• Main Navigation
  • Main Content
  • Sidebar

Russian Digital Libraries Journal

  • Home
  • About
    • About the Journal
    • Aims and Scopes
    • Themes
    • Editor-in-Chief
    • Editorial Team
    • Submissions
    • Open Access Statement
    • Privacy Statement
    • Contact
  • Current
  • Archives
  • Register
  • Login
  • Search
Published since 1998
ISSN 1562-5419
16+
Language
  • Русский
  • English

Search

Advanced filters

Search Results

An Ontology-Based Approach for Distributed Multi-Agent Modeling of the Radio-Technical Systems

Andrey Olegovich Schiriy
1109-1125
Abstract:

he ontology-based approach to multi-agent modeling involves the implementation of a modeling system through the creation of ontologies. An example of a holistic implementation of an ontology-based approach to agent-based modeling is the IEEE 1516 Standard for Modeling and Simulation High Level Architecture. The work is devoted to a multi-agent modeling system designed for modeling complex radio engineering systems (especially radar systems), its relevance is due to the need to replace part of the field tests of radio engineering systems with simulation experiments. The motivation for switching to the IEEE 1516 standard for a "heavy" multi-agent modeling system, among other things, is to ensure scalability, openness and multiple reuse of the developed agent models, which is completely logical to do based on the existing well-developed and proven standard that establishes rules for the interaction of models and the development of software interfaces. The general principles of construction and architecture of the modeling system are given. The basic requirements for the main modeling agents, their role and place in the complex modeling system are shown, a special place among which is occupied by the simulator of the background-target environment. The possibility of combining two simulation schemes is also discussed: discrete-event and step-by-step. The fact is that the step-by-step scheme has advantages such as simplicity and clarity, it is convenient to model processing algorithms, components of radio engineering systems. However, it is impossible to implement true autonomy and asynchrony of agents in it. Combining two modeling schemes allows you to combine their advantages.

Keywords: multi-agent modeling, simulation, discrete event modeling, ontologies, radio-technical systems, over-the-horizon radars.

Vit Quantization: CPU-Centric Analysis of the Trade-Off between Size and Speed

Amir Ramisovich Nigmatullin, Rustam Arifovich Lukmanov, Ahmad Taha
262-286
Abstract:

Using Vision Transformer (ViT) models in real medical practice – for example, in hospitals or diagnostic centers – is often difficult because doctors' work computers usually do not have powerful graphics processors (GPUs), and computing resources are limited. This work investigates a complete practical pipeline for model inference, aimed at reducing computational costs without significant loss of predictive performance.


The proposed approach combines several optimization techniques. First, knowledge distillation (KD) is used, where a compact student model learns to mimic the behavior of a larger, more accurate teacher model. Second, Exponential Moving Average (EMA) of the model weights is applied to stabilize training and improve generalization. Third, post-training INT8 quantization (PTQ) is explored to reduce model size and accelerate inference. Additionally, a simplified quantization-aware training variant (QAT-lite) is considered, where the effects of quantization are partially incorporated during fine-tuning.


Experiments are conducted on the ISIC dataset, which contains dermoscopic images of skin lesions. Model performance is evaluated using standard classification metrics, including accuracy, macro-averaged F1 score, and area under the ROC curve (ROC-AUC). CPU performance is also analyzed, including inference latency, throughput, memory consumption, and the final model size.


The results show that post-training INT8 quantization preserves performance close to the FP32 baseline while substantially reducing memory and computational requirements. In contrast, QAT-lite does not consistently provide reproducible improvements over PTQ.

Keywords: Vision Transformer, knowledge distillation, EMA, post-training quantization, quantization-aware training.

LLM Applications to the task of Word Sense Disambiguation in Russian texts

Polina Andreevna Gousyatskaya, Natalia Valentinovna Loukachevitch
1118-1132
Abstract:

This study is dedicated to experiments in Word Sense Disambiguation on Russian-language material using generative (decoder-only) models of small and medium size. While the direct application of generative models is not an optimal approach for this task, such models demonstrate potential as semantic annotators of large volumes of raw data. The automation of semantic text annotation using generative models may help overcome the bottleneck of insufficient labeled data for training encoder-based models.


