26 papers · ranked by Valyu relevance
Paul Brunet
The formal analysis of automated systems is an important and growing industry. This activity routinely requires new verification frameworks to be developed to tackle new programming features, or new considerations (bugs of interest). Often, one particular property can prove frustrating to establish: completeness of the…
Stephen M. Watt
Large required courses in theoretical computer science face two related challenges: helping students engage with abstract material and supporting reliable student assessment at scale. This paper describes LogicLab, a lightweight computational toolkit developed for CS 245, Logic and Computation, at the University of…
Feihao Fang, My T. Thai, Yuanyuan Lei
Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a symbolic solver as an external module. In this work, we instead ask whether LLMs contain a shared internal logical subspace that simultaneously…
Lars Vogt
This manuscript introduces the Semantic Units Framework, a technology-agnostic representational approach to semantic modularization in which statements and compound meaning structures are treated as first-class semantic units with explicit boundaries, identity, and epistemic status. Motivated by recurring limitations…
Pedro Domingos
Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which was never intended for AI. Their lack of support for automated reasoning and…
Reto Gubelmann
Taking Leibniz' ideal of a universal truth-calculating machine as a vantage point, this article provides a philosophically sound analysis of the concept of reasoning in NLP. It argues that reasoning always involves inference, which in turn requires being guided by reason relations. Based on this, the article argues…
Christoph Benzmüller, Daniel Kirchner, Luca Pasetto
This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line of research that expanded into a range of logic embeddings in HOL and inspired the LogiKEy logic-pluralistic knowledge representation and reasoning methodology. This…
Yuxiang Yao, Dong Liu, Zheting Zhang, Chengchen Zhao + 1 more
Complex biosystems exhibit ordered, functional, self-organized features, yet a universal framework for exploring their logical paradigms and dynamic behaviors remains lacking. Here we present BioLogical, a user-friendly R package designed to analyze logical properties of gene regulatory systems. Through a standard…
Adam Pease, Richard Thompson
Human language is often vague and ambiguous. There have been many efforts to create formal languages and many attempts to translate human language into formal languages. Logic has a great deal of flexibility, not least in how the symbols used are defined. We anchor lexical elements in a formal ontology, which helps…
Luna Xingyu Li, Yue Zhang, Boris Aguilar, Tazein Shah + 2 more
Logical gene regulatory network (GRN) models provide interpretable, mechanistic representations of cellular regulation and are widely used in systems biology. However, most existing models remain incomplete, context-specific, and difficult to extend to comprehensive GRNs, limiting their broader applicability to tasks…
Lun Ai, Stephen H. Muggleton, Shi-Shun Liang, Geoff S. Baldwin
Reasoning about hypotheses and updating knowledge through empirical observations are central to scientific discovery. In this work, we applied logic-based machine learning methods to drive biological discovery by guiding experimentation. Genome-scale metabolic network models (GEMs) - comprehensive representations of…
Lei Cao, Yuntain Li, Hua Qin, Yanbang Shang + 13 more
While AI has automated bioinformatic workflows, biological interpretation remains fragmented and often disconnected from mechanistic insights. Existing AI is bifurcated between statistical “black-box” models that lack logical grounding and simple agents restricted to shallow knowledge retrieval. To bridge this divide…
Karthika Veeramani, Allen Joseph N, Pavithran M
Automating tax calculations and optimisation is challenging because modern AI systems such as large language models operate probabilistically, while legal and financial reasoning requires deterministic compliance with statutory rules. This research presents a new approach to automate taxes in India through the…
Luna Xingyu Li, Carissa Bleker, Sylvain Soliman, Laurence Calzone + 13 more
Logical models are widely used to study regulatory and signaling systems, yet their reuse, annotation, and exchange across tools remain challenging. Although SBML Level 3 Qualitative Models (SBML-qual) provides a standard representation, its XML-based syntax is difficult to inspect and edit directly. Here we introduce…
Anh Phong Tran, Dhruv D. Jatkar, M. Ali Al-Radhawi, Elizabeth A. Ernst + 1 more
Minimal synthesis of Boolean functions is an NP-hard problem, and heuristic approaches typically give suboptimal circuits. However, in the emergent field of synthetic biology, genetic logic designs that use even a single additional Boolean gate can render a circuit unimplementable in a cell. This has led to a renewed…
Alexandra Sarafoglou, Anne S.F. Giacobello, Henrik R. Godmann, Tamar Johnson + 3 more
Researchers have begun using Bayesian hierarchical modeling to study semantic representations, for instance, in the context of natural language quantifiers such as most, few, and more than half. Building on previous work, we propose a Bayesian hierarchical model to disentangle three key semantic parameters: the meaning…
Ben Baker, Richard D. Lange, Andrew Richmond, Nikolaus Kriegeskorte + 3 more
Representations play a central role in the study of both biological and artificial intelligence, as well as philosophy of mind. Across neuroscience, computer science, and philosophy, a recurring theme is that representations not only carry information but should be ``useful'' for or ``usable'' by an agent in some…
Authors not listed
Traditional electron-configuration notation (e.g. 1s^2 2s^2 2p^6) compresses multi-electron quantum information into integer occupancies that convey allowed maxima and most-probable arrangements but obscure the underlying probabilistic distribution and the spread of possible measurement outcomes. We present a…
Authors not listed
Machine learning is increasingly used to predict reaction properties such as barrier heights, reaction energies, rates, or yields, as well as the underlying molecular geometries, including transition state structures. While such predictions have the potential to provide mechanistic insight for high-impact applications…
Vincent P. Ferrera, Samuel Lippl, Kenneth Kay, Fabian Munoz + 3 more
Transitive inference (TI) is the ability to reason about transitive relationships in an ordered set of items (e.g., if A>B and B>C, then A>C). TI is widely held to depend on a linear representation of the serial (rank) order of those items. By what computational mechanism is such an ordering constructed during…
Authors not listed
Modeling of chemical reactions is essential for understanding kinetic mechanisms and predicting possible outcomes of reacting systems. Quantum mechanical calculations are accurate but often prohibitively expensive. Deep learning has emerged as a faster alternative, but progress is slowed by a fragmented software…
Authors not listed
Computational methods for predictive modeling have been increasingly utilized in the early stages of drug discovery to supplement high-throughput screening. The advent of highly efficient and complex machine learning architectures necessitates new methods of collating the plethora of topological, geometrical, and…
Hanlin Zhu, Assia Chericoni, Taha Ismail, Elizabeth A. Mickiewicz + 17 more
Humans handle numbers nimbly, suggesting a richer neural manifold structure than the prevalent mental number line model. In populations of medial temporal lobe (MTL) neurons in humans performing two simple tasks (dot counting and arithmetic), we find robust neural coding of numerosity that results in high dimensional…
Sebastijan Veselic, Nour Mohsen, Lennart Luettgau, Elena Gutierrez + 5 more
Reasoning flexibly composes known elements to solve novel problems. Recent theories suggest the brain uses the axis of time to compose elements for reasoning. In this view, elements are packaged into fast neural sequences, with each sequence exploring the implications of a different composition. Using…
Authors not listed
Conventional molecular graphs often are unable to reliably encode stereochemistry, especially for symmetric molecules, non-tetrahedral centers, and transition states. To overcome this, we present StereoMolGraph, an open source Python library implementing a stereochemistry-aware graph representation for molecules and…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…