Abstract: At least one aspect of the present disclosure is directed to systems and methods of pruning retrieval tokens from sets of retrieval tokens based on criteria. The system can receive a plurality of retrieval tokens including a second retrieval token. The system can retrieve an indication of a first token and a plurality of requests. The system can construct a first bit string based on the predicted requests and the first retrieval token. The system can retrieve a second bit string corresponding to the second retrieval token. The system can compare the first bit string to the second bit string to determine a similarity value. The system can determine the similarity value is greater than a predetermined threshold. The system can remove the first and second retrieval token from the plurality to create a pruned set of retrieval tokens. The system can provide the pruned set to a content.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of secure and privacy preserving device classification. A server can maintain a plurality of data records, each including an indication of a request and a known classification value. The server can train a context obfuscation model using each of the plurality of requests and known classification values. The server can train a classification model using resources and category information from a data structure in the memory of the client device. The server can transmit the context obfuscation model to a different plurality of client devices. The server can receive a request for classification including a classification vector and request metadata. The server can determine the classification of the device responsible for the request using the classification model. The server can transmit the device classification to the device responsible for the request.

Abstract: Enhanced search results are generated using multi-document summarization. A multi-document summarization system receives a search query from a user and retrieves a plurality of search result documents based on the search query. The summarization system generates a summary of each of the plurality of search result documents using distinct per-document summarization machine learning models, where the distinct per-document summarization machine learning models are trained on a training dataset. The summarization system synthesizes the summary of each of the plurality of search result documents into a single-consolidated answer responsive to the received search query. The multi-document summarization system formats the single-consolidated answer to include citations to the plurality of search result documents.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of secure and privacy preserving device classification. A server can maintain a plurality of data records, each including an indication of a request and a known classification value. The server can train a context obfuscation model using each of the plurality of requests and known classification values. The server can train a classification model using resources and category information from a data structure in the memory of the client device. The server can transmit the context obfuscation model to a different plurality of client devices. The server can receive a request for classification including a classification vector and request metadata. The server can determine the classification of the device responsible for the request using the classification model. The server can transmit the device classification to the device responsible for the request.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of pruning retrieval tokens from sets of retrieval tokens based on criteria. The system can receive a plurality of retrieval tokens including a second retrieval token. The system can retrieve an indication of a first token and a plurality of requests. The system can construct a first bit string based on the predicted requests and the first retrieval token. The system can retrieve a second bit string corresponding to the second retrieval token. The system can compare the first bit string to the second bit string to determine a similarity value. The system can determine the similarity value is greater than a predetermined threshold. The system can remove the first and second retrieval token from the plurality to create a pruned set of retrieval tokens.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of pruning retrieval tokens from sets of retrieval tokens based on criteria. The system can receive a plurality of retrieval tokens including a second retrieval token. The system can retrieve an indication of a first token and a plurality of requests. The system can construct a first bit string based on the predicted requests and the first retrieval token. The system can retrieve a second bit string corresponding to the second retrieval token. The system can compare the first bit string to the second bit string to determine a similarity value. The system can determine the similarity value is greater than a predetermined threshold. The system can remove the first and second retrieval token from the plurality to create a pruned set of retrieval tokens. The system can provide the pruned set to a content provider.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of secure and privacy preserving device classification. A server can maintain a plurality of data records, each including an indication of a request and a known classification value. The server can train a context obfuscation model using each of the plurality of requests and known classification values. The server can train a classification model using resources and category information from a data structure in the memory of the client device. The server can transmit the context obfuscation model to a different plurality of client devices. The server can receive a request for classification including a classification vector and request metadata. The server can determine the classification of the device responsible for the request using the classification model. The server can transmit the device classification to the device responsible for the request.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of pruning retrieval tokens from sets of retrieval tokens based on criteria. The system can receive a plurality of retrieval tokens including a second retrieval token. The system can retrieve an indication of a first token and a plurality of requests. The system can construct a first bit string based on the predicted requests and the first retrieval token. The system can retrieve a second bit string corresponding to the second retrieval token. The system can compare the first bit string to the second bit string to determine a similarity value. The system can determine the similarity value is greater than a predetermined threshold. The system can remove the first and second retrieval token from the plurality to create a pruned set of retrieval tokens. The system can provide the pruned set to a content provider.