Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to students' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.

Active learning in introductory programming depends on frequent, high-quality feedback, yet instructors often struggle to deliver consistent support at scale. In this poster, we introduce INSIGHT, an AI-driven classroom assistant designed to promote active learning in introductory programming (CS1) courses through scalable, personalized, and explainable feedback. The assistant combines the generative capabilities of large language models (LLMs) with instructor-in-the-loop authoring and an explainable code analysis engine to ensure pedagogically aligned support. Instructors can co-design problems with LLM assistance, provide exemplar solutions, define common student errors, and author targeted feedback. The AI engine analyzes student code submissions, identifies misconceptions, and maps them to instructor-verified feedback in real time. INSIGHT is designed to ensure that key educational concepts and common misconceptions are explicitly addressed by instructors, while also leveraging LLMs to provide reasonable feedback for novel or edge-case solutions that instructors may not have anticipated. By combining instructor expertise with the flexibility of generative AI, the assistant helps close feedback gaps and ensures more comprehensive coverage of student learning needs, especially in large or diverse classrooms with limited instructional support.

A significant portion of student programming submissions in CS1 learning environments are uncompilable, limiting their use in student modeling and downstream knowledge tracing. Traditional modeling pipelines often exclude these cases, discarding observations of student learning. This study investigates automated program repair as a strategy to recover uncompilable code while preserving students' structural intent for use in student modeling. Within this framework, we assess large language models (LLMs) as repair agents under high- and low-context prompting conditions. Repairs were evaluated for compilability, edit distance, and preservation of students' original structure and logic. While all models produced compilable repairs, they differed in how well they preserve students' control flow and code structure, affecting their pedagogical utility. By recovering uncompilable submissions, this work enables richer and more comprehensive analyses of learners' coding processes and development over time.

As artificial intelligence (AI) becomes increasingly embedded in scientific and technical domains, the ability to engage in AI-integrated STEM problem-solving is emerging as a critical skill for the future STEM workforce. Supporting students in this type of problem-solving requires building a strong foundation in computational thinking, particularly through pedagogically effective and technically robust tools. In this paper, we propose augmenting i-Sail, a block-based programming environment designed for AI-integrated STEM problem-solving, with large language model-driven feedback capabilities to facilitate students' problem-solving while reinforcing key computational thinking skills for middle-grade students. We prompt a large language model with structured knowledge about breadth-first search to provide contextualized, adaptive feedback. The LLM helps students connect their problem-solving steps to the high-level structure of the breadth-first search algorithm and apply this understanding to pathfinding. We present a proof-of-concept evaluation that demonstrates the potential of the system to support the development of computational thinking through AI-integrated problem solving in diverse STEM contexts.

We present a reproducible pipeline that aligns CS1 textbook sections with problems from a public dataset via a Knowledge Component (KC) -a single conceptual skill required for problem solving- ontology. It assigns KCs to sections and problems, respects the prerequisite order to avoid inserting problems too early, and generates tips for not-yet-taught concepts. We evaluate three KC assignment strategies: embedding-only, embedding with a Large Language Model (LLM) tie-breaker, and direct LLM assignment. We find direct assignment matches or exceeds human annotators. Our results show that constrained LLMs can enrich CS1 textbooks with curriculum-aware practice problems.

Novice programmers can greatly improve their understanding of challenging programming concepts by studying worked examples that demonstrate the implementation of these concepts. Despite the extensive repositories of effective worked examples created by CS education experts, a key challenge remains: identifying the most relevant worked example for a given programming problem and the specific difficulties a student faces solving the problem. Previous studies have explored similar example recommendation approaches. Our research introduces a novel method by utilizing deep learning code representation models to generate code vectors, capturing both syntactic and semantic similarities among programming examples. Driven by the need to provide relevant and personalized examples to programming students, our approach emphasizes similarity assessment and clustering techniques to identify similar code problems, examples, and challenges. This method aims to deliver more accurate and contextually relevant recommendations based on individual learning needs. Providing tailored support to students in real-time facilitates better problem-solving strategies and enhances students' learning experiences, contributing to the advancement of programming education.

Identifying Knowledge Components (KCs) in computer science education improves curriculum design and teaching strategies. We introduce a framework using Large Language Models to identify KCs from programming assignments automatically. Our framework helps educators align assignments with course objectives. GPT-4 identifies relevant KCs well, though there's a low match with expert-generated KCs at the course level. At the problem level, performance is lower, but key KCs are reasonably identified.

