arXiv subjects

Konstantin Korovin

Publications and source records attributed to Konstantin Korovin.

18 recordsLinked to original sources

arXiv2026

Neuro-Symbolic Software Verification: Hyper-charging Local Language Models with Symbolic Reasoning at Scale

Loop invariant synthesis remains a central and pivotal bottleneck in formal software verification. Recent LLM-based Neuro-Symbolic tools have achieved impressive solve rates. However, these tools rely on proprietary, often expensive cloud APIs, which constitute a hurdle for privacy-sensitive industrial deployments where the source code cannot leave the organisation or where cost is a factor. We present VerIbmc, a neuro-symbolic pipeline that pairs symbolic invariant generation with locally deployable open-weight language models with the ESBMC verification tool. Our pipeline combines a deterministic symbolic invariant synthesis phase with an iterative LLM refinement loop driven by structured verifier feedback. In addition, we provide two types of pipelines that differ in their prompting strategy: Chain-of-Thought vs. Tree-of-Thought. We conduct an extensive experimental evaluation with five open-weight models (ranging from 7B to 120B parameters) across five benchmark families comprising of 520 problems (499 after excluding 21 with unavoidable overflow). Overall, the best single configuration (GPT-OSS-120B) solves 431 of 499 problems (86.4%). Additionally, on the four benchmark suites shared with the strongest cloud-API tools, VerIbmc is competitive running only on a single local machine. The evaluation shows symbolic invariant synthesis solves 75 problems without any LLM call and yields up to +35 additional problems for the weakest model. Importantly, all inference runs entirely on a single local machine using open-weight models -- no cloud API or proprietary model is required. Overall, we demonstrate that a neuro-symbolic approach based on LLMs can be used effectively for invariant synthesis in a privacy-preserving and energy-efficient manner, without having to resort to expensive proprietary frontier models locked behind APIs.

cs.SE↗

arXiv2026

ConVer: Using Contracts and Loop Invariant Synthesis for Scalable Formal Software Verification

Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up to the predetermined bound by unrolling all nested constructs. We present ConVer, a top-down compositional verification tool. Given a C program with a top-level assertion, ConVer decomposes verification top-down: it uses a large language model (LLM) to synthesise function contracts from the system property, then alternates system-level and function-level checks in a CEGAR-CEGIS loop, refining contracts whenever a check fails via SMART ICE learning. We evaluate ConVer on four benchmark suites of increasing difficulty and against other state-of-the-art (SOTA) tools. On the Frama-C benchmark of 45 simple C programs, ConVer achieves 82-96% verification success across three LLM backends, with 93-95% of converged programs requiring only a single CEGAR-CEGIS iteration. On the X.509 parser benchmark (6~programs) and LF2C-Simple suite (17 programs), ConVer achieves 33-50% and 82-88% success respectively. On the VerifyThis suite of 11 recursive and loop-intensive programs, the Pre-Abstraction strategy achieves 55-64% success. In addition, we present ESBMC-LF a preprocessor tool that converts LF models to C while preserving the properties of the LF files, enabling ConVer to verify them. We transpile the LF Verifier Benchmarks using ESBMC-LF to C; we denote those LF-Hard. We show that ConVer successfully verifies 67% of LF-Hard benchmarks overall.

cs.SE↗

arXiv2026

The Use of AI-Robotic Systems for Scientific Discovery

The process of developing theories and models and testing them with experiments is fundamental to the scientific method. Automating the entire scientific method then requires not only automation of the induction of theories from data, but also experimentation from design to implementation. This is the idea behind a robot scientist -- a coupled system of AI and laboratory robotics that has agency to test hypotheses with real-world experiments. In this chapter we explore some of the fundamentals of robot scientists in the philosophy of science. We also map the activities of a robot scientist to machine learning paradigms, and argue that the scientific method shares an analogy with active learning. We demonstrate these concepts using examples from previous robot scientists, and also from Genesis: a next generation robot scientist designed for research in systems biology, comprising a micro-fluidic system with 1000 computer-controlled micro-bioreactors and interpretable models based in controlled vocabularies and logic.

