Abstract: Verifying large language model responses involves obtaining a query and its corresponding answer from a large language model. This conversational text is then fed into a second large language model, which translates the answer into first-order logic. The verification process uses an automated theorem prover. It checks the validity of this logic translation by determining the unsatisfiability of two scenarios: one where the negation of the logic translation and domain-specific logic formulas are combined, and another where the logic translation itself is combined with these formulas. Based on this analysis, the theorem prover ascertains whether the translated answer is valid, invalid, or neither. The final step is communicating this verification status through an appropriate output medium, such as a graphical user interface, a database, or a report, providing a structured and methodical approach to assessing the accuracy and reliability of language model responses.

Abstract: System and methods for IoT event detector correctness verification. Detector models (e.g., state-based models including variables, states, transitions and actions) take IoT device data as input and detect, based on the data, events that triggers actions. To verify a correctness of the models prior to deploying the models at scale, an event detector model correctness checker obtains a representation of a definition of the model, verifies, based on analysis of the model definition, whether the model complies with correctness properties, and generates a report indicating whether the model complies. Example correctness properties include a reachability correctness property that indicates that respective states or actions are reachable according to the definition of the event detector model. The analysis may be accessed via an interface element and may result in generation of a report that identifies a location of non-compliance within the model definition.

Abstract: Techniques for encoding quantum circuit mapping problems as SAT solver optimization problems are disclosed. Quantum circuit mapping often requires the use of SWAP gates in order to configure logical quantum computations to be executed using fixed quantum hardware device layouts. A quantum compilation service takes a logical quantum circuit, a physical qubit connectivity graph, and a requested number of SWAP gates to solve the mapping using and encodes the information into a Conjunctive Normal Form (CNF) equation using a layout-transition-based encoding scheme. The CNF equation is then provided to a SAT solver which attempts to determine an assignment for the mapping using the set number of SWAP gates requested. Multiple CNF equations corresponding to different requested numbers of SWAP gates may be solved for in parallel using multiple SAT solving instances.

Abstract: System and methods for IoT event detector correctness verification. Detector models (e.g., state-based models including variables, states, transitions and actions) take IoT device data as input and detect, based on the data, events that triggers actions. To verify a correctness of the models prior to deploying the models at scale, an event detector model correctness checker obtains a representation of a definition of the model, verifies, based on analysis of the model definition, whether the model complies with correctness properties, and generates a report indicating whether the model complies. Example correctness properties include a reachability correctness property that indicates that respective states or actions are reachable according to the definition of the event detector model. The analysis may be accessed via an interface element and may result in generation of a report that identifies a location of non-compliance within the model definition.

Abstract: A software development process may support a transition from unverifiable, legacy code to verifiable code that is provably correct by construction. A behavioral model may be developed for legacy software that includes various behavioral criteria. Then, source code implemented in a verifiable language may be verified using the behavioral model to perform verification. Once the source code is complete and verified, a new verified implementation may be compiled. The verified implementation may then be executed, along with the legacy software, to identify differences in behavior which are fed back into the behavioral model and subsequently into the new source code. This process may then be iterated with the verifiable code being deployable once behavioral differences are resolved.

Abstract: A document anonymization system transforms structured documents, such as security policies, that contain user-specific and other sensitive data, producing encoded logic problems in the format or language of one or more constraint solvers; the logic problems do not contain any of the sensitive data. The system may perform a one- or two-stage anonymization process: in a first stage, the electronic document is analyzed according to its document type to identify parameters likely to contain sensitive data, and the associated values are replaced with arbitrary values; in a second stage, after the anonymized electronic document is converted into logic formulae representing the data, the system performs replacements of string constants in the logic formulae with arbitrary strings to further anonymize the sensitive data.