The panel comprises a diverse set of Computing educators working on AI in education. The panelists will address four areas of AI in Computing education: 1) AI for introductory CS classrooms, 2) Investigating opportunities presented by LLMs, 3) LLM-based tool development, and 4) Ethics and inclusion in AI curriculum. The panel will share experiences and discuss opportunities and challenges in AI education with the community.

The emergence of publicly accessible large language models (LLMs) such as ChatGPT poses unprecedented risks of new types of plagiarism and cheating where students use LLMs to solve exercises for them. Detecting this behavior will be a necessary component in introductory computer science (CS1) courses, and educators should be well-equipped with detection tools when the need arises. However, ChatGPT generates code non-deterministically, and thus, traditional similarity detectors might not suffice to detect AI-created code. In this work, we explore the affordances of Machine Learning (ML) models for the detection task. We used an openly available dataset of student programs for CS1 assignments and had ChatGPT generate code for the same assignments, and then evaluated the performance of both traditional machine learning models and Abstract Syntax Tree-based (AST-based) deep learning models in detecting ChatGPT code from student code submissions. Our results suggest that both traditional machine learning models and AST-based deep learning models are effective in identifying ChatGPT-generated code with accuracy above 90%. Since the deployment of such models requires ML knowledge and resources that are not always accessible to instructors, we also explore the patterns detected by deep learning models that indicate possible ChatGPT code signatures, which instructors could possibly use to detect LLM-based cheating manually. We also explore whether explicitly asking ChatGPT to impersonate a novice programmer affects the code produced. We further discuss the potential applications of our proposed models for enhancing introductory computer science instruction.

Identifying misconceptions in student programming solutions is an important step in evaluating their comprehension of fundamental programming concepts. While misconceptions are latent constructs that are hard to evaluate directly from student programs, logical errors can signal their existence in students' understanding. Tracing multiple occurrences of related logical bugs over different problems can provide strong evidence of students' misconceptions. This study presents preliminary results of utilizing an interpretable state-of-the-art Abstract Syntax Tree-based embedding neural network to identify logical mistakes in student code. In this study, we show a proof-of-concept of the errors identified in student programs by classifying correct versus incorrect programs. Our preliminary results show that our framework is able to automatically identify misconceptions without designing and applying a detailed rubric. This approach shows promise for improving the quality of instruction in introductory programming courses by providing educators with a powerful tool that offers personalized feedback while enabling accurate modeling of student misconceptions.

This study utilizes large language models to extract foundational programming concepts in programming assignments in a CS1 course. We seek to answer the following research questions: RQ1. How effectively can large language models identify knowledge components in a CS1 course from programming assignments? RQ2. Can large language models be used to extract program-level knowledge components, and how can the information be used to identify students' misconceptions? Preliminary results demonstrated a high similarity between course-level knowledge components retrieved from a large language model and that of an expert-generated list.

Automated analysis of programming data using code representation methods offers valuable services for programmers, from code completion to clone detection to bug detection. Recent studies show the effectiveness of Abstract Syntax Trees (AST), pre-trained Transformer-based models, and graph-based embeddings in programming code representation. However, pre-trained large language models lack interpretability, while other embedding-based approaches struggle with extracting important information from large ASTs. This study proposes a novel Subtree-based Attention Neural Network (SANN) to address these gaps by integrating different components: an optimized sequential subtree extraction process using Genetic algorithm optimization, a two-way embedding approach, and an attention network. We investigate the effectiveness of SANN by applying it to two different tasks: program correctness prediction and algorithm detection on two educational datasets containing both small and large-scale code snippets written in Java and C, respectively. The experimental results show SANN's competitive performance against baseline models from the literature, including code2vec, ASTNN, TBCNN, CodeBERT, GPT-2, and MVG, regarding accurate predictive power. Finally, a case study is presented to show the interpretability of our model prediction and its application for an important human-centered computing application, student modeling. Our results indicate the effectiveness of the SANN model in capturing important syntactic and semantic information from students' code, allowing the construction of accurate student models, which serve as the foundation for generating adaptive instructional support such as individualized hints and feedback.

No abstract available.