cs.LG↗

arXiv2025

ESBMC v7.6: Enhanced Model Checking of C++ Programs with Clang AST

This paper presents Efficient SMT-Based Context-Bounded Model Checker (ESBMC) v7.6, an extended version based on previous work on ESBMC v7.3 by K. Song et al. The v7.3 introduced a new Clang-based C++ front-end to address the challenges posed by modern C++ programs. Although the new front-end has demonstrated significant potential in previous studies, it remains in the developmental stage and lacks several essential features. ESBMC v7.6 further enhanced this foundation by adding and extending features based on the Clang AST, such as 1) exception handling, 2) extended memory management and memory safety verification, including dangling pointers, duplicate deallocation, memory leaks and rvalue references and 3) new operational models for STL updating the outdated C++ operational models. Our extensive experiments demonstrate that ESBMC v7.6 can handle a significantly broader range of C++ features introduced in recent versions of the C++ standard.

cs.LO↗

arXiv2024

Genesis: Towards the Automation of Systems Biology Research

The cutting edge of applying AI to science is the closed-loop automation of scientific research: robot scientists. We have previously developed two robot scientists: `Adam' (for yeast functional biology), and `Eve' (for early-stage drug design)). We are now developing a next generation robot scientist Genesis. With Genesis we aim to demonstrate that an area of science can be investigated using robot scientists unambiguously faster, and at lower cost, than with human scientists. Here we report progress on the Genesis project. Genesis is designed to automatically improve system biology models with thousands of interacting causal components. When complete Genesis will be able to initiate and execute in parallel one thousand hypothesis-led closed-loop cycles of experiment per-day. Here we describe the core Genesis hardware: the one thousand computer-controlled $μ$-bioreactors. For the integrated Mass Spectrometry platform we have developed AutonoMS, a system to automatically run, process, and analyse high-throughput experiments. We have also developed Genesis-DB, a database system designed to enable software agents access to large quantities of structured domain information. We have developed RIMBO (Revisions for Improvements of Models in Biology Ontology) to describe the planned hundreds of thousands of changes to the models. We have demonstrated the utility of this infrastructure by developed two relational learning bioinformatic projects. Finally, we describe LGEM+ a relational learning system for the automated abductive improvement of genome-scale metabolic models.

cs.AI↗

arXiv2024

SMLP: Symbolic Machine Learning Prover (User Manual)

SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and stability constraints, based on SMT, constraint and NN solvers. In addition its exploration methods are guided by probabilistic and statistical methods. SMLP is a general purpose tool that requires only data suitable for ML modelling in the csv format (usually samples of the system's input/output). SMLP has been applied at Intel for analyzing and optimizing hardware designs at the analog level. Currently SMLP supports NNs, polynomial and tree models, and uses SMT solvers for reasoning and optimization at the backend, integration of specialized NN solvers is in progress.

cs.LG↗

arXiv2024

SMLP: Symbolic Machine Learning Prover

Symbolic Machine Learning Prover (SMLP) is a tool and a library for system exploration based on data samples obtained by simulating or executing the system on a number of input vectors. SMLP aims at exploring the system based on this data by taking a grey-box approach: SMLP combines statistical methods of data exploration with building and exploring machine learning models in close feedback loop with the system's response, and exploring these models by combining probabilistic and formal methods. SMLP has been applied in industrial setting at Intel for analyzing and optimizing hardware designs at the analog level. SMLP is a general purpose tool and can be applied to systems that can be sampled and modeled by machine learning models.

cs.LG↗

arXiv2023

ESBMC v7.4: Harnessing the Power of Intervals

ESBMC implements many state-of-the-art techniques for model checking. We report on new and improved features that allow us to obtain verification results for previously unsupported programs and properties. ESBMC employs a new static interval analysis of expressions in programs to increase verification performance. This includes interval-based reasoning over booleans and integers, forward and backward contractors, and particular optimizations related to singleton intervals because of their ubiquity. Other relevant improvements concern the verification of concurrent programs, as well as several operational models, internal ones, and also those of libraries such as pthread and the C mathematics library. An extended memory safety analysis now allows tracking of memory leaks that are considered still reachable.

