Even as efforts to promote K-12 CS education forge ahead, there is a growing consensus that students must also be taught artificial intelligence (AI) and machine learning (ML) in order to be prepared for the fast-changing world powered by AI/ML. How can ensure that we leverage learnings from two decades of CS education research and practice, and build on successes while mitigating missteps? This panel invites researchers with deep expertise in 'CSForAll' efforts for a timely discussion and sharing of valuable lessons from CS education efforts about pedagogies, attention to equity, and teacher preparation that will also benefit K-12 AI education.

Women and people from historically marginalized groups are recognized as underrepresented in computer science (CS) courses. We approach this issue by building a K-12 teacher workforce as role models to K-12 students. In this project, we develop a K-12 CS Educator Certificate Program and provide scholarships to 20 Black, Latina, and Native American women in-service teachers. To support these scholars, we provided a community of practice that includes mentoring from experienced CS educators and flexible tutoring from CS content experts. Through these efforts to increase diversity and representation in those who teach CS, we are making strides toward all students seeing themselves in the field of CS.

The computer science (CS) education field is exploring several instructional strategies for teaching CS to children in elementary school. Strong arguments have been made for integration--- constructing activities that not only teach CS, but use the CS to support learning in a core subject. Integrating CS materials into a specific curriculum is a non-trivial task that may unfairly burden elementary teachers, who are often generalists. Successful development and classroom implementation of integrated materials relies on many decisions about what, when, and how much subject matter to cover in relation to the main curriculum.

Curriculum development is dependent on the following question: What are the learning goals for a specific topic, and what are reasonable ways to organize and order those goals? Learning trajectories (LTs) for computational thinking (CT) topics will help to guide emerging curriculum development efforts for computer science in elementary school. This study describes the development of an LT for Debugging. We conducted a rigorous analysis of scholarly research on K-8 computer science education to extract what concepts in debugging students should and are capable of learning. The concepts were organized into the LT presented within. In this paper, we describe the three dimensions of debugging that emerged during the creation of the trajectory: (1) strategies for finding and fixing errors, (2) types of errors, and (3) the role of errors in problem solving. In doing so, we go beyond identification of specific debugging strategies to further articulate knowledge that would help students understand when to use those techniques and why they are successful. Finally, we illustrate how the Debugging LT has guided our efforts to develop an integrated mathematics and CT curriculum for grades 3-5.

As new initiatives in computational thinking and computer science (CS/CT) are being developed and deployed, it is important to identify and understand the key concepts that are essential for student learning. In this study, we present the phases of construction of a learning trajectory (LT) for Decomposition in the context of CS/CT in K-8 education. From an extensive literature review, 63 learning goals representative of decomposition understanding and practices were identified and synthesized into 13 consensus goals. The focus of this paper is how relationships between these consensus goals were identified and used to place the goals into a learning trajectory. We discuss the theories and frameworks that guided the trajectory's construction as well as the methodology and justifications used to draw pathways through the trajectory in each phase. Finally, we discuss potential uses for the trajectory and suggest further explorations for decomposition in CS/CT.

Computing curricula are being developed for elementary school classrooms, yet research evidence is scant for learning trajectories that drive curricular decisions about what topics should be addressed at each grade level, at what depth, and in what order. This study presents learning trajectories based on an in-depth review of over 100 scholarly articles in computer science education research. We present three levels of results. First, we present the characteristics of the 600+ learning goals and their research context that affected the learning trajectory creation process. Second, we describe our first three learning trajectories (Sequence, Repetition, and Conditionals), and the relationship between the learning goals and the resulting trajectories. Finally, we discuss the ways in which assumptions about the context (mathematics) and language (e.g., Scratch) directly influenced the trajectories.

Research on appropriate topics and goals for computer science (CS) education in elementary and middle school has been ongoing for decades, but the recent movement toward CS for all requires the research community to gain a better understanding of what is most important to teach, to whom, and in what order. We conducted a literature review with specific attention to cataloging computer science learning goals that experts theorize are important to teach as well as learning goals that have been explored and researched with students in K-8. By mapping the former onto the latter, we discovered six categories of goals that are theorized as important but, according to our review, are yet to be researched with K-8 students. We discuss the potential implications of these gaps for future research.