Previous studies show that state-of-the-art English and multilingual models can achieve accuracy above 90% on this task, while smaller models typically reach 80%+. The present study aims to determine whether a comparable task can be successfully addressed for small- and medium-scale models adapted to Russian, that do not require substantial computational resources.


The experiments reported in this paper are conducted both in a basic setting (one/few-shot prompting) with separate tests for narrow and broad context windows of the ambiguous lexeme, as well as under several modifications, such as context enrichment with paradigmatic information (e.g., hypernyms, hyponyms, domain labels of the target word) and ensemble approaches in which one model validates and refines the predictions of another. The study is based on the Russian annotated resource RuSemCor, annotated in terms of the RuWordNet semantic net.


The experiments ultimately pursue the development of an efficient and accessible pipeline for automatic semantic annotation of Russian texts, useful both for direct application and for preparing annotated data for machinelearning tasks.

Keywords: word sense disambiguation, LLM, computational semantics, classification.

PromptAlign: Automatic Iterative Alignment of a Large Language Model to Expert Annotations without Fine-Tuning

Alexander Alekseevich Agathonov, Akhat Rustemovich Khusainov, Nikolai Arkadievich Prokopyev
2265-2292
Abstract:

Large language models are increasingly used in social and psychological sciences; however, their predictions are systematically biased relative to expert annotations (alignment shift), and attempts to manually refine instructions or to supply examples lead to a “blanket-pulling” effect – degradation of minority classes.


We propose PromptAlign, an automatic prompt-optimization pipeline that requires neither access to model weights nor human involvement in iterative correction, because the taxonomy and the feature space are specified by an expert a priori. The pipeline extracts hybrid linguistic and semantic features using the large language model itself, builds interpretable L1-regularized logistic regressions to localize disagreements with the expert, performs a meta-analysis of errors, and compiles new prompts while controlling the class balance through a class-imbalance index (Blanket Pulling Index, BPI). An experiment on a corpus of 541 Russian-language texts with three psychological classes showed an increase in macro-F1 on the held-out test set from 0.655 to 0.749 and in the minimum per-class F1 from 0.449 to 0.656 (p>0.99 by a paired bootstrap test). The method significantly outperforms both the zero-shot baseline and few-shot prompting. A component-contribution analysis confirms the critical role of semantic interpretation of features and of periodic prompt rebuilding. The final prompt contains five rules that reflect latent expert criteria; unlike the “black boxes” produced by automatic optimizers, these rules are available for inspection and correction by a specialist.

Keywords: large language model, prompt optimization, alignment, interpretability, L1 regularization, bootstrap test, text classification, psychological annotation, surrogate model, class imbalance index, Russian-language corpus.

Integration of Semantic and Mathematical Modeling for the Analysis of Energy Security Problems

Alexey Genadevich Massel, Timur Gabilovich Mamedov
842-859
Abstract:

The study addresses the problem of integrating cognitive and mathematical modeling in research on the development directions of the fuel and energy complex, taking into account energy security requirements. The relevance of the work is due to the fact that in the existing two-level research methodology, the transition from the results of qualitative analysis using cognitive modeling to the parameters of the mathematical model is largely performed manually, which reduces the reproducibility of numerical experiments and limits the efficiency of accumulated knowledge usage. The aim of the work is to develop a software component that ensures the combined use of cognitive and mathematical models within an Energy Knowledge Ecosystem. A software component is proposed, implemented as part of the INTEC‑SAW suite, which provides the transformation of changes in the cognitive model into the parameters of the economic-mathematical model, as well as the reverse interpretation of calculation results. Technology for conducting numerical experiments has been developed, including the construction of semantic (ontological and cognitive) models, formation of computational scenarios, execution of optimization calculations, and presentation of results, distinguished by the automation of the joint use of ontological, cognitive, and economic-mathematical models. To account for uncertainty, a numerical method of stochastic parameter adjustment based on cognitive weights is proposed. The effectiveness of the approach is demonstrated through a numerical experiment investigating the impact of CO₂ emission constraints on the energy balances of the Siberian Federal District. The practical significance of the work lies in increasing the validity and reproducibility of research on the development of the fuel and energy complex through the coordinated use of qualitative and quantitative analysis tools.

