Abstract: A merchant terminal or a customer terminal receives first input(s) associated with a first POS transaction with a first customer. Based on the first input(s), it is determined that the first POS transaction is in a first item-input portion and so the merchant terminal is designated as a state control terminal for the first POS transaction. Based on a trigger event occurring for the first POS transaction, it is determined that the first POS transaction is in a payment-input portion, and the customer terminal is designated as the state control terminal. Second input(s) associated with a second POS transaction with a second customer are received prior to receiving payment input to the first POS transaction and while the customer terminal is the state control terminal for the first POS transaction. Based on the second input(s), it is determined that that the second POS transaction is in a second-transaction item-input portion.

Abstract: A media content platform is described. In accordance with the described techniques, a first request is received from an artist entity to make a media content item available for modification by other entities on the media content platform. The first request includes one or more access controls that control use of the media content item. The media content item is stored on the media content platform. A second request is received from a requesting entity to modify the media content item. The second request accepts the one or more access controls. Access to the media content item for modification is granted to the requesting entity. A new media content item that incorporates at least a portion of the media content item is received from the requesting entity is received.

Abstract: Intelligent application of reserves to transactions is described. In an example, server(s) associated with a payment processing service receives first transaction data associated with a plurality of first transactions, wherein the first transaction data includes indications, for an individual first transaction, of whether a chargeback request occurred and item(s) and a customer associated with the transaction. In an example, the servers process the plurality of first transactions. A predictive model is trained based at least in part on the first transaction data. Second transaction data is received from a POS device of a second merchant associated with a second transaction. A value reflective of a level of risk for the second transaction is determined based on inputting an item or customer associated with the second transaction into the predictive model.

Abstract: An electronic device may include a printed circuit board having a physically unclonable function (PUF) source. The PUF source includes a plurality of fuses that provide PUF data based on a measurement of electrical parameters resulting from a first signal being transmitted through the plurality of fuses. The electronic device also has processing circuitry in communication with the PUF source that can detect a triggering event at the electronic device and determine an event type based on the detected triggering event. The processing circuitry can select at least one fuse of the plurality of fuses based on the determined event type and change an electrical property of the selected at least one fuse such that the PUF data from the PUF source is modified.

Abstract: In one embodiment, a method includes receiving, by a payment service system (PSS), a payment request from a payment application executing on a device of a sender. The payment request includes a recipient identifier corresponding to a recipient. The sender and recipient have financial accounts associated with the PSS. The method includes determining a similarity score based on a comparison of contact records associated with the device of the sender and contact records associated with a device of the recipient. The method includes, responsive to determining that the similarity score does not satisfy a threshold similarity score, transmitting a confirmation request to the device of the sender to confirm an identity of the recipient. The method includes receiving, from the device of the sender, an approval response to the confirmation request. The method includes, authorizing a payment transaction associated with the payment request based on the approval response.

Abstract: Technologies are described herein for classifying personalized interactions at an application. A method can include receiving and storing user inputs associated with interactions between users of the application, building historical models based on the user inputs to classify the interactions, wherein building a historical model for a particular user comprises aggregating particular user inputs associated with a set of previous interactions between a particular user and other users, in association with a pending interaction for the particular user and during the pending transaction associating a current user input with the historical model for the particular user and based on analyzing the historical model for the particular user, determining that the pending interaction satisfies a condition, and interrupting the pending interaction based on determining that the pending interaction satisfies the condition.

Abstract: Technologies are described herein for refining, using visual media inputs, generative artificial intelligence (AI) model outputs that include item descriptions. In some implementations, a method includes receiving, from a first device, a component list for an item that is to be included in a menu of items, the list including multiple components. Using a first generative AI model, a text natural language response is generated that includes a description for the item based on the component list. The text natural language response and visual media data of the item are provided to a second generative AI model that modifies the description for the item in the text natural language response based on detection of at least one component in the visual media data. The modified description is provided to the first device for inclusion in the menu of items.

Abstract: Technologies are described herein for refining, using visual media inputs, generative artificial intelligence (AI) model outputs that include media playlists. In some implementations, a method includes obtaining context data associated with a physical area of a merchant, where at least some of the context data is received from a first device. The context data includes visual media data depicting a scene of the physical area. The context data is provided to a content recommendation service that utilizes machine learning model(s) and searches a catalog based on the context data to obtain a list of content items. The list of content items and context data are provided to a generative AI model that filters and ranks the content items into an ordered list of recommended content items based on the context data. The ordered list is provided to the first device for playback of the recommended content items.

Abstract: Particular embodiments receive, by a payment service in association with a user account associated with a service provider, an identity verification submission associated with an identifier and a name. The payment service, for the phone number, queries contact records associated with user accounts associated with the service provider. The payment service receives, as a result of the query, several name options associated with the phone number, where each of the name options are stored in individual contact records. The payment service determines a name option of the several name options to associate with the identifier based at least in part on a similarity of individual name options to other name options. The payment service approves or rejects the identity verification submission based at least in part on the determined name option.

Abstract: Implementing extended reality (XR) tags in an XR platform is described. A server(s) may obtain, via a user interface of an application executing on a client device, a definition of an XR tag, and may embed information in the XR tag in accordance with the definition of the XR tag. The server(s) may further obtain, via the user interface, one or more rules applicable to the XR tag. The server(s) may further store data representing the XR tag in a data store. In some examples, the definition and/or the one or more rules allow for customizing the XR tag and/or the information embedded in the XR tag to other client devices that are accessing the XR tag, users of the other client devices, and/or a creator of the XR tag.

