Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, audio data that corresponds to an utterance. The actions further include determining a first value corresponding to a likelihood that the utterance includes a hotword. The actions further include receiving a second value corresponding to a likelihood that the utterance includes the hotword, the second value being determined by a second computing device. The actions further include comparing the first value and the second value. The actions further include based on comparing the first value to the second value, initiating speech recognition processing on the audio data.

Abstract: Implementations described herein relate to receiving user input directed to an automated assistant, processing the user input to determine whether data from a server and/or third-party application is needed to perform certain fulfillment of an assistant command included in the user input, and generating a prompt that requests a user consent to transmitting of a request to the server and/or the third-party application to obtain the data needed to perform the certain fulfillment. In implementations where the user consents, the data can be obtained and utilized to perform the certain fulfillment. In implementations where the user does not consent, client data can be generated locally at a client device and utilized to perform alternate fulfillment of the assistant command. In various implementations, the request transmitted to the server and/or third-party application can be modified based on ambient noise captured when the user input is received.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

Abstract: Image data is processed for noise reduction before encoding and subsequent decoding. For an input image in a spatial domain, two-dimensional (2-D) wavelet coefficients at multiple levels are generated. Each level includes multiple subbands, each associated with a respective subband type in a wavelet domain. For respective levels, a flat region of a subband is identified, which flat region includes blocks of the subband having a variance no higher than a first threshold variance. A flat block set for the subband type associated with the subband is identified, which includes blocks common to respective flat regions of the subband. A second threshold variance is determined using variances of the flat block set, and is then used for thresholding at least some of the 2-D wavelet coefficients to remove noise. After thresholding, a denoised image is generated in the spatial domain using the levels.

Abstract: A computer-implemented method includes receiving a batch of neural network inputs to be processed using a neural network on a hardware circuit. The neural network has multiple layers arranged in a directed graph and each layer has a respective set of parameters. The method includes determining a partitioning of the neural network layers into a sequence of superlayers. Each superlayer is a partition of the directed graph that includes one or more layers. The method includes processing the batch of inputs using the hardware circuit, which includes, for each superlayer in the sequence: i) loading the respective set of parameters for the layers in the superlayer into memory of the hardware circuit, and ii) for each input in the batch, processing the input through each of the layers in the superlayer using the parameters in the memory of the hardware circuit to generate a superlayer output for the input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Abstract: Processing of acoustic features of audio data to generate one or more revised versions of the acoustic features, where each of the revised versions of the acoustic features isolates one or more utterances of a single respective human speaker. Various implementations generate the acoustic features by processing audio data using portion(s) of an automatic speech recognition system. Various implementations generate the revised acoustic features by processing the acoustic features using a mask generated by processing the acoustic features and a speaker embedding for the single human speaker using a trained voice filter model. Output generated over the trained voice filter model is processed using the automatic speech recognition system to generate a predicted text representation of the utterance(s) of the single human speaker without reconstructing the audio data.

Abstract: Systems and methods of offloading multicast virtual network packet processing to a network interface card are provided. In an example implementation, a network interface card can route packets in a virtual network. The network interface card can be configured to receive a data packet having a multicast header for transmission to a plurality of destination virtual machines. The network interface card can retrieve a list of next hop destinations for the data packet. The network interface card can replicate the packet for each next hop destination. The network interface card can encapsulate each replicated packet with a unicast header that includes a next hop destination virtual IP address indicating the next hop destination and a source virtual IP address, and transmit the encapsulated packets.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes an attention neural network configured to perform the machine learning task, the attention neural network including one or more attention layers, each attention layer comprising an attention sub-layer and a feed-forward sub-layer that applies an element-wise multiplication between two vectors generated as a result of two different linear transformations performed on the same attended layer input.

