Abstract: In one example, a system can receive a target input for a target model, update a summary statistic for a distribution based on the target input, and generate a set of input samples by sampling the distribution. The system can then provide the target input and the set of input samples as input to the target model, which can generate a target output based on the target input and a set of output samples based on the set of input samples. A background dataset can be updated based on the target output and the set of output samples. The updated background dataset, the target input, and the target output can then be input to an explanatory model, which can generate an explanation of why the target model generated the target output based on the target input. The explanation can be output to a user.

Abstract: A computing device accesses a plurality of datasets, each dataset comprising an input of a first plurality of inputs to a computer program, a first output of a plurality of outputs of the computer program, and a value identifying an importance of the input to the first output and produced by an explanation service. The computing device trains a machine-learned model to predict values based on the plurality of dataset. The computing device executes the computer program with a second plurality of inputs to produce a second output. The computing device inserts the second plurality of inputs and the second output into the machine-learned model, and the machine-learned model produces values for the second plurality of inputs based on the second plurality of inputs and the second output.

Abstract: A computing device obtains a plurality of input objects. The computing device determines settable attributes of each input object of the plurality of input objects and creates a subset of the settable attributes based on an input filter. The computing device inserts the subset of the settable attributes into a rules engine, the rules engine comprising a set of rules evaluated with an input and producing an output during an execution of the rules engine. The computing device determines, during an execution of the rules engine, a plurality of output objects created during the execution of the rules engine and gettable attributes of each output object of the plurality of output objects and creates a subset of the gettable attributes based on an output filter. The computing device stores rules and corresponding gettable attributes and values of the gettable attributes based on the subset of the gettable attributes in memory.

Abstract: A plurality of perturbed seed data values may be generated by performing a plurality of perturbation operations on an initial value to be processed by a predictive model. A plurality of counterfactual operations may be performed to generate a plurality of background data values of a background data store based on respective ones of the plurality of perturbed seed data values, a reference value within a domain of a predictive model, and the predictive model. A model analysis engine may be executed to generate a model analysis of the predictive model utilizing the background data store and the initial value.

Abstract: A plurality of perturbed seed data values may be generated by performing a plurality of perturbation operations on an initial value to be processed by a predictive model. A plurality of counterfactual operations may be performed to generate a plurality of background data values of a background data store based on respective ones of the plurality of perturbed seed data values, a reference value within a domain of a predictive model, and the predictive model. A model analysis engine may be executed to generate a model analysis of the predictive model utilizing the background data store and the initial value.

Abstract: Systems and methods are provided for simulating quantile behavior of a physical system. A plurality of parameter samples to a physical system are accessed and a subset of the parameter samples are identified, each of the plurality of parameter samples including a variation of parameters for the physical system. The physical system is simulated based on the subset of the parameter samples to generate simulation results, each of the subset of the parameter samples corresponding to a respective one of the simulation results. A neural network is trained to predict the simulation results based on the subset of the parameter samples.