cs.SE↗

arXiv2023

LGEM$^\text{+}$: a first-order logic framework for automated improvement of metabolic network models through abduction

Scientific discovery in biology is difficult due to the complexity of the systems involved and the expense of obtaining high quality experimental data. Automated techniques are a promising way to make scientific discoveries at the scale and pace required to model large biological systems. A key problem for 21st century biology is to build a computational model of the eukaryotic cell. The yeast Saccharomyces cerevisiae is the best understood eukaryote, and genome-scale metabolic models (GEMs) are rich sources of background knowledge that we can use as a basis for automated inference and investigation. We present LGEM+, a system for automated abductive improvement of GEMs consisting of: a compartmentalised first-order logic framework for describing biochemical pathways (using curated GEMs as the expert knowledge source); and a two-stage hypothesis abduction procedure. We demonstrate that deductive inference on logical theories created using LGEM+, using the automated theorem prover iProver, can predict growth/no-growth of S. cerevisiae strains in minimal media. LGEM+ proposed 2094 unique candidate hypotheses for model improvement. We assess the value of the generated hypotheses using two criteria: (a) genome-wide single-gene essentiality prediction, and (b) constraint of flux-balance analysis (FBA) simulations. For (b) we developed an algorithm to integrate FBA with the logic model. We rank and filter the hypotheses using these assessments. We intend to test these hypotheses using the robot scientist Genesis, which is based around chemostat cultivation and high-throughput metabolomics.

q-bio.QM↗

arXiv2023

Graph Sequence Learning for Premise Selection

Premise selection is crucial for large theory reasoning as the sheer size of the problems quickly leads to resource starvation. This paper proposes a premise selection approach inspired by the domain of image captioning, where language models automatically generate a suitable caption for a given image. Likewise, we attempt to generate the sequence of axioms required to construct the proof of a given problem. This is achieved by combining a pre-trained graph neural network with a language model. We evaluated different configurations of our method and experience a 17.7% improvement gain over the baseline.

cs.LO↗

arXiv2022

Machine Learning Meets The Herbrand Universe

The appearance of strong CDCL-based propositional (SAT) solvers has greatly advanced several areas of automated reasoning (AR). One of the directions in AR is thus to apply SAT solvers to expressive formalisms such as first-order logic, for which large corpora of general mathematical problems exist today. This is possible due to Herbrand's theorem, which allows reduction of first-order problems to propositional problems by instantiation. The core challenge is choosing the right instances from the typically infinite Herbrand universe. In this work, we develop the first machine learning system targeting this task, addressing its combinatorial and invariance properties. In particular, we develop a GNN2RNN architecture based on an invariant graph neural network (GNN) that learns from problems and their solutions independently of symbol names (addressing the abundance of skolems), combined with a recurrent neural network (RNN) that proposes for each clause its instantiations. The architecture is then trained on a corpus of mathematical problems and their instantiation-based proofs, and its performance is evaluated in several ways. We show that the trained system achieves high accuracy in predicting the right instances, and that it is capable of solving many problems by educated guessing when combined with a ground solver. To our knowledge, this is the first convincing use of machine learning in synthesizing relevant elements from arbitrary Herbrand universes.

cs.LG↗

arXiv2021

AC Simplifications and Closure Redundancies in the Superposition Calculus

Reasoning in the presence of associativity and commutativity (AC) is well known to be challenging due to prolific nature of these axioms. Specialised treatment of AC axioms is mainly supported by provers for unit equality which are based on Knuth-Bendix completion. The main ingredient for dealing with AC in these provers are ground joinability criteria adapted for AC. In this paper we extend AC joinability from the context of unit equalities and Knuth-Bendix completion to the superposition calculus and full first-order logic. Our approach is based on an extension of the Bachmair-Ganzinger model construction and a new redundancy criterion which covers ground joinability. A by-product of our approach is a new criterion for applicability of demodulation which we call encompassment demodulation. This criterion is useful in any superposition theorem prover, independently of AC theories, and we demonstrate that it enables demodulation in many more cases, compared to the standard criterion.