Abstract: Coherent optical communications technology for recovery of 1D and 2D formatted optical signals. For example, 1D or 2D formatted signals that travel through fiber optic media may be recovered by separating the light into X- and Y-polarization components, rotating one polarization component (e.g., Y-component) into the polarization space of the other component (e.g., Y-component into the X-polarization space), delaying the rotated component enough to avoid destructive interference and combining the delayed component with the undelayed component to form a folded optical signal, which may then be processed as a X-polarized signal.

Abstract: Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. Search results responsive to a query are identified including a first search result in a top set of search results, the first search result associated with a first entity. A first eligible content item is identified for presentation along with the search results, the first eligible content item associated with the first entity. A combined content item is identified that is a combination of the first search result and first eligible content item and is to be presented as a search result responsive to the query. The combined content item is augmented including: identifying entities related to the first entity, identifying content items that are associated with the related entities, selecting at least one identified content item, and using content from the selected content items to augment the combined content item.

Abstract: A method for conserving resources in a distributed system includes receiving an event-criteria list from a resource controller. The event-criteria list includes one or more events watched by the resource controller and the resource controller controls at least one target resource and is configured to respond to events from the event-criteria list that occur. The method also includes determining whether the resource controller is idle. When the resource controller is idle, the method includes terminating the resource controller, determining whether any event from the event-criteria list occurs after terminating the resource controller, and, when at least one event from the event-criteria list occurs after terminating the resource controller, recreating the resource controller.

Abstract: A method, in a user device configured to communicate with a first base station via a radio link, for managing communication of a segmented radio resource control (RRC) message that includes N segments includes transmitting (212) a first M segments of the segmented RRC message to the first base station, M being an integer greater than zero and less than N, detecting (220), by processing hardware of the user device and before transmitting an (M+1)-th segment of the segmented RRC message, a failure of the radio link, and, after detecting the failure of the radio link, transmitting (264) at least a last N?M+1 segments of the segmented RRC message to either the first base station or a second base station.

Abstract: Bitrate-adaptive segmentation is performed for transcoding a video stream uploaded to an online video platform for hosting and later playback to platform users. The video stream is segmented into chunks based on prediction-based bit costs determined for frames of the video stream rather than based on scene changes detected within the video stream. The bitrate-adaptive segmentation includes determining inter-prediction bit costs and intra-prediction bit costs for frames of the video stream based on information indicated within a pass log based on a first pass encoding of the video stream, determining chunk boundaries for segmenting the video stream into a chunk based on the inter-prediction bit costs and the intra-prediction bit costs for the frames, and transcoding the chunk to produce a transcoded video stream.

Abstract: A method for remote attestation includes establishing, using a cryptographic protocol, a communication session between a first computing device and a second computing device. The communication session includes communications encrypted by an ephemeral session key. The method includes receiving, at the first communication device via the communication session, from the second computing device, an attestation request requesting the first computing device to provide an attestation report. The method includes generating, by the first computing device, the attestation report based on the ephemeral session key and sending, using the communication session, the attestation report to the second computing device.

Abstract: Features described herein generally relate to an electronic device and a method for activity detection. Particularly, an electronic device can be detected as being in a docked mode and/or a tablet mode. In the docked mode, activity can be detected based on a first detector. In the tablet mode, activity can be detected based on a second detector. The activity can be classified as corresponding to an activity type and a display screen of the electronic device can be updated based on the activity type.

Abstract: Local execution of smart device mesh automations with cloud-based failover is described herein. Embodiments operate in context of network-connected devices in a smart device mesh with a local automation system, where all devices communicate with cloud-based automation, and at least some also communicate with local automation. A determination is made whether to claim each automation routine for local automation, or to automatically execute the automation by the cloud when triggered. Triggered locally claimed automation routines cause attempted default execution locally by local automation with automatic failover execution by the cloud-based automation. Some embodiments further involve electing an executor device as part of claiming an automation routine and/or monitoring execution of automation routines to determine when to automatically de-claim locally claimed automation routines with poor local execution success rates.