Keywords: energy complex, energy security, cognitive modeling, ontologies, computational experiment, linear programming.

Constrained Decoding for Structural Error Suppression in Dependency Tree Generation with Large Language Models

Elena Denisovna Shamaeva
1269-1292
Abstract:

In the field of syntactic parsing, fine-tuning large language models to generate a sentence's syntactic structure in bracket form is a promising approach. Existing fine-tuned models demonstrate high values of syntax parsing metrics; however, in some cases they generate an incorrect bracket sequence (for example, with an unbalanced number of opening and closing parentheses). Therefore, this study aims to develop a method to reduce the number of incorrectly generated sequences. A system of constraints has been introduced on the set of tokens generated at each stage of the large language model. The implemented method was tested on four fine-tuned models (adapted and non-adapted with 4 and 8 billion parameters) on the SynTagRus dependency tree dataset. For all models, the number of incorrectly generated sequences decreased. However, some sentences were not parsed, because the LLMs generated an excessively long token sequence and were interrupted. The code for this study is publicly available.

Keywords: dependency parsing, large language model, fine-tuning, generation constraing, natural language processing.

Educational analytics and adaptive training using student model in the intellectual learning systems

Михаил Владиславович Каяшев, Денис Юрьевич Макаров, Антон Александрович Марченко
181-192
Abstract:

For support of adaptive training and educational analytics in the intellectual learning systems, it is necessary to collect, process data on progress of the student and his various individual characteristics. It can be realized by means of the student model. The analysis of approaches to modeling of the student has shown that application of several types of models is an optimal solution, considering requirements to the learning system. Three approaches were chosen and united into one model: overlay, Bayesian network, error model. Use of overlay model allows to build individual trajectories of student training. Bayesian networks realize competence-based approach in training. The model of mistakes keeps track of wrong knowledge of the student and helps the student to correct them at early stages. The student model uniting in itself these approaches is more suitable for realization of the personalized training, allows to keep track of progress of the student according to various characteristics and also gives the chance to easily submit the card of subjects, knowledge, competence of the student of various areas in the form of the count that is quite convenient and clear representation.

Keywords: intellectual learning system, student model, competence, adaptive training, educational analytics, overlay model, Bayesian network, domain model.

An Innovative Approach to the Design of Integrated Tasks in Computer Modeling Training

Olga Aleksandrovna Shirokova, Tatyana Yurievna Gainutdinova
378-393
Abstract:

The article discusses the possible use of LMS Moodle in the development of the course “The use of computer modeling in education”. The course is based on the introduction of interdisciplinary integration of higher mathematics, computer modeling, programming into the educational process and involves the use of computer mathematics systems and software environments. Examples of specific integrated tasks are presented.


When designing the training course “Using Computer Simulation in Education” in LMS Moodle, the following set of elements was used: “lecture”, “task”, “test”, “forum”, “resource”, “wiki”, “chat”, “glossary”.


The use of the methodology for compiling integrated tasks based on LMS Moodle showed that: integrated tasks using information technology help to increase the level of mastering the material of complex sections of higher mathematics; the content of the course of higher mathematics is the fundamental basis of the material studied in the proposed course, and contributes to a deep understanding of mathematical disciplines; integrated design tasks form practical skills and abilities of computer modeling using programming in various software environments.

Keywords: integrated tasks, higher mathematics, computer modeling, programming, LMS Moodle, computer mathematics systems.

