arXiv subjects

Rosemary Monahan

Publications and source records attributed to Rosemary Monahan.

At least 19 recordsLinked to original sources

arXiv2026

Graph Construction and Matching for Imperative Programs using Neural and Structural Methods

Reusing verification artefacts requires identifying structural and semantic similarities across programs and their specifications. In this paper, we focus on graph construction as a foundational step toward this goal. We present a pipeline that converts imperative programs and their annotations into typed, attributed graphs. Our experiments cover datasets including C with ACSL, Java with JML, and Dafny programs. The pipeline integrates abstract syntax tree parsing with semantic embeddings derived from models such as SentenceTransformer and CodeBERT. This enables the generation of graph representations that capture both structural relationships and semantic context. Our results show that consistent graph representations can be constructed across different languages and annotation styles. This work provides a practical basis for future steps in semantic enrichment and approximate graph matching for scalable verification artefact reuse.

cs.SE↗

arXiv2026

Learning-Infused Formal Reasoning: From Contract Synthesis to Artifact Reuse and Formal Semantics

This paper articulates a long-term research vision for formal methods at the intersection with artificial intelligence, outlining multiple conceptual and technical dimensions and reporting on our ongoing work toward realising this vision. It advances a forward-looking perspective on the next generation of formal methods based on the integration of automated contract synthesis, semantic artifact reuse, and refinement-based theory. We argue that future verification systems must builds towards individual correctness proofs toward a cumulative, knowledge-driven paradigm in which specifications, contracts, and proofs are continuously synthesised and transferred across systems. To support this shift, we outline a hybrid framework combining large language models with graph-based representations to enable scalable semantic matching and principled reuse of verification artifacts. Learning-based components provide semantic guidance across heterogeneous notations and abstraction levels, while symbolic matching ensures formal soundness. Grounded in compositional reasoning, this vision points toward verification ecosystems that evolve systematically, leveraging past verification efforts to accelerate future assurance.

cs.SE↗

arXiv2026

Quantitative Linear Logic for Neuro-Symbolic Learning and Verification

Differentiable Logics are deployed in neuro-symbolic learning tasks as a way of embedding logical constraints in the training objective of neural networks. A differentiable logic consists of a syntax to write logical properties and a semantics to interpret them as real-valued functions to be folded in the loss function. A defining trade-off of the field is that between logical properties of the connectives, and analytic concerns for the semantics, with both aspects being relevant in applications. At one extreme we find fuzzy logics, that have well-established algebraic and proof-theoretic foundations, and at the other ad-hoc differentiable logics like Fischer's DL2, conceived for deep learning applications. However, no satisfactory foundation has emerged yet. We propose a resolution to this long-standing tension via a novel logic, Quantitative Linear Logic (QLL), with foundational ambitions. Our design is driven by naturality -- the idea that, since logical constraints are translated to losses, the semantics of the connectives should be pertinent operations used in ML practice (that is, sum and log-sum-exp) on additive quantities (like logits). We then judge the result on two aspects: logical adequacy -- that they satisfy most of the standard logical laws of Linear Logic; and empirical effectiveness -- test-time performance (as measured by adversarial attacks) is well-correlated to the actual verification of the logical constraints (as measured by off-the-shelf neural network verifiers), which makes QLL stand out among SoTA techniques.

cs.LO↗

arXiv2026

Evaluating LLM-Generated ACSL Annotations for Formal Verification

Formal specifications are crucial for building verifiable and dependable software systems, yet generating accurate and verifiable specifications for real-world C programs remains challenging. This paper presents an empirical evaluation of automated ACSL annotation generation strategies for C programs, comparing a rule-based Python script, Frama-C's RTE plugin, and three large language models (DeepSeek-V3.2, GPT-5.2, and OLMo 3.1 32B Instruct). The study focuses on one-shot annotation generation, assessing how these approaches perform when directly applied to verification tasks. Using a filtered subset of the CASP benchmark, we evaluate generated annotations through Frama-C's WP plugin with multiple SMT solvers, analyzing proof success rates, solver timeouts, and internal processing time. Our results show that rule-based approaches remain more reliable for verification success, while LLM-based methods exhibit more variable performance. These findings highlight both the current limitations and the potential of LLMs as complementary tools for automated specification generation.