Abstract: This document describes techniques and systems that enable grid-based enrollment for face authentication. The techniques and systems include overlaying a three-dimensional (3D) tracking window over a preview image of the user's face displayed via a display device. The 3D tracking window includes a plurality of segments, which persist to correspond to an approximate direction that the user's face is facing. Based on the tracking, segments are highlighted to indicate the approximate direction that the user's face is facing, a camera captures enrollment images of the user's face facing that direction, and embeddings are generated based on the enrollment images and stored in a fixed grid of pose cells corresponding to various facial poses for use in face authentication. Responsive to generation and storage of the embeddings, an indication that the one or more segments are completed is provided.

Abstract: Techniques and apparatuses are described that perform audioplethysmography calibration. Provided according to one or more preferred embodiments is a hearable, such as an earbud, that is capable of performing a novel physiological monitoring process termed herein audioplethysmography, an active acoustic method capable of sensing subtle physiologically-related changes observable at a user's outer and middle ear. The hearable can utilize audioplethysmography to monitor a user's biometrics, recognize facial behaviors, and/or sense an environment using acoustic signals. The techniques for audioplethysmography calibration enable the hearable to dynamically select frequencies that improve the performance of audioplethysmography. With audioplethysmography calibration, the hearable may utilize different frequencies for different ears and these frequencies may change over time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for distributing digital contents to client devices are described. For each of a plurality of client devices, the system receives a digital component request, identifies one or more user attributes of a user based on the digital component request, and sends the identified user attributes to the client device. The system obtains, from a shared storage of each client device, accumulated user attribute data and generates an aggregated user attribute report for a set of aggregation keys using the obtained accumulated user attribute data. The system distributes digital components to the client devices based on distribution parameters adjusted based on the aggregated user attribute report.

Abstract: A qubit device includes an elongated thin film uninterrupted by Josephson junctions, a quantum device in electrical contact with a proximal end of the elongated thin film, and a ground plane that is co-planar with the elongated thin film and is in electrical contact with a distal end of the elongated thin film, in which the thin film, the quantum device, and the ground plane comprise a material that is superconducting at a designed operating temperature.

Abstract: Techniques and apparatuses are described that perform respiration rate sensing. Provided according to one or more preferred embodiments is a hearable, such as an earbud, that is capable of performing a novel physiological monitoring process termed herein audioplethysmography, an active acoustic method capable of sensing subtle physiologically-related changes observable at a user's outer and middle ear. Instead of relying on other auxiliary sensors, such as optical or electrical sensors, audioplethysmography involves transmitting and receiving acoustic signals to monitor a user's respiration rate. In addition to being relatively unobtrusive, some hearables can be configured to support audioplethysmography without the need for additional hardware. As such, the size, cost, and power usage of the hearable can help make health monitoring accessible to a larger group of people and improve the user experience with hearables.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

Abstract: Aspects of the disclosed technology include techniques and mechanisms for an efficient error correction coding scheme that can detect and correct data errors that may occur in a memory. In general, the scheme comprises segmenting the data that would be transferred as part of a data request into different parts and applying error correction codes to the separate parts.

Abstract: Systems and techniques include using a sensor of a computing device to detect the presence of a first portion of a code, the code including at least the first portion and a second portion, where the first portion of the code is decodable and includes an identifier and the second portion of the code is non-decodable. The computing device recognizes the identifier in the first portion of the code and obtains instructions for decoding the second portion of the code using the identifier and/or data associated with the identifier. The instructions to decode the second portion of the code are processed to generate a decoded second portion of the code. The computing device performs an action defined in the decoded second portion of the code.

Abstract: A sensor system includes a touch sensor having a plurality of conductive sensing elements integrated with a flexible substrate. A first subset of sensing elements is coupled to a first side of the flexible substrate and a second subset of sensing elements is coupled to a second side of the flexible substrate. At least one sensing element of the first subset overlies a second sensing element and a third sensing element of the second subset. The sensor system is configured to obtain touch data based at least in part on a respective response to the touch input by the plurality of conductive sensing elements. The sensor system is configured to determine whether the touch input is associated with the first subset of conductive sensing elements or the second subset of conductive sensing elements based at least in part on the respective response to the touch input by the sensing elements.