Stability Studies of a Coupled Model to Perturbation of Initial Data

Konstantin Pavlovich Belyaev, Gury Mikhaylovich Mikhaylov, Alexey Nikolaevich Salnikov, Natalia Pavlovna Tuchkova
615-633
Abstract: The stability problem is considered in terms of the classical Lyapunov definition. For this, a set of initial conditions is set, consisting of their preliminary calculations, and the spread of the trajectories obtained as a result of numerical simulation is analyzed. This procedure is implemented as a series of ensemble experiments with a joint MPI-ESM model of the Institute of Meteorology M. Planck (Germany). For numerical modeling, a series of different initial values of the characteristic fields was specified and the model was integrated, starting from each of these fields for different time periods. Extreme ocean level characteristics over a period of 30 years were studied. The statistical distribution was built, the parameters of this distribution were estimated, and the statistical forecast for 5 years in advance was studied. It is shown that the statistical forecast of the level corresponds to the calculated forecast obtained by the model. The localization of extreme level values was studied and an analysis of these results was carried out. Numerical calculations were performed on the Lomonosov-2 supercomputer of Lomonosov Moscow State University.
Keywords: non-linear circulation models, Ensemble numerical experiments, analysis of stability of the model trajectories.

Situational Modeling Technology in Virtual Environment Systems

Mikhail Vasilievich Mikhailyuk, Dmitry Alekseevich Kononov, Dmitry Mikhailovich Loginov
889-901
Abstract:

The technology of modelling various situations in virtual environment systems, which are computer three-dimensional models of a real or artificial environment, is discussed. The user can view these scenes directly on the computer screen, wall screen, in a stereo glasses, virtual reality glasses, etc. He can also move inside a virtual scene and interact with its objects. In turn, the environment can also change. This allows modelling of various situations (situation modelling) in the virtual environment system. With such modelling, some static or dynamic situation is set in the virtual environment system in which the operator must perform the tasks assigned to him.


A mechanism for setting situations by changing a virtual three-dimensional scene using configuration files and virtual control panels is proposed. A special language has been developed for writing configuration files, and a special editor has been developed for creating virtual control panels. The approbation of the proposed methods is presented on the examples of two virtual scenes: a training ground for mobile robots and a jet backpack for the rescue of an astronaut in outer space.

Keywords: virtual environment system, situational modeling, three-dimensional scene, configuration file, virtual control panels.

Comparative Analysis of Geological Texts using Large Language Models

Michail Ivanovich Patuk, Vera Viktorovna Naumova
806-821
Abstract:

The rapid increase in the volume of publications in various fields of geology makes it crucial to introduce methods for automated processing of scientific texts. Large language models based on neural networks represent one of the most promising approaches to solving this challenge. The recent breakthroughs in artificial intelligence have made such models indispensable tools for researchers. Our work on semantic search for publications using additionally trained language models and measuring the similarity between geological texts yielded good results. However, the models we used were unable to perform in-depth text analysis. A comparative analysis of modern architectures identified the DeepSeek R1 model as belonging to a class of systems with advanced logical inference abilities. This type of model represents a fundamentally new level of quality in text generation. Based on the chosen model, we have developed a web service that provides unique functionality for comparative analysis of up to 5 scientific articles. The service supports multilingual sources, allowing users to input text in English, Chinese, Russian, etc. It generates structured reports in Russian, highlighting key theses, contradictions, and patterns. The proposed approach has been tested on geological publications, and the results have been promising.

Keywords: artificial intelligence, large language models, natural language processing, texts analysis, geology.

Behavioral Cloning Across Game Variants: Domain Adaptation and Player Personalization in Chess960

Timur Ruselevich Arslanov
1483-1494
Abstract:

Behavioral cloning allows creating models capable of making decisions in the same way humans do. Although various models successfully predict human actions in games, their ability to imitate individual players decreases when game variants change. In this work, we explore domain adaptation and personalization strategies using Fischer Random Chess with random piece placement. Using the Maia chess model presented by Tang et al., we tested several fine-tuning strategies. The results revealed three key patterns: old player records have no impact; each new record is highly effective; domain adaptation and personalization complement each other - their combination yields the best result.

