Abstract: Responsive to digital input received in a natural language, examples formulate an instruction for a generative machine learning model (GMLM), where the instruction includes an input validation sub-instruction and a code generation sub-instruction. Via processing of the digital input and the code generation sub-instruction by the GMLM, examples generate and output, by the GMLM, code in a programming language, where the code in the programming language corresponds to the digital input received in the natural language. Via processing of the input validation sub-instruction and the code by the GMLM, examples detect an unvalidated portion of the digital input. Examples may exclude the unvalidated portion of the digital input from an execution of the code generated by the GMLM.

Abstract: In some examples, input is provided to a first input augmentation sub-agent of a multi-agent system and input augmentation data is received from the first input augmentation sub-agent. The input augmentation data includes an aggregation of query results generated by an execution of a query on a dataset. The query is formulated by a generative machine learning model (GMLM) in response to a code generation instruction. The code generation instruction is formulated by the first input augmentation sub-agent in response to the input. The aggregation of query results is formulated by the GMLM in response to the execution of the query. A learning including a machine learning-based representation of the input and the input augmentation data is generated. The learning is used to determine a non-explicit user preference. The non-explicit user preference is used to control execution of a task according to the non-explicit user preference.

Abstract: A method involves first receiving a set of data on rewards associated with previously chosen content variant choices, selected based on an initial content variant choice model. This initial model is informed by a prior set of data. A second, updated content variant choice model is then determined based on this first set of reward data. When a request for selecting a content variant choice is received, it comes with contextual features. The method involves estimating the expected rewards for a range of content variant choices, considering these contextual features. Subsequently, a specific content variant choice is chosen based on both the updated model and the anticipated rewards. Finally, the chosen content variant is displayed on a device, responding to the initial request.

Abstract: Computer-implemented techniques for recipient session attribution in an online service. When the techniques are implemented in the context of an online service in which end-users are alerted about the online end-user actions of other end-users, the impact of the online actions on the online session activity of the recipients of the alerts can be measured post-hoc, after the online actions have been taken and the online sessions have been conducted. The techniques may be implemented in the context of a single-randomization AB experiment with the online service to measure the recipient session impact of the treatment feature of the experiment where the end-user action under test of the experiment is an alert-triggering action.

Abstract: A method for managing account data and handling account recovery requests are disclosed. The method comprises a multi-level identity verification process, including a first level where a specific computing device requesting recovery of an electronic account is requested to identify a trusted contact for the electronic account and a second level where the specific computing device is requested to provide a dynamically generated security code that has been communicated to a trusted contact identified by the specific computing device.

Abstract: A method for managing account data and handling account recovery requests are disclosed. The method comprises a multi-level identity verification process, including a first level where a specific computing device requesting recovery of an electronic account is requested to identify a trusted contact for the electronic account and a second level where the specific computing device is requested to provide a dynamically generated security code that has been communicated to a trusted contact identified by the specific computing device.

Abstract: Techniques are provided for displaying information about entities in a social network. An analysis of profiles of multiple representatives is performed. Each representative is registered with a social network provider and represents an organization from multiple organizations. Based on the analysis, the organizations are ranked. Data about a subset of the organizations is presented, based on the ranking, through a user interface. A user selects an indicator that is associated with a particular organization of the multiple organizations. In response to the input, a subset of the representatives is identified. One or more scores that were generated for a particular representative in the subset are determined. Data about the subset of the representatives is caused to be presented through the user interface. The data identifies the one or more scores and associates the one or more scores with the particular representative.