We analyzed 133 linguistic features for automated proficiency classification under the Common European Framework of Reference (CEFR) in a two-tier architecture: deterministic Tier 1 (lexical, morphological, and syntactic measures) and machine-learning-based Tier 2 (semantic coherence, topic structure, cohesion, and error-analysis signals). Experiments were conducted on a corpus of 3,205 learner texts from mixed sources, with triangulated validation against expert-verified Cambridge examination subsets. The materials were collected in 2022--2025 and included a substantial institutional corpus of over 3,000 essays and other writing texts produced by students of Moscow Institute of Physics and Technology (MIPT) studying English as a foreign language and regularly assessed by our AI-powered testing system ISTOK (Intelligent System for Testing General Language Competencies). Feature matrices were standardized after missing-value handling (fold-local median imputation for cross-validation and zero-fill for held-out reporting). In supervised evaluation, the best Tier 1+2 model reaches 66.72% exact accuracy (macro F1 = 0.69) and 94.53% adjacent accuracy (within one CEFR level) on a 3,198-sample CEFR-labeled benchmark split; an extended comparison including preliminary Tier 3 features achieves 67.50%. Unsupervised analyses show strong structure for extreme levels (A1 99.5% purity; C2 82.4% purity) and moderate alignment with professional Cambridge labels (Adjusted Rand Index = 0.303). We report block ablations and compact subset searches, with strongest signals from morphological complexity and lexical sophistication, and consistent incremental gains from error-based features. The results provide a validated, interpretable feature inventory and practical guidance for feature selection in automated language assessment systems.

This article is devoted to the problem of verifying parallel programs that may contain special types of errors associated with the synchronization of parallel executed threads and access to shared memory. Such errors include deadlocks and data races. There is a division of parallel program verification methods into static and dynamic. The second ones require running the code and allow to check only the current implementation of the program for races, which, if there are a large number of branches, can lead to missing races. Among static methods, analytical methods (for example, based on deductive analysis) and model checking methods are most widely used. However, they are difficult to implement, and model checking still require a significant amount of manual work from the programmer to build such a model. In this regard, it is necessary to use models that can be built automatically. Previously, the authors developed a model based on an extension of Petri nets, which allows automatic creation based on sequential code and its conversion into parallel code. Automatic creation of a model of a parallel program introduces new, previously unused requirements related to the interaction of parallel threads. Thus, this article discusses the features of modeling using extended Petri nets with semantic relations of the main synchronization primitives implemented in most languages and parallel programming technologies for shared memory systems. In the future, these models will be used to search for data races and deadlocks in parallel programs.

Process mining is a field of computer science that deals with the discovery and analysis of process models based on automatically generated event logs. Currently, many companies are using this technology to optimize and improve their business processes. However, a discovered process model may be too detailed, sophisticated, and difficult for experts to understand. In this paper, we consider a problem of discovering the hierarchical business process model from a low-level event log, i. e., the problem of the automatic synthesis of more readable and understandable process models based on the data stored in the event logs of information systems. The discovery of better-structured and more readable process models is extensively studied in the framework of process mining research from different perspectives. In this paper, we present an algorithm for discovering hierarchical process models represented as two-level workflow Petri nets. The algorithm is based on predefined event partitioning so that this partitioning defines a sub-process corresponding to a high-level transition at the top level of a two-level net. In contrast to existing solutions, our algorithm does not impose restrictions on the process control flow and allows for concurrency and iterations.

The process-oriented programming is a paradigm based on the process concept where each process is a concurrent finite state machine inside. The paradigm is intended for PLC (programmable logic controllers) developers to write Industry 4.0-enabled software. The poST language is a promising process-oriented extension of the IEC 61131-3 Structured Text (ST) language designed to provide a conceptual consistency of the PLC source code with technological description of the process under control. This language combines the advantages of FSM-based programming with the standard syntax of the ST language. We propose transformational semantics of poST providing rules for translation of poST language statements to Promela — the input language of the SPIN model checker. Following these semantic rules, our Xtext-based translator outputs a Promela model for the poST program. Our contribution is the poST transformational semantics and the method for automatic generation of the Promela code from poST control programs. The resulting Promela program is ready to be verified with SPIN model checker against linear temporal logic requirements to the source poST program. In the paper we provide an overview of related work, as well as a brief description of the poST and Promela languages. Further, the Promela poST translation rules cover control flow statements, process creation and state management constructs, and timeout management. Then we define service processes for modeling the external environment and managing high-level LTL specifications. Then we present the main ideas of implementing the translator poST to Promela. We also illustrate our approach using the example of a system for managing electricity consumption and production, including renewable sources.

This article describes a series of experiments in the Gazebo simulation environment aimed at studying the influence of external weather conditions on the automatic landing of an unmanned aerial vehicle (UAV) on a moving platform using computer vision and a previously developed control system based on PID and polynomial controllers. As part of the research, methods for modeling external weather conditions were developed and landing tests were carried out simulating weather conditions such as wind, light, fog and precipitation, including their combinations. In all experiments, successful landing on the platform was achieved; during the experiments, landing time and its accuracy were measured. The graphical and statistical analysis of the obtained results revealed the influence of illumination, precipitation and wind on the UAV landing time, and the introduction of wind into the simulation under any other external conditions led to the most significant increase in landing time. At the same time, the study failed to identify a systemic negative influence of external conditions on landing accuracy. The results obtained provide valuable information for further improvement of autonomous automatic landing systems for UAVs without the use of satellite navigation systems.