Abstract: Methods, systems, and media for navigating a user interface are provided. In some embodiments, methods for navigating a user interface is provided, the method comprising: causing a user interface to be presented including media identifiers that correspond media assets; causing the media identifiers to be arranged along a first direction; causing a first media identifier at a first position to be highlighted; causing a menu element to be presented at a first menu position associated with the first media identifier; receiving an instruction from a user input device to navigate to a next element along the first direction; causing a second media identifier next to the first position to be highlighted in response to receiving the instruction; causing the menu element to be presented at a second menu position associated with the second media identifier; and inhibiting presentation of the menu element at the first menu position.

Abstract: Techniques of generating short answers for queries by a search engine include performing a training operation on a corpus of training data to train the score prediction engine, the corpus of training data including candidate passages providing short answers for display in callouts and remaining respective passages, from which a top scoring short answer is generated. In such implementations, the corpus of training data further includes the remaining respective passages and the respective titles of the candidate passage and remaining respective passages.

Abstract: A computer-implemented method for providing dynamically scrolling content within a vertically scrolling online publication is implemented by a content serving computing device in communication with a memory. The method includes retrieving a dynamically scrolling content item, receiving a set of display information related to a user computing device, and serving the dynamically scrolling content item within a slot of a vertically scrolling online publication presented at the user computing device, wherein the dynamically scrolling content item is served based partially on the set of display information, wherein the dynamically scrolling content item is configured to scroll horizontally in response to a first haptic input received by a user of the user computing device.

Abstract: A method for managing cloud infrastructure includes receiving, from a user of a user device, a cloud infrastructure modification request requesting modification to cloud infrastructure. The cloud infrastructure modification request includes abstract configuration data derived from a user interaction with a graphical user interface (GUI) executing on the user device. The method includes translating the abstract configuration data into a configuration command. The configuration command describes a configuration of the cloud infrastructure. The method includes updating a configuration file with the configuration command. The configuration file includes one or more cloud infrastructure specifications for the cloud infrastructure and is controlled by a source control management system. The method includes provisioning, using the updated configuration file, the cloud infrastructure.

Abstract: Smart glasses including a first audio device, a second audio device, a frame including a first portion, a second portion, and a third portion, the second portion and the third portion are moveable in relation to the first portion, the second portion including the first audio device and the third portion including the second audio device, and a processor configured to cause the first audio device to generate a signal, receive the signal via the second audio device, estimate a distance based on the received signal, and determine a configuration of the frame.

Abstract: A method for data storage includes assigning multiple different portions of a given object, which is stored in non-volatile storage, for access by multiple respective software modules running on one or more processors. Storage operations are performed by the software modules in the portions of the given object. Respective local values, which are indicative of most recent times the storage operations were performed in the given object by the respective software modules, are updated by the software modules. A global value is updated for the given object, by consolidating updates of the local values performed by the software modules.

Abstract: A mapping system allows a user to interact with any location on a digital map and present the user with location related information associated with the selected location. The location related information may be in the form or a card, pop-up, image, or other graphic and may be displayed on the map at or near the selected location, around the map, etc. The displayed location related information may include predetermined or pre-stored data about the location or may include location related information collected and generated on the fly in response to the user interaction with the digital map. The displayed location related information may be displayed in the same graphical format on the digital map regardless of whether location related information is predetermined information about the location that already exists or information that is collected and generated on the fly in response to the user interaction.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: Systems and methods for attributing a scroll event are described herein. The system can provide, to a client device, an infinite scroll attribution script. The script can cause the client device to set a dimension of an inline frame, embedded with a content document, of an page to a dimension corresponding to a viewport of an application and determine, responsive to detecting a scroll event, that a first offset between a first content document end and a first viewport end is less than or equal to a first predetermined threshold. The script can further cause the client device to determine, responsive to detecting the scroll event, that a second offset between a second content document end and a second viewport end is greater than or equal to a second threshold and assign the scroll event to the inline frame responsive to the determinations of the first and second offsets.