Abstract: Using risk metrics to facilitate transactions is described. A payment service computing platform may, in association with a request to initiate an interaction with a merchant, determine a user risk metric associated with a user of a payment service. The platform may determine, based on transaction data associated with merchants, merchant risk metrics associated with the merchants, filter the merchants based on the user risk metric and the merchant risk metrics to generate a list of merchants, and cause a user interface of a payment application associated with the payment service and executing on a device of the user to present at least a portion of the list of merchants. The platform may then receive indications of a selected merchant and an item(s) to be purchased from the selected merchant, use a single-use payment instrument to complete a transaction for the item(s), and generate a loan associated with the transaction.

Abstract: Systems and methods for transaction facilitation are disclosed. The method includes receiving a request to initiate a payment transaction at a payment terminal of a seller, the request including a reference to a payment card associated with payment accounts of a user. In response to the request, a computer system queries a database for an identifier associated with the payment card and transmits a selection message to a mobile device based on the identifier. The selection message triggers an application executing at the mobile device to display a selection interface presenting the payment accounts, each associated with a respective interactive element, and a feedback interactive element enabling the user to provide feedback associated with the payment transaction. The computer system receives a selection of a payment account and feedback from the application, and facilitates the payment transaction based on the selected payment account and the feedback.

Abstract: Embedding-based search adjustment system is described. In an example, a search system generates digital content embeddings based on digital content characteristics using machine learning and indexes these embeddings with respective identifiers according to an embedding schema based on the digital content characteristics. Upon receiving a search result containing references to multiple items in response to a search query, the search system generates a search result embedding for the referenced items using machine learning. The search system then performs a similarity search comparing the search result embedding against the digital content embeddings to generate affinity scores. User interaction data related to the items in the search result is obtained. Based on both the affinity scores and the user interaction data, the search system adjusts the items within the search result. The adjusted search result is then presented for display in a user interface.

Abstract: Embedding-based search adjustment system is described. In an example, a search system generates digital content embeddings based on digital content characteristics using machine learning and indexes these embeddings with respective identifiers according to an embedding schema based on the digital content characteristics. Upon receiving a search result containing references to multiple items in response to a search query, the search system generates a search result embedding for the referenced items using machine learning. The search system then performs a similarity search comparing the search result embedding against the digital content embeddings to generate affinity scores. User interaction data related to the items in the search result is obtained. Based on both the affinity scores and the user interaction data, the search system adjusts the items within the search result. The adjusted search result is then presented for display in a user interface.

Abstract: A payment processing service (PPS) can receive, during a transaction, and from a mobile device, tokenized data associated with a customer's payment instrument. The PPS can determine that a first application on the mobile device, and a second application on a second mobile device of a second user, both have connectivity to the PPS. The PPS can register an association between the applications and determine a service offered by the second user. Using the tokenized data, the PPS can determine historical transaction data associated with the payment instrument. The PPS can send personalized content to the mobile device and receive an authorization request and transaction data for the transaction from the mobile device, which the mobile device receives from the second mobile device. The PPS can process payment for the transaction and send to the second application an indication of the authorization, without providing access to card information.

Abstract: A digital content contribution verification system in a decentralized network is described. In an implementation, digital content is obtained and a plurality of portions are located from the digital content. A decentralized identifier and verifiable credential are identified as associated with a respective portion of the plurality of portions. The decentralized identifier is resolvable to a respective node from a decentralized network of nodes individually configured to store, receive, and transmit data. Representations are displayed of the decentralized identifiers indicative of a respective entity and corresponding verifiable credentials validating a relationship of the respective entity with the respective portion.

Abstract: Techniques described herein are directed to determining that multimedia content displays a representation of an item offered for sale (1) at a first timestamp and (2) at a first location relative to a viewable window of a user device; generating an interactive element comprising an e-commerce tag interactable for purchase of the item; rendering, at the first timestamp, the interactive element on a first portion of the multimedia content and positioned relative to the representation of the item in a predetermined spatial configuration in the viewable window; rendering, at a second timestamp, the interactive element on a second portion of the multimedia content and positioned relative to the representation in the same spatial configuration; detecting an interaction with the interactive element; and based on detecting the interaction, displaying a graphical user interface configured to allow the user to purchase the item.

Abstract: Gating logic is described to control access based on verifiable credentials. The gating logic is employable in a variety of ways to leverage verifiable credentials in support of identity, qualifications, or other attributes of an entity, and may do so without exposing personal information. To do so, a software development kit is described in one or more examples that is configured to incorporate gating logic at a service provider system to leverage use of verifiable credentials.

Abstract: Point of sale (POS) systems and methods are described. The POS device detects, based on sensor data, a position of at least a portion of a user relative to a position of the POS device. The POS device includes a housing and a base. The POS device determines an adjustment to the position of the POS device applicable to the housing of the POS device. The adjustment causes the housing to rotate about an axis that is parallel to a surface of the housing and directs the POS device to face the position of at least the portion of the user. The POS device actuates at least one actuator to perform the adjustment.