Keywords: games, artificial intelligence, player modeling, behavioral cloning, chess.

Detection of Hallucinations Based on the Internal States of Large Language Models

Timur Rustemovich Aisin, Tatiana Vyacheslavovna Shamardina
1282-1305
Abstract:

In recent years, large language models (LLMs) have achieved substantial progress in natural language processing tasks and have become key instruments for addressing a wide range of applied and research problems. However, as their scale and capabilities grow, the issue of hallucinations — i.e., the generation of false, unreliable, or nonexistent information presented in a credible manner—has become increasingly acute. Consequently, analyzing the nature of hallucinations and developing methods for their detection has acquired both scientific and practical significance.


This study examines the phenomenon of hallucinations in large language models, reviews their existing classification, and investigates potential causes. Using the Flan-T5 model, we analyze differences in the model’s internal states when generating hallucinations versus correct responses. Based on these discrepancies, we propose two approaches for hallucination detection: one leveraging attention maps and the other utilizing the model’s hidden states. These methods are evaluated on data from HaluEval and Shroom 2024 benchmarks in tasks such as summarization, question answering, paraphrasing, machine translation, and definition generation. Additionally, we assess the transferability of the trained detectors across different hallucination types, in order to evaluate the robustness of the proposed methods.

Keywords: large language models, hallucinations, detection, Flan-T5, natural language processing, attention maps, hidden states, HaluEval, Shroom.

Digital Modeling for Scoping Review in Studying Intergenerational Cultural Congruence

Aisylu Munavirovna Ganieva
1057-1069
Abstract:

The aim of the work is to identify key topics in modern psychological research of cultural congruence using the method of thematic digital modeling of an array of scientific publications.


The modernity and significance of the conducted research is due to the growing importance of cultural congruence in the context of the digital transformation of society, which is changing the ways of socialization and interaction. Modern technologies require rethinking the psychological mechanisms of individual adaptation to the cultural environment, especially in childhood and adolescence. Despite the active study of this phenomenon, there is a noticeable shortage of research on the cultural congruence of adults. The use of digital modeling and artificial intelligence allows us to systematize knowledge and identify the structure of the thematic field with high accuracy. The obtained data opens up the prospect for further study of cultural congruence throughout the entire life cycle.


The thematic field review of cultural congruence research was conducted based on an analysis of digital archives comprising a curated collection of 112 scholarly publications on the topic. The review employed a topic modeling algorithm implemented in the Python programming language and leveraged digital platforms incorporating multimodal neural network–based tools (GigaChat, Qwen, DeepSeek). The data analysis yielded four distinct age groups that reflect the developmental specificity of cultural congruence manifestations: preschoolers, primary school–age children, adolescents, and adults.

Keywords: cultural congruence, psychological research, developmental psychology, topic modeling, scoping review.

The low level implementation of the noradrenaline pathways of spiking neural network

Юлия Сергеевна Сафандеева, Максим Олегович Таланов
251-286
Abstract: We propose to re-implement basic emotions described by Silvian Tomkins via "Cube of emotions" of Hugo Lövheim, and spiking NNs. We use the basic mechanism of noradrenaline neuromodulation and map it to the influence over computational processes in modern computers. We implement noradrenaline pathways via neuro-biological simulator NEST.
Keywords: NEST, Lövheim, nor-adrenaline, NeuCogAR.

On the Synonym Search Model

Olga Muratovna Ataeva, Vladimir Alekseevich Serebriakov, Natalia Pavlovna Tuchkova
1006-1022
Abstract:

The problem of finding the most relevant documents as a result of an extended and refined query is considered. For this, a search model and a text preprocessing mechanism are proposed, as well as the joint use of a search engine and a neural network model built on the basis of an index using word2vec algorithms to generate an extended query with synonyms and refine search results based on a selection of similar documents in a digital semantic library. The paper investigates the construction of a vector representation of documents based on paragraphs in relation to the data array of the digital semantic library LibMeta. Each piece of text is labeled. Both the whole document and its separate parts can be marked. The problem of enriching user queries with synonyms was solved, then when building a search model together with word2vec algorithms, an approach of "indexing first, then training" was used to cover more information and give more accurate search results. The model was trained on the basis of the library's mathematical content. Examples of training, extended query and search quality assessment using training and synonyms are given.