A key goal of many computer science education efforts is to increase the number and diversity of students who persist in the field of computer science and into computing careers. Many interventions have been developed in computer science designed to increase students' persistence in computing. However, it is often difficult to measure the efficacy of such interventions, as measuring actual persistence by tracking student enrollments and career placements after an intervention is difficult and time-consuming, and sometimes even impossible. In the social sciences, attitudinal research is often used to solve this problem, as attitudes can be collected in survey form around the same time that interventions are introduced and are predictive of behavior. This can allow researchers to assess the potential efficacy of an intervention before devoting the time and energy to conduct a longitudinal analysis. In this paper, we develop and validate a scale to measure intentions to persist in computing, and demonstrate its use in predicting actual persistence as defined by enrolling in another computer science course within two semesters. We conduct two analyses to do this: First, we develop a computing persistence index and test whether our scale has high alpha reliability and whether our scale predicts actual persistence in computing using students' course enrollments. Second, we conduct analyses to reduce the number of items in the scale, to make the scale easy for others to include in their own research. This paper contributes to research on computing education by developing and validating a novel measure of intentions to persist in computing, which can be used by computer science educators to evaluate potential interventions. This paper also creates a short version of the index, to ease implementation.

As AI becomes more widely used across a variety of disciplines, it is increasingly important to teach AI concepts to K-12 students in order to prepare them for an AI-driven future workforce. Hence, educators and researchers have been working to develop curricula that make these concepts accessible to K-12 students. We are designing and developing a comprehensive AI curriculum delivered through a series of carefully crafted activities in an adapted \emph{Snap!} environment for middle-grade students. In this work, we lay out the proposed content of our curriculum and present the design, development, and implementation results of the first unit of our curriculum that focuses on teaching the breadth-first search algorithm. The activities in this unit have been revised after being piloted with a single high-school student. These activities were further refined after a group of K-12 teachers examined and critiqued them during a two-week professional development workshop. Our teachers created a lesson plan around the activities and implemented that lesson in a summer workshop with 14 middle school students. Our results demonstrated that our activities were successful in helping many of the students in understanding and implementing the algorithm through block-based programming while extra supplementary material was needed to assist some other students. In this paper, we explain our curriculum and technology, the results of implementing the first unit of our curriculum in a summer camp, and lessons learned for future developments.

Are women less likely to persist in computer science because of gender differences in self-assessed computing ability? And why do gender differences exist in self-assessments among women and men who earn the same grades? We use a mixed-method research design to answer these questions, utilizing both quantitative survey data (n = 764) and qualitative interview data (n = 59) from students in introductory computing courses at a large U.S. state university. Quantitatively, we find that women self-assess their computing ability significantly lower than men who earn the same grades, and that these lower self-assessments reduce the likelihood that women enroll in future CS courses (relative to men who earn equivalent grades). Qualitatively, we explore how women and men perceive their own computing ability to understand why women self-assess their ability lower than men. Our interviews revealed that women were much less likely than men to make favorable comparative judgements about their ability relative to their classmates. Women also had higher personal performance standards than men. Lastly, women were more likely than men to experience disrespectful treatment, with an undertone of presumed incompetence, from their TAs and classmates. In sum, this research furthers our understanding of why gender differences exist in self-assessments of computing ability and how these differences can contribute to gender disparities in computing persistence. It also draws attention to the importance of feedback in computing courses and suggests that improving course feedback may reduce gender disparities in computing.

Research has shown that high self-assessment of ability, sense of belonging, and professional role confidence are crucial for students' persistence in computing. As grades in introductory computer science courses tend to be lower than other courses, it is essential to provide students with contextualized feedback about their performance in these courses. Giving students unambiguous and con- textualized feedback is especially important during COVID when many classes have moved online and instructors and students have fewer opportunities to interact. In this study, we investigate the effect of a lightweight, scalable intervention where students received personalized, contextualized feedback from their instructors after two major assignments during the semester. After each intervention, we collected survey data to assess students' self-assessment of computing ability, sense of belonging, intentions to persist in computing, professional role confidence, and the likelihood of stating intention to pursue a major in computer science. To analyze the effectiveness of our intervention, we conducted linear regression and mediation analysis on student survey responses. Our results have shown that providing students with personalized feedback can significantly improve their self-assessment of computing ability, which will significantly improve their intentions to persist in computing. Furthermore, our results have demonstrated that our intervention can significantly improve students' sense of belonging, professional role confidence, and the likelihood of stating an intention to pursue a major in computer science.