Abstract: A method for training a non-autoregressive TTS model includes obtaining a sequence representation of an encoded text sequence concatenated with a variational embedding. The method also includes using a duration model network to predict a phoneme duration for each phoneme represented by the encoded text sequence. Based on the predicted phoneme durations, the method also includes learning an interval representation and an auxiliary attention context representation. The method also includes upsampling, using the interval representation and the auxiliary attention context representation, the sequence representation into an upsampled output specifying a number of frames. The method also includes generating, based on the upsampled output, one or more predicted mel-frequency spectrogram sequences for the encoded text sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. One of the methods includes obtaining netlist data for a computer chip; and generating a computer chip placement, comprising placing a respective macro node at each time step in a sequence comprising a plurality of time steps, the placing comprising, for each time step: generating an input representation for the time step; processing the input representation using a node placement neural network having a plurality of network parameters, wherein the node placement neural network is configured to process the input representation in accordance with current values of the network parameters to generate a score distribution over a plurality of positions on the surface of the computer chip; and assigning the macro node to be placed at the time step to a position from the plurality of positions using the score distribution.

Abstract: A method includes receiving audio features and generating a latent speech representation based on the audio features. The method also includes generating a target quantized vector token and a target token index for a corresponding latent speech representation. The method also includes generating a contrastive context vector for a corresponding unmasked or masked latent speech representation and deriving a contrastive self-supervised loss based on the corresponding contrastive context vector and the corresponding target quantized vector token. The method also include generating a high-level context vector based on the contrastive context vector and, for each high-level context vector, learning to predict the target token index at the corresponding time step using a cross-entropy loss based on the target token index.

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

Abstract: The present disclosure provides for using multiple inertial measurement units (IMUs) to recognize particular user activity, such as particular types of exercises and repetitions of such exercises. The IMUs may be located in consumer products, such as smartwatches and earbuds. Each IMU may include an accelerometer and a gyroscope, each with three axes of measurement, for a total of 12 raw measurement streams. A training image includes a plurality of subplots or tiles, each depicting a separate data stream. The training image is then used to train a machine learning model to recognize IMU data as corresponding to a particular type of exercise.

Abstract: Techniques of providing continual augmented reality navigation include combining first and second 6DoF poses from, respectively, a localization from a map in a vicinity of a location to an image and from predicted 6DoF poses based on IMU data. The first 6DoF pose is based on a visual positioning system that uses map data from a vicinity of a location combined with an image from the world-facing camera of the AR smartglasses that provides 6DoF pose in world coordinates independent of the IMU. The second 6DoF pose is based on compensated rotational velocity and acceleration measurements derived from IMU intrinsic values.

Abstract: Implementations disclosed herein are directed to utilizing ephemeral learning techniques and/or federated learning techniques to update audio-based machine learning (ML) model(s) based on processing streams of audio data generated via radio station(s) across the world. This enables the audio-based ML model(s) to learn representations and/or understand languages across the world, including tail languages for which there is no/minimal audio data. In various implementations, one or more deduping techniques may be utilized to ensure the same stream of audio data is not overutilized in updating the audio-based ML model(s). In various implementations, a given client device may determine whether to employ an ephemeral learning technique or a federated learning technique based on, for instance, a connection status with a remote system. Generally, the streams of audio data are received at client devices, but the ephemeral learning techniques may be implemented at the client device and/or at the remote system.

Abstract: Implementations relate to determining a language for speech recognition of a spoken utterance, received via an automated assistant interface, for interacting with an automated assistant. Implementations can enable multilingual interaction with the automated assistant, without necessitating a user explicitly designate a language to be utilized for each interaction. Selection of a speech recognition model for a particular language can based on one or more interaction characteristics exhibited during a dialog session between a user and an automated assistant. Such interaction characteristics can include anticipated user input types, anticipated user input durations, a duration for monitoring for a user response, and/or an actual duration of a provided user response.