cs.SE↗

arXiv2026

Short Version of VERIFAI2026 Paper -- Learning Infused Formal Reasoning: Contract Synthesis, Artefact Reuse and Semantic Foundations

Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opaque and difficult to verify, limiting their applicability in safety-critical systems. Formal methods provide mathematically rigorous mechanisms for specifying and verifying system behaviour, yet the creation and maintenance of formal specifications remains labour intensive and difficult to scale. This paper outlines a research vision called Learning-Infused Formal Reasoning (LIFR), which integrates machine learning techniques with formal verification workflows. The framework focuses on three complementary research directions: automated contract synthesis from natural language requirements, semantic reuse of verification artifacts using graph matching and learning-based embeddings, and mathematically grounded semantic foundations based on the Unifying Theories of Programming (UTP) and the Theory of Institutions. Together these research threads aim to transform verification from isolated correctness proofs into a cumulative knowledge-driven process where specifications, contracts and proofs can be synthesised, aligned and reused across systems.

cs.SE↗

arXiv2025

Leveraging LLMs for Formal Software Requirements -- Challenges and Prospects

Software correctness is ensured mathematically through formal verification, which involves the resources of generating formal requirement specifications and having an implementation that must be verified. Tools such as model-checkers and theorem provers ensure software correctness by verifying the implementation against the specification. Formal methods deployment is regularly enforced in the development of safety-critical systems e.g. aerospace, medical devices and autonomous systems. Generating these specifications from informal and ambiguous natural language requirements remains the key challenge. Our project, VERIFAI^{1}, aims to investigate automated and semi-automated approaches to bridge this gap, using techniques from Natural Language Processing (NLP), ontology-based domain modelling, artefact reuse, and large language models (LLMs). This position paper presents a preliminary synthesis of relevant literature to identify recurring challenges and prospective research directions in the generation of verifiable specifications from informal requirements.

cs.SE↗

arXiv2025

A General Framework for Property-Driven Machine Learning

Neural networks have been shown to frequently fail to learn critical safety and correctness properties purely from data, highlighting the need for training methods that directly integrate logical specifications. While adversarial training can be used to improve robustness to small perturbations within $ε$-cubes, domains other than computer vision -- such as control systems and natural language processing -- may require more flexible input region specifications via generalised hyper-rectangles. Differentiable logics offer a way to encode arbitrary logical constraints as additional loss terms that guide the learning process towards satisfying these constraints. In this paper, we investigate how these two complementary approaches can be unified within a single framework for property-driven machine learning, as a step toward effective formal verification of neural networks. We show that well-known properties from the literature are subcases of this general approach, and we demonstrate its practical effectiveness on a case study involving a neural network controller for a drone system. Our framework is made publicly available at https://github.com/tflinkow/property-driven-ml.

cs.LG↗

arXiv2025

Working Document -- Formalising Software Requirements with Large Language Models

This draft is a working document, having a summary of nighty-four (94) papers with additional sections on Traceability of Software Requirements (Section 4), Formal Methods and Its Tools (Section 5), Unifying Theories of Programming (UTP) and Theory of Institutions (Section 6). Please refer to abstract of [7,8]. Key difference of this draft from our recently anticipated ones with similar titles, i.e. AACS 2025 [7] and SAIV 2025 [8] is: [7] is a two page submission to ADAPT Annual Conference, Ireland. Submitted on 18th of March, 2025, it went through the light-weight blind review and accepted for poster presentation. Conference was held on 15th of May, 2025; [8] is a nine page paper with additional nine pages of references and summary tables, submitted to Symposium on AI Verification (SAIV 2025) on 24th of April, 2025. It went through rigorous review process. The uploaded version on arXiv.org [8] is the improved one of the submission, after addressing the specific suggestions to improve the paper.