We have found that giving top-performing students in CS1 courses personalized feedback increases their intentions to persist in computing, especially among students who are women. This personalized feedback also appears to improve students' course experience and increases the likelihood that women apply to be CS1 TAs. Yet despite these benefits, giving personalized feedback may seem too impractical and time-intensive for faculty members to adopt in their own classrooms. In this workshop, we will reduce the burden of giving students personalized feedback by: 1) giving instructors empirically validated email templates to use in their own courses, and 2) guiding faculty how to send emails at-scale. We will also discuss how self-assessments influence students' career choices, how gender stereotypes bias self-assessments, and what faculty can do to counteract biased self-assessments of computing ability.

Open-ended programming engages students by connecting computing with their real-world experience and personal interest. However, such open-ended programming tasks can be challenging, as they require students to implement features that they may be unfamiliar with. Code examples help students to generate ideas and implement program features, but students also encounter many learning barriers when using them. We explore how to design code examples to support novices' effective example use by presenting our experience of building and deploying Example Helper, a system that supports students with a gallery of code examples during open-ended programming. We deployed Example Helper in an undergraduate CS0 classroom to investigate students' example usage experience, finding that students used different strategies to browse, understand, experiment with, and integrate code examples, and that students who make more sophisticated plans also used more examples in their projects.

Recent years have seen increasing awareness of the need for all students in primary and secondary education to learn computer science (CS) concepts and skills. Educational games hold significant potential to serve as a platform for CS education because they integrate engaging problem solving with effective pedagogical strategies. This potential is especially high for narrative-centered educational games that embed learning activities within rich interactive stories. In this paper, we present an educational game featuring block-based programming challenges contextualized within an engaging narrative, designed to promote CS learning for middle school students (ages 11 to 13). In the game, students undertake problem-solving challenges that are aligned with the K-12 Computer Science Framework. Results from a classroom implementation of the game with middle grade students suggest that their perceived game control ratings are positively correlated with their progress in the game, which suggests the need for adaptively supporting students' game-based learning activities. Building on these findings, we discuss design implications for creating student-adaptive CS learning experiences in educational games that incorporate block-based programming enriched narrative-centered gameplay.

The lack of effective guidelines for assessing students' computer science (CS) competencies is creating significant demand by K-12 teachers for CS assessments to evaluate students' learning. We propose a conceptual assessment framework that guides teachers through designing appropriate assessments for computer science (CS) activities in their classrooms. The framework addresses the critical problem of incorporating CS into K-12 curricula without corresponding assessments. We illustrate its use with the design of a rubric for a bubble sort algorithm situated in a game-based learning environment for middle-grade students. We also apply a preliminary and a revised version of this assessment on two datasets collected from students' interactions with the learning environment. We found consistency among results identified through applying the preliminary and the revised rubric. The results reveal distinctive patterns in students' approaches to CS problem solving and coherency with respect to different aspects of the rubric.*

With national K-12 education initiatives such as "CSForAll," block-based programming environments have emerged as widely used tools for teaching novice programming. A key challenge presented by block-based programming environments is assessing students' computational thinking (CT) and programming competencies. Developing assessment methods that can evaluate students' use of CT practices such as testing and refining, and developing and using appropriate algorithms, can help teachers evaluate students learning and provide appropriate scaffolding. In this work, we utilize an evidence-centered assessment design approach to devise a three-dimensional assessment to evaluate students' CT competencies based on evidence extracted from their programming trajectories in a block-based programming environment. In this assessment, the first dimension assesses students' knowledge of essential CT concepts, the second dimension assesses students' dynamic testing and refining strategies, and the third dimension assesses their overall problem-solving efficiency. We apply the assessment framework to data collected from students' interactions with a game-based learning environment designed to develop middle-grade students' CT competencies and programming skills. The results demonstrate that students' knowledge of basic CT constructs, such as appropriate use and combination of control structures, serves as the foundation for designing and implementing effective algorithms. Further, we assessed students testing and refining strategies over the three dimensions of novelty, positivity, and scale. The results demonstrate that students with higher algorithmic capabilities tend to make more novel, positive, and small-scale changes. The results reveal distinctive patterns in students' approaches to computational thinking problem solving and make a step toward identifying and assessing productive computational thinking practices.