Keywords: search model, word2vec algorithm, synonyms, information query, query extension.

Representation of Intraword Syntagmatic Relations in Vector Language Models

Daria Kirillovna Rodionova, Olga Aleksandrovna Mitrofanova
898-918
Abstract:

The paper discusses semantic structure representation of derivatives in language models, taking into account the intraword syntagmatic relations between derivational morphemes. Experiments were conducted using morphemic models developed by the Russian National Corpus (RNC), as well as fastText and ruRoBERTa models. The study is aimed at the verification of the hypothesis dealing with compositionality of derived words which are represented as aggregated morpheme vectors. In experiments we explore the representation of semantic relationships using fastText morpheme vectors and standard subword vectors in ruRoBERTa. The results indicate moderate sensitivity of fastText vectors to syntagmatic relations between morphemes as well as to derivational types. At the same time, it was found that aggregating morpheme vectors in fastText provides better representation of semantic relations between words compared to aggregating subword vectors in ruRoBERTa.


Standard BPE (Byte-Pair Encoding) and WordPiece tokenizers used in Transformer-based models are poorly interpretable with respect to linguistic data, as word segments do not always correspond to morphemes. The research problem lies in the need to assess the extent to which modern language models can capture linguistic features that characterize the relationships of derived words within word-formation families. The aim of the study is to evaluate the ability of predictive distributed vector embedding models to reproduce syntagmatic connections between morphemes within derived words and at the level of word-formation families in the Russian language.


The obtained results encourage the development of neural network architectures that take into account syntagmatic relations between morphemes, the improvement of morpheme tokenizers, and their integration into language models.

Keywords: language models, morphemic analysis, word-formation methods, compositionality.

Visual Modeling of Game Mechanics in Tula: Temporal and Probabilistic Aspects

Vlada Vladimirovna Kugurakova, Vsevolod Tarasovich trofimchuk
1557-1584
Abstract:

The paper addresses the problem of visual representation of temporal and probabilistic elements in formal modeling tools for game mechanics. An analysis of existing visual modeling systems – Machinations, Petri nets, UML state diagrams, and UPPAAL – reveals their key limitations in describing complex game scenarios. An approach to visualizing temporal operators and probabilistic constructs in the Tula tool developed by the authors is proposed. A set of visual primitives is described that ensures bidirectional correspondence between visual representation and formal specification in the gameplay specification language. Examples of visual modeling of typical game scenarios with time delays, conditional probabilities, and multiplayer interactions are given. The possibility of automatic transformation of visual models into formal specifications suitable for verification with PRISM and UPPAAL is demonstrated. A comparative analysis of the expressive capabilities of Tula and predecessor systems is conducted, showing that Tula is the only system among those considered that simultaneously provides formally verifiable semantics, built-in support for temporal operators (X, G, F, U), and arbitrary probability distributions, as well as a visual notation organized around resource flows and game events. The two-level specification principle with bidirectional transformation proposed in Tula closes the design–formalization–verification–correction loop, lowering the entry barrier to formal methods for practitioners without loss of verification completeness. This makes it possible to consider Tula as an intermediate layer between iterative game design and industrial verifiers.

Keywords: visual modeling, game mechanics, temporal operators, probabilistic models, formal verification, Tula, Machinations, Petri nets.