cs.SE↗

arXiv2025

A Short Survey on Formalising Software Requirements using Large Language Models

This paper presents a focused literature survey on the use of large language models (LLM) to assist in writing formal specifications for software. A summary of thirty-five key papers is presented, including examples for specifying programs written in Dafny, C and Java. This paper arose from the project VERIFAI - Traceability and verification of natural language requirements that addresses the challenges in writing formal specifications from requirements that are expressed in natural language. Our methodology employed multiple academic databases to identify relevant research. The AI-assisted tool Elicit facilitated the initial paper selection, which were manually screened for final selection. The survey provides valuable insights and future directions for utilising LLMs while formalising software requirements.

cs.SE↗

arXiv2025

Formalising Software Requirements using Large Language Models

This paper is a brief introduction to our recently initiated project named VERIFAI: Traceability and verification of natural language requirements. The project addresses the challenges in the traceability and verification of formal specifications through providing support for the automatic generation of the formal specifications and the traceability of the requirements from the initial software design stage through the systems implementation and verification. Approaches explored in this project include Natural Language Processing, use of ontologies to describe the software system domain, reuse of existing software artefacts from similar systems (i.e. through similarity based reuse) and large language models to identify and declare the specifications as well as use of artificial intelligence to guide the process.

cs.SE↗

arXiv2025

Adventures in FRET and Specification

This paper gives an overview of previous work in which the authors used NASA's Formal Requirement Elicitation Tool (FRET) to formalise requirements. We discuss four case studies where we used FRET to capture the system's requirements. These formalised requirements subsequently guided the case study specifications in a combination of formal paradigms. For each case study we summarise insights gained during this process, exploring the expressiveness and the potential interoperability of these approaches. Our experience confirms FRET's suitability as a framework for the elicitation and understanding of requirements and for providing traceability from requirements to specification.

cs.SE↗

arXiv2025

Comparing differentiable logics for learning with logical constraints

Extensive research on formal verification of machine learning systems indicates that learning from data alone often fails to capture underlying background knowledge, such as specifications implicitly available in the data. Various neural network verifiers have been developed to ensure that a machine-learnt model satisfies correctness and safety properties; however, they typically assume a trained network with fixed weights. A promising approach for creating machine learning models that inherently satisfy constraints after training is to encode background knowledge as explicit logical constraints that guide the learning process via so-called differentiable logics. In this paper, we experimentally compare and evaluate various logics from the literature, present our findings, and highlight open problems for future work. We evaluate differentiable logics with respect to their suitability in training, and use a neural network verifier to check their ability to establish formal guarantees. The complete source code for our experiments is available as an easy-to-use framework for training with differentiable logics at https://github.com/tflinkow/comparing-differentiable-logics.

cs.LO↗

arXiv2024

Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report

The increased reliance of self-driving vehicles on neural networks opens up the challenge of their verification. In this paper we present an experience report, describing a case study which we undertook to explore the design and training of a neural network on a custom dataset for vision-based autonomous navigation. We are particularly interested in the use of machine learning with differentiable logics to obtain networks satisfying basic safety properties by design, guaranteeing the behaviour of the neural network after training. We motivate the choice of a suitable neural network verifier for our purposes and report our observations on the use of neural network verifiers for self-driving systems.

cs.LO↗

arXiv2023

Comparing Differentiable Logics for Learning Systems: A Research Preview

Extensive research on formal verification of machine learning (ML) systems indicates that learning from data alone often fails to capture underlying background knowledge. A variety of verifiers have been developed to ensure that a machine-learnt model satisfies correctness and safety properties, however, these verifiers typically assume a trained network with fixed weights. ML-enabled autonomous systems are required to not only detect incorrect predictions, but should also possess the ability to self-correct, continuously improving and adapting. A promising approach for creating ML models that inherently satisfy constraints is to encode background knowledge as logical constraints that guide the learning process via so-called differentiable logics. In this research preview, we compare and evaluate various logics from the literature in weakly-supervised contexts, presenting our findings and highlighting open problems for future work. Our experimental results are broadly consistent with results reported previously in literature; however, learning with differentiable logics introduces a new hyperparameter that is difficult to tune and has significant influence on the effectiveness of the logics.