Abstract: A method of detecting a cough in an audio stream includes a step of performing one or more pre-processing steps on the audio stream to generate an input audio sequence comprising a plurality of time-separated audio segments. An embedding is generated by a self-supervised triplet loss embedding model for each of the segments of the input audio sequence using an audio feature set, the embedding model having been trained to learn the audio feature set in a self-supervised triplet loss manner from a plurality of speech audio clips from a speech dataset. The embedding for each of the segments is provided to a model performing cough detection inference. This model generates a probability that each of the segments of the input audio sequence includes a cough episode. The method includes generating cough metrics for each of the cough episodes detected in the input audio sequence.

Abstract: Techniques are described herein for selectively processing a user's utterances captured prior to and after an event that invokes an automated assistant to determine the user's intent and/or any parameters required for resolving the user's intent. In various implementations, respective measures of fitness for triggering responsive action by the automated assistant may be determined for pre-event and a post-event input streams. Based on the respective measures of fitness, one or both of the pre-event input stream or post-event input stream may be selected and used to cause the automated assistant to perform one or more responsive actions.

Abstract: Illustrative systems and methods for performing extended reality projection using monochrome pixel panels in inverted arrangements are described herein. For example, an extended reality projection system may include a binocular head-mounted display having a left side and a right side, a first set of monochrome pixel panels distributed in a first arrangement and collectively configured to produce a color image for presentation on the left side, and a second set of monochrome pixel panels distributed in a second arrangement and collectively configured to produce the color image for presentation on the right side. In this extended reality projection system, the second arrangement may be inverted from the first arrangement such that a color non-uniformity associated with the presentation on the right side is inverted from a color non-uniformity associated with the presentation on the left side. Corresponding methods and systems are also disclosed.

Abstract: A computer-implemented method that provides watermark-based image reconstruction to compensate for lossy encoding schemes. The method can generate a difference image describing the data loss associated with encoding an image using a lossy encoding scheme. The difference image can be encoded as a message and embedded in the encoded image using a watermark and later extracted from the encoded image. The difference image can be added to the encoded image to reconstruct the original image. As an example, an input image encoded using a lossy JPEG compression scheme can be embedded with the lost data and later reconstructed, using the embedded data, to a fidelity level that is identical or substantially similar to the original.

Abstract: Techniques for preparing datasets for geo experiments and improving accuracy of geo experiments are presented herein. The system can access a dataset of a plurality of geographic pairs. Additionally, the system can calculate a first outcome estimate based on a difference in response data and a difference in input data for a first geographic pair. Moreover, the system can calculate a plurality of experimental uncertainty estimates associated with the plurality of geographic pairs during an experimental time interval. The system can access historical data associated with the plurality of geographic pairs. Furthermore, the system can determine a beta value and a trim rate that reduces a sum of the plurality estimates. Subsequently, the system can remove, based on the first outcome estimate and the beta value, the first geographic pair from the plurality of geographic pairs to generate the first subset of geographic pairs.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for tailoring composite graphical assistant interfaces for interacting with multiple different connected devices. The composite graphical assistant interfaces can be generated in response to a user providing a request for an automated assistant to cause a connected device to perform a particular function. In response to the automated assistant receiving the request, the automated assistant can identify other connected devices, and other functions capable of being performed by the other connected devices. The other functions can then be mapped to various graphical control elements in order to provide a composite graphical assistant interface from which the user can interact with different connected devices. Each graphical control element can be arranged to reflect how each connected device is operating simultaneous to the presentation of the composite graphical assistant interface.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for the selection, provision and display of one or more digital components during display of content. Methods can include identifying a plurality of digital components that can be presented on the client device. A maximum number of digital components that can be presented in a slot of a content and the time duration of the slot is determined. For each digital component a score is generated based on the duration, a position requirement and the number of times the digital component is available for provision within the slot is generated. A first set of digital component is selected based on the scores and provided to the client device.