Common Digital Space of Scientific Knowlege Content Fragments Modeling

Svetlana Aleksandrovna Vlasova, Nikolay Evgenievich Kalenov, Alexander Nikolaevich Sotnikov
353-368
Abstract:

The article reflects the new results of research related to the formation of the Common Digital Space of Scientific Knowledge (CDSSK). This work has been carried out since 2019 in a number of academic organizations, including the Interdepartmental Supercomputer Center of the Russian Academy of Sciences (now the Department of Supercomputer Systems and Parallel Computing at the National Research Center "Kurchatov Institute"). As part of these studies, the structure of the CDSSK ontology, a language for its description, and a number of unified software tools have been developed to ensure the formation of the ontology of individual subspaces and the input of various types and kinds of object attributes and named relationships into the CDSSK. Currently, the formation of the CDSSK content is being modeled using the example of a universal and a number of thematic subspaces. The results of this modeling are presented below. The attributes and relationships of the "Administrative Units" class objects belonging to the "Geography" subspace, the "Organizations and Their Subdivisions" class, and the "Classification Systems" class belonging to the universal subspace are presented. The ability to navigate through the loaded real resources is demonstrated.

Keywords: scientific knowledge space, ontology, named relationships, data loading, Russian administrative units, city coats of arms.

Application of Supercomputer Technologies for Long-Term Modeling of Permafrost Boundaries in the Oil and Gas Fields of the Arctic

Mikhail Yurievich Filimonov, Nataliia Anatolyevna Vaganova, Elena Nikolaevna Akimova, Vladimir Evgenevich Misilov
848-865
Abstract: A model of propagation of thermal fields in permafrost from various engineering objects operating in Arctic regions is considered. The proposed model includes the most significant technical and climatic parameters affecting the formation of thermal fields in the surface layer of the soil. The main objective of the study is a long-term forecasting of changes in the dynamics of permafrost boundaries during operation of cluster sites of northern oil and gas fields. Such a forecast is obtained by simulation of complex system consisting of heat or cold sources and frozen soil, thawing of which can lead to the loss of the bearing capacity and possible technogenic and environmental accidents. For example, the sources of heat can be production wells, and the sources of cold can be seasonal cooling devices that are used to stabilize the soil. To minimize the impact of heat sources on permafrost, various options for thermal insulation are used, and to preserve the original temperature regime of the top layer of soil, riprap materials consisting of sand, concrete, foam concrete, or other heat insulating material are used. The developed set of programs was used in the design of 12 northern oil and gas fields. To solve the described problem in a complex three-dimensional area, substantial computational resources are required. The computing time of one variant can often exceed 10–20 hours of machine time on a supercomputer. To speed up the numerical calculations, multi-core processors are used. Numerical calculations illustrate the possibility of a developed set of programs for making long-term forecasts for determining changes in the boundaries of the permafrost zones, and show that on multi-core processors it is possible to achieve acceleration close to the theoretical one.
Keywords: computer software, heat and mass transfer, cryolithozone, simulation, parallel computing, Stefan problem, OpenMP.

Straightening the Trajectory From Algebraic Models and Computer Modeling in Additional Construction

Henrietta Petrova, Petr Sovertkov
119-127
Abstract: Рresents educational and research building model trajectory.
Keywords: Keywords: algebraic model, computer simulation, an additional building, digital education.

Software for forest fire simulation with respect to weather and environmental conditions

Арслан Альфирович Гиниятов, Влада Владимировна Кугуракова, Ринат Султанович Якушев
180-192
Abstract: Prediction of forest fire dynamics is no easy task, requiring thoughtful examination of many factors involved, such as landscape, vegetation, climate and weather conditions, humidity, urbanization of land, and many others. One of the best approaches to this problem is a computer simulation. In this paper, we describe the thought process and the development of a forest fire simulator that means to address all of those difficulties.
Keywords: 3D, virtual reality, virtual simulation, forest fire simulation.