This paper presents a study of the problem of automatic classification of short coherent texts (essays) in English according to the levels of the international CEFR scale. Determining the level of text in natural language is an important component of assessing students knowledge, including checking open tasks in e-learning systems. To solve this problem, vector text models were considered based on stylometric numerical features of the character, word, sentence structure levels. The classification of the obtained vectors was carried out by standard machine learning classifiers. The article presents the results of the three most successful ones: Support Vector Classifier, Stochastic Gradient Descent Classifier, LogisticRegression. Precision, recall and F-score served as quality measures. Two open text corpora, CEFR Levelled English Texts and BEA-2019, were chosen for the experiments. The best classification results for six CEFR levels and sublevels from A1 to C2 were shown by the Support Vector Classifier with F-score 67 % for the CEFR Levelled English Texts. This approach was compared with the application of the BERT language model (six different variants). The best model, bert-base-cased, provided the F-score value of 69 %. The analysis of classification errors showed that most of them are between neighboring levels, which is quite understandable from the point of view of the domain. In addition, the quality of classification strongly depended on the text corpus, that demonstrated a significant difference in F-scores during application of the same text models for different corpora. In general, the obtained results showed the effectiveness of automatic text level detection and the possibility of its practical application.

This study is aimed at building an automated model for business writing assessment, based on 14 rubrics that integrate EFL teacher assessment frameworks and identify expected performance against various criteria (including language, task fulfillment, content knowledge, register, format, and cohesion). We developed algorithms for determining the corresponding numerical features using methods and tools for automatic text analysis. The algorithms are based on a syntactic analysis with the use of dictionaries. The model performance was subsequently evaluated on a corpus of 20 teacher-assessed business letters. Heat maps and UMAP results represent comparison between teachers’ and automated score reports. Results showed no significant discrepancies between teachers’ and automated score reports, yet detected bias in teachers’ reports. Findings suggest that the developed model has proved to be an efficient tool for natural language processing with high interpretability of the results, the roadmap for further improvement and a valid and unbiased alternative to teachers’ assessment. The results may lay the groundwork for developing an automatic students’ language profile. Although the model was specifically designed for business letter assessment, it can be easily adapted for assessing other writing tasks, e.g. by replacing dictionaries.

The research is devoted to classification of news articles about P. G. Demidov Yaroslavl State University (YarSU) into 4 categories: “society”, “education”, “science and technologies”, “not relevant”.The proposed approaches are based on using the BERT neural network and methods of machine learning: SVM, Logistic Regression, K-Neighbors, Random Forest, in combination of different embedding types: Word2Vec, FastText, TF-IDF, GPT-3. Also approaches of text preprocessing are considered to achieve higher quality of the classification. The experiments showed that the SVM classifier with TF-IDF embedding and trained on full article texts with titles achieved the best result. Its micro-F-measure and macro-F-measure are 0.8214 and 0.8308 respectively. The BERT neural network trained on fragments of paragraphs with YarSU mentions, from which the first 128 words and the last 384 words were taken, showed comparable results. The resulting micro-F-measure and macro-F-measure are 0.8304 and 0.8181 respectively. Thus, using paragraphs with the target organisation mentions is enough to classify text by categories efficiently.

The paper analyzes the possibilities of transforming C programming language constructs into objects of EO programming language. The key challenge of the method is the transpilation from a system programming language into a language of a higher level of abstraction, which doesn’t allow direct manipulations with computer memory. Almost all application and domain-oriented programming languages disable such direct access to memory. Operations that need to be supported in this case include the use of dereferenced pointers, the imposition of data of different types in the same memory area, and different interpretation of the same data which is located in the same memory address space. A decision was made to create additional EO-objects that directly simulate the interaction with computer memory as in C language. These objects encapsulate unreliable data operations which use pointers. An abstract memory object was proposed for simulating the capabilities of C language to provide interaction with computer memory. The memory object is essentially an array of bytes. It is possible to write into memory and read from memory at a given index. The number of bytes read or written depends on which object is being used. The transformation of various C language constructs into EO code is considered at the level of the compilation unit. To study the variants and analyze the results a transpiler was developed that provides necessary transformations. It is implemented on the basis of Clang, which forms an abstract syntax tree. This tree is processed using LibTooling and LibASTMatchers libraries. As a result of compiling a C program, code in EO language is generated. The considered approach turns out to be appropriate for solving different problems. One of such problems is static code analysis. Such solutions make it possible to isolate low-level code fragments into separate program objects, focusing on their study and possible transformations into more reliable code.

The article is written in support of the educational discipline “Non-classical logics”. Within the framework of this discipline, the objects of study are the basic principles and constructive elements, with the help of which the formal construction of various non-classical propositional logics takes place. Despite the abstractness of the theory of non-classical logics, in which the main attention is paid to the strict mathematical formalization of logical reasoning, there are real practical areas of application of theoretical results. In particular, languages of temporal modal logics are widely used for modeling, specification, and verification (correctness analysis) of logic control program systems. This article demonstrates, using the linear temporal logic LTL as an example, how abstract concepts of non-classical logics can be reƒected in practice in the field of information technology and programming. We show the possibility of representing the behavior of a software system in the form of a set of LTL-formulas and using this representation to verify the satisfiability of program system properties through the procedure of proving the validity of logical inferences, expressed in terms of the linear temporal logic LTL. As program systems, for the specification of the behavior of which the LTL logic will be applied, Minsky counter machines are considered. Minsky counter machines are one of the ways to formalize the intuitive concept of an algorithm. They have the same computing power as Turing machines. A counter machine has the form of a computer program written in a high-level language, since it contains variables called counters, and conditional and unconditional jump operators that allow to build loop constructions. It is known that any algorithm (hypothetically) can be implemented in the form of a Minsky three-counter machine.