Evgeny Alexandrovich Cherkashin

This article presents a description of scientific discourse in the context of human-AI technology interactions, highlighting the challenge of creating high-quality scientific products in the modern digital environment. It proposes a model of the discursive space of scientific text - an article - organized using artificial intelligence technology - Large Language Models (LMMs) configured using prompts and contexts. The structure of the article’s discursive space organization model using prompt strategies consists of strategic, tactical, and editorial levels, where a continuous series of speech acts is realized, organized according to three principles (progressive clarification, co-authorship and feedback, contextual continuity). At these levels, the meta-design of the discursive space, the construction of its elements, and the integration and harmonization of the discursive space occur. The proposed model views article writing as the purposeful design and filling of a discursive space, where prompt strategies form the instrumental basis for its design. The purposeful and structured creation of a text relies on a sequence of controlled, managed, and iterative steps. The model helps prevent logical and structural errors. The proposed model is universal and adaptive. Its e ectiveness is confirmed by a significant reduction in the time required to process scientific texts without losing the original intent and by the high-quality volume of the resulting results. The scientific novelty of the study lies in the synthesis of the theory of discursive space and speech act theory with the practice of prompt engineering, resulting in the first-of-itskind structured model for organizing the discursive space of a scientific article for human-artificial intelligence interaction.

The article presents an innovative methodology for applying Semantic Web technologies to support fundamental geological research. The problem of semantic i

The article presents an innovative methodology for applying Semantic Web technologies to support fundamental geological research. The problem of semantic integration of heterogeneous geological data, characterized by different scales and interdisciplinarity, is considered. A five-stage methodology is developed, including domain analysis, ontological conceptual modeling, data transformation into a knowledge graph, deployment of a distributed data access infrastructure based on the conceptual model, and integration with processing and analysis procedures. Practical testing was conducted on three case studies: analysis of geochemical data for assessing territory pollution levels, creation of an information system about faults, and research on reservoir shoreline dynamics. The proposed ontological approach ensures compliance with FAIR principles and overcoming the "semantic barrier" in geological research. It is shown that Semantic Web technologies enable a transition from fragmented information arrays to a holistic semantic space of geological knowledge, opening new opportunities for generating comprehensive scientific hypotheses and cross-disciplinary research.

Introduction: A well-known limitation of Machine Learning (ML) approaches is the inability to automatically interpret their results as a clear data transformation procedure. This opacity arises because a neural network, for instance, is essentially a set of coefficients that model the synapses and structures connecting artificial neurons. Methods: The proposed solution involves constructing a hierarchical system of pattern recogni-tion models. The lower level processes the outcomes of recognition and classification performed by ML methods or algorithmic procedures. The middle levels represent the static aspect of a sce-ne, captured through object properties and logical connections, which are expressed as syntactic patterns. The higher levels describe an information flow of events derived from the low-level model data. Results: We propose the application of the logical language Logtalk for constructing syntactic Pattern Recognition (PR) models and for transformational interpretation. Two use cases are pre-sented: 1) the automatic generation of Java source code for objects representing modules of a Big Data analysis library, and 2) the recognition of PDF structure in documents generated according to a common template. Discussion: A technique is proposed to justify the correctness of ML results by evaluating their correspondence to a structure with predefined relations. This is achieved by utilizing these results within a first-order logic inference procedure of an applied theory. A successful inference indi-cates that the ML results are consistent with the logical theory, thereby providing a higher degree of confidence in their accuracy. The integration of syntactic PR with neural networks and analysis techniques based on large linguistic models allows for the automated validation of results against the possibility of such logical inference. Conclusion: This technique enables software developers to utilize ML results as input data for syntactic pattern recognition, thereby facilitating the description of dynamic processes. Signifi-cant emphasis is placed on modeling the interpretation of recognition results as a transformation of an information model.

Задача исследования состоит в создании технологии синтаксического анализа предложений русского языка при помощи обработки морфологических данных слов из корпуса языка АОТ, функций-предикатов распознавания соответствия слов по грамматическим (синтаксическим) правилам, управляемого эвристическим переборным алгоритмом, реализованным на компилируемом функциональном языке программирования Haskell

The paper presents an approach to solve the problem of reducing complexity of representing hierarchical control systems of autonomous underwater vehicles (AUV), their models and interaction with external objects, as well as hardware in the form of information objects. For this purpose, a specialized environment for research is being developed, including a conceptual model of the subject area in the form of a formalized ontology, a domain specific language (DSL), a translator from this language, a system for transforming the obtained structures into software objects and data objects of other programming systems, thus providing the upper level of the software management.

A description of the calculus of positively constructed formulas (PCF) and prover based on this calculus is considered. The PCF calculus has been developed by Russian scientists S.N. Vassiliev and A.K. Zherlov by an evolutionary way in describing and solving control theory problems. This calculus has features, which are applicable in control theory. The described implementation of the prover uses several techniques and strategies to improve prover performance. The prover is being tested by means of solving problems from TPTP library. The usage of implemented inference search strategies is also commented in this paper.