A method includes receiving a labeled dataset that includes a plurality of labeled samples and initially training the machine learning model using the labeled dataset. The method also includes receiving an unlabeled dataset that includes a plurality of unlabeled samples. The method also includes computing latent representation spaces for each respective sample of the plurality of labeled samples and each respective sample of the plurality of the unlabeled samples. The method also includes generating a k-nearest neighbor similarity graph based on the latent representation spaces, generating a combined similarity graph by augmenting the k-nearest neighbor similarity graph using an expert-derived similarity graph, and propagating, using the combined similarity graph, labels to each respective sample of the plurality of unlabeled samples.

Abstract: Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.