LLM Confidence in Constructing Semantic Classifications of Arguments

Daniil Sergeevich Larionov, Elena Nikolaevna Nikitina, Ivan Valentinovich Smirnov
1155-1173
Abstract:

This article addresses the problem of quantifying the confidence of large language models (LLMs) in the automatic semantic classification of arguments with emotive predicates. Using Russian-language social media posts, we analyze verbs of fear (to scare, to be afraid, etc.) and emotional attitude (to like, to love) with the semantic roles of experiencer, causator, and object. The study aims to compare self-assessed confidence of LLM Claude Sonnet 4.5 with expert assessments of the model's reasoning texts in argument classification in the healthcare domain. The experiment utilized a stratified set of 300 examples using chain-of-thoughts reasoning in Russian and four-step confidence scale. The results showed a moderate Spearman correlation between the expert and model assessments. A statistically significant relationship was found only between self-assessment of the model and the actual classification accuracy, while expert assessment of the linguistic characteristics of reasoning was unrelated to accuracy. It was concluded that explicit LLM reasoning is not directly related to its self-assessment of confidence and is separate from the decision-making process; reasoning may be an important functional part of the user interface, but not of the research.

Keywords: semantic roles, argument classification, verb of emotion, large language models, LLM reasoning, LLM confidence.

Development of simulational software of destruction by the floods with multifactors

Ляйсан Зиннуровна Римова, Влада Владимировна Кугуракова, Ринат Султанович Якушев
238-250
Abstract: Floods were and are continuing to be a great threat to human properties, farms, agriculture, and households. To reduce the flood-related damage, we have to be able to reliably predict the flood dynamics, and the best way to do this is a computer simulation. Such simulational software must take into consideration many factors, such as the landscape qualities, human infrastructure, protective buildings, and more. In this paper, we try to systematize all those factors and create the software that will adhere to those requirements.
Keywords: 3D, virtual reality, virtual simulation, flood, floodwaters.

Automatic Speech Recognition Quality Prediction based on Large Language Models

Anton Vyacheslavovich Polevoi
1189-1211
Abstract:

Despite the rapid development in the field of automatic speech recognition (ASR) systems, the recognition quality remains poor for audio recordings with acoustic degradation (music, crowd shouts, sounds of machinery, etc.). This becomes especially important when implementing models in critical areas that are characterized by increased attention to control and reliability of the results (aviation, medicine, autopilots, etc.). Error in such areas is very expensive and the use of models becomes impossible, even if the error occurs rarely. To reduce risks, it is advisable to evaluate the expected recognition quality in advance.


This article proposes an approach to predicting the Word Error Rate (WER) based on the acoustic characteristics of the signal and calculating the perplexity of language models. The proposed method involves the creation of diverse sets of audio data by applying various types of acoustic observations to pure speech samples at various levels of quality and intelligibility. Unlike previous studies, a complete set of speech features is extracted and analyzed: prediction of the value of the signal-to-noise ratio (SNR), neural network sound quality metrics (NISQA, etc.) as well as the perplexity of the text of the ASR hypothesis using the language model as an additional feature for training a unified model.


Experiments are being conducted using modern speech recognition architectures to demonstrate the effectiveness of the proposed method in predicting WER in various acoustic conditions. It is shown that the inclusion of perplexity significantly improves the quality of the WER prediction, in particular for data where acoustic features are weakly correlated with recognition errors. The results are applicable for automatic evaluation of the expected quality of speech recognition and filtering of audio inputs.

Keywords: WER prediction, acoustic degradation in speech recognition, perplexia, ASR confidence.
1 - 25 of 192 items 1 2 3 4 5 6 7 8 > >> 
Information
  • For Readers
  • For Authors
  • For Librarians
Make a Submission
Current Issue
  • Atom logo
  • RSS2 logo
  • RSS1 logo

Russian Digital Libraries Journal

ISSN 1562-5419

Information

  • About the Journal
  • Aims and Scopes
  • Themes
  • Author Guidelines
  • Submissions
  • Privacy Statement
  • Contact
  • eLIBRARY.RU
  • dblp computer science bibliography

Send a manuscript

Authors need to register with the journal prior to submitting or, if already registered, can simply log in and begin the five-step process.

Make a Submission
About this Publishing System

© 2015-2026 Kazan Federal University; Institute of the Information Society