cs.LO↗

arXiv2021

Bayesian Optimisation with Formal Guarantees

Application domains of Bayesian optimization include optimizing black-box functions or very complex functions. The functions we are interested in describe complex real-world systems applied in industrial settings. Even though they do have explicit representations, standard optimization techniques fail to provide validated solutions and correctness guarantees for them. In this paper we present a combination of Bayesian optimisation and SMT-based constraint solving to achieve safe and stable solutions with optimality guarantees.

cs.LG↗

arXiv2021

The ksmt calculus is a $δ$-complete decision procedure for non-linear constraints

ksmt is a CDCL-style calculus for solving non-linear constraints over real numbers involving polynomials and transcendental functions. In this paper we investigate properties of the ksmt calculus and show that it is a $δ$-complete decision procedure for bounded problems. We also propose an extension with local linearisations, which allow for more efficient treatment of non-linear constraints.

cs.LO↗

arXiv2019

A CDCL-style calculus for solving non-linear constraints

In this paper we propose a novel approach for checking satisfiability of non-linear constraints over the reals, called ksmt. The procedure is based on conflict resolution in CDCL style calculus, using a composition of symbolical and numerical methods. To deal with the non-linear components in case of conflicts we use numerically constructed restricted linearisations. This approach covers a large number of computable non-linear real functions such as polynomials, rational or trigonometrical functions and beyond. A prototypical implementation has been evaluated on several non-linear SMT-LIB examples and the results have been compared with state-of-the-art SMT solvers.

cs.LO↗

arXiv2018

Premise selection with neural networks and distributed representation of features

We present the problem of selecting relevant premises for a proof of a given statement. When stated as a binary classification task for pairs (conjecture, axiom), it can be efficiently solved using artificial neural networks. The key difference between our advance to solve this problem and previous approaches is the use of just functional signatures of premises. To further improve the performance of the model, we use dimensionality reduction technique, to replace long and sparse signature vectors with their compact and dense embedded versions. These are obtained by firstly defining the concept of a context for each functor symbol, and then training a simple neural network to predict the distribution of other functor symbols in the context of this functor. After training the network, the output of its hidden layer is used to construct a lower dimensional embedding of a functional signature (for each premise) with a distributed representation of features. This allows us to use 512-dimensional embeddings for conjecture-axiom pairs, containing enough information about the original statements to reach the accuracy of 76.45% in premise selection task, only with simple two-layer densely connected neural networks.

cs.AI↗

arXiv2016

Computing exponentially faster: Implementing a nondeterministic universal Turing machine using DNA

The theory of computer science is based around Universal Turing Machines (UTMs): abstract machines able to execute all possible algorithms. Modern digital computers are physical embodiments of UTMs. The nondeterministic polynomial (NP) time complexity class of problems is the most significant in computer science, and an efficient (i.e. polynomial P) way to solve such problems would be of profound economic and social importance. By definition nondeterministic UTMs (NUTMs) solve NP complete problems in P time. However, NUTMs have previously been believed to be physically impossible to construct. Thue string rewriting systems are computationally equivalent to UTMs, and are naturally nondeterministic. Here we describe the physical design for a NUTM that implements a universal Thue system. The design exploits the ability of DNA to replicate to execute an exponential number of computational paths in P time. Each Thue rewriting step is embodied in a DNA edit implemented using a novel combination of polymerase chain reactions and site-directed mutagenesis. We demonstrate that this design works using both computational modelling and in vitro molecular biology experimentation. The current design has limitations, such as restricted error-correction. However, it opens up the prospect of engineering NUTM based computers able to outperform all standard computers on important practical problems.

cs.CC↗

arXiv2002

Knuth-Bendix constraint solving is NP-complete

We show the NP-completeness of the existential theory of term algebras with the Knuth-Bendix order by giving a nondeterministic polynomial-time algorithm for solving Knuth-Bendix ordering constraints.

cs.LO↗