cs.LO↗

arXiv2023

Visualization of AI Systems in Virtual Reality: A Comprehensive Review

This study provides a comprehensive review of the utilization of Virtual Reality (VR) for visualizing Artificial Intelligence (AI) systems, drawing on 18 selected studies. The results illuminate a complex interplay of tools, methods, and approaches, notably the prominence of VR engines like Unreal Engine and Unity. However, despite these tools, a universal solution for effective AI visualization remains elusive, reflecting the unique strengths and limitations of each technique. We observed the application of VR for AI visualization across multiple domains, despite challenges such as high data complexity and cognitive load. Moreover, it briefly discusses the emerging ethical considerations pertaining to the broad integration of these technologies. Despite these challenges, the field shows significant potential, emphasizing the need for dedicated research efforts to unlock the full potential of these immersive technologies. This review, therefore, outlines a roadmap for future research, encouraging innovation in visualization techniques, addressing identified challenges, and considering the ethical implications of VR and AI convergence.

cs.HC↗

arXiv2023

Repositioning Tiered HotSpot Execution Performance Relative to the Interpreter

Although the advantages of just-in-time compilation over traditional interpretive execution are widely recognised, there needs to be more current research investigating and repositioning the performance differences between these two execution models relative to contemporary workloads. Specifically, there is a need to examine the performance differences between Java Runtime Environment (JRE) Java Virtual Machine (JVM) tiered execution and JRE JVM interpretive execution relative to modern multicore architectures and modern concurrent and parallel benchmark workloads. This article aims to fill this research gap by presenting the results of a study that compares the performance of these two execution models under load from the Renaissance Benchmark Suite. This research is relevant to anyone interested in understanding the performance differences between just-in-time compiled code and interpretive execution. It provides a contemporary assessment of the interpretive JVM core, the entry and starting point for bytecode execution, relative to just-in-time tiered execution. The study considers factors such as the JRE version, the GNU GCC version used in the JRE build toolchain, and the garbage collector algorithm specified at runtime, and their impact on the performance difference envelope between interpretive and tiered execution. Our findings indicate that tiered execution is considerably more efficient than interpretive execution, and the performance gap has increased, ranging from 4 to 37 times more efficient. On average, tiered execution is approximately 15 times more efficient than interpretive execution. Additionally, the performance differences between interpretive and tiered execution are influenced by workload category, with narrower performance differences observed for web-based workloads and more significant differences for Functional and Scala-type workloads.

cs.PL↗

arXiv2022

Building Specifications in the Event-B Institution

This paper describes a formal semantics for the Event-B specification language using the theory of institutions. We define an institution for Event-B, EVT, and prove that it meets the validity requirements for satisfaction preservation and model amalgamation. We also present a series of functions that show how the constructs of the Event-B specification language can be mapped into our institution. Our semantics sheds new light on the structure of the Event-B language, allowing us to clearly delineate three constituent sub-languages: the superstructure, infrastructure and mathematical languages. One of the principal goals of our semantics is to provide access to the generic modularisation constructs available in institutions, including specification-building operators for parameterisation and refinement. We demonstrate how these features subsume and enhance the corresponding features already present in Event-B through a detailed study of their use in a worked example. We have implemented our approach via a parser and translator for Event-B specifications, EBtoEVT, which also provides a gateway to the Hets toolkit for heterogeneous specification.

cs.LO↗

arXiv2022

Modelling the Turtle Python library in CSP

Software verification is an important tool in establishing the reliability of critical systems. One potential area of application is in the field of robotics, as robots take on more tasks in both day-to-day areas and highly specialised domains. Robots are usually given a plan to follow, if there are errors in this plan the robot will not perform reliably. The capability to check plans for errors in advance could prevent this. Python is a popular programming language in the robotics domain, through the use of the Robot Operating System (ROS) and various other libraries. Python's Turtle package provides a mobile agent, which we formally model here using Communicating Sequential Processes (CSP). Our interactive toolchain CSP2Turtle with CSP model and Python components, enables Turtle plans to be verified in CSP before being executed in Python. This means that certain classes of errors can be avoided, and provides a starting point for more detailed verification of Turtle programs and more complex robotic systems. We illustrate our approach with examples of robot navigation and obstacle avoidance in a 2D grid-world.

cs.RO↗