pith. sign in

arxiv: 2604.10400 · v1 · submitted 2026-04-12 · 💻 cs.HC

Tracing Prompt-Level Trajectories to Understand Student Learning with AI in Programming Education

Tianyu Shao , Miguel Feij\'oo-Garc\'ia , Yi Zhang , Hugo Castellanos , Tawfiq Salem , Alejandra Magana , Tianyi Li This is my paper

Pith reviewed 2026-05-10 16:36 UTC · model grok-4.3

classification 💻 cs.HC
keywords AI in educationprogramming educationprompt engineeringself-regulated learninglearning trajectoriesstudent-AI collaborationintroductory Pythoninteraction analysis
0
0 comments X

The pith

Prompting trajectories in student-AI chats indicate self-regulation and learning in programming classes

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper investigates student engagement with AI tools like ChatGPT in an introductory Python programming assignment by analyzing chat histories and final submissions from 163 students. It traces prompt-level strategies and identifies trajectories that range from full delegation to the AI to iterative refinement of generated code. While most students directly copied AI code into their submissions, many used multiple prompts to build upon and improve the output. These interaction patterns are contrasted with assignment outcomes and course performance to suggest that prompting trajectories offer windows into students' self-regulation and learning orientations. The authors draw implications for designing educational AI systems that foster more productive and personalized collaborative learning.

Core claim

Tracing the prompt-level trajectories of student interactions with AI during programming tasks reveals a spectrum of engagement styles, from complete reliance on AI-generated code to iterative co-construction, which serve as indicators of self-regulatory processes and orientations toward learning.

What carries the argument

Prompt-level trajectories: the sequences of student prompts and AI responses that map the progression of problem-solving interactions in the assignment.

Load-bearing premise

Chat histories and final code submissions capture the students' learning processes and strategies sufficiently, without major unobserved influences from prior knowledge or external help.

What would settle it

Collecting data on students' prior experience and any external resources used, then verifying whether the identified trajectories still predict learning outcomes independently of those factors.

Figures

Figures reproduced from arXiv: 2604.10400 by Alejandra Magana, Hugo Castellanos, Miguel Feij\'oo-Garc\'ia, Tawfiq Salem, Tianyi Li, Tianyu Shao, Yi Zhang.

Figure 1
Figure 1. Figure 1: An illustration of the qualitative analysis process. [PITH_FULL_IMAGE:figures/full_fig_p007_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Prompt-level co-occurrence matrix of prompt themes. Darker cells indicate stronger co-occurrence frequencies. [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Sankey diagram of student–LLM conversation flows that follows the [PITH_FULL_IMAGE:figures/full_fig_p013_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Sankey diagram of student–LLM conversation flows that follows the [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Sankey diagram of student–LLM conversation flows that follows the [PITH_FULL_IMAGE:figures/full_fig_p014_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Sankey diagram of student–LLM conversation flows that follows the [PITH_FULL_IMAGE:figures/full_fig_p014_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Assignment grades across different LLM interaction trajectories. [PITH_FULL_IMAGE:figures/full_fig_p016_7.png] view at source ↗
read the original abstract

As AI tools such as ChatGPT enter programming classrooms, students encounter differing rules across courses and instructors, which shape how they use AI and leave them with unequal capabilities for leveraging it. We investigate how students engaged with AI in an introductory Python assignment, analyzing student-LLM chat histories and final code submissions from 163 students. We examined prompt-level strategies, traced trajectories of interaction, and compared AI-generated code with student submissions. We identified trajectories ranging from full delegation to iterative refinement, with hybrid forms in between. Although most students directly copied AI-generated code in their submission, many students scaffolded the code generation through iterative refinement. We also contrasted interaction patterns with assignment outcomes and course performance. Our findings show that prompting trajectories serve as promising windows into students' self-regulation and learning orientation. We draw design implications for educational AI systems that promote personalized and productive student-AI collaborative learning.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper analyzes prompt-level interaction trajectories from LLM chat histories and final code submissions of 163 students in an introductory Python assignment. It classifies trajectories along a spectrum from full delegation to iterative refinement (with hybrids), contrasts these patterns against assignment and course performance metrics, and concludes that such trajectories offer promising windows into students' self-regulation and learning orientations, with implications for designing educational AI systems that support productive collaboration.

Significance. If the observational mappings can be strengthened with controls and validation, the work has moderate significance for HCI and CS education research by providing ecologically valid data on real student-AI interactions at scale. The collection of 163 authentic chat histories paired with submissions is a clear strength, enabling concrete trajectory identification that prior survey-based studies often lack.

major comments (2)
  1. [Abstract / Methods] Abstract and methods description: the claim that 'prompting trajectories serve as promising windows into students' self-regulation and learning orientation' is underdetermined because the manuscript provides no details on the coding scheme used to classify trajectories (e.g., full delegation vs. iterative refinement), inter-rater reliability, or how assignment/course outcomes were operationalized and statistically controlled. Without these, post-hoc correlations cannot isolate self-regulation from confounds such as prior Python experience or external resources.
  2. [Results / Discussion] Results / Discussion: the contrast between interaction patterns and performance metrics is presented as evidence for the central claim, yet the manuscript does not report controls for prior knowledge, peer collaboration, or non-AI help-seeking. This is load-bearing because the skeptic correctly notes that observational traces alone leave the mapping to internal constructs underdetermined; convergent validation (e.g., self-regulation scales or think-aloud data) would be needed to support the inference.
minor comments (2)
  1. [Abstract] The abstract states 'many students scaffolded the code generation through iterative refinement' but does not quantify the distribution of trajectory types or provide example prompts; adding a table or figure with counts and representative excerpts would improve clarity.
  2. [Methods] The manuscript should explicitly state the IRB or consent process for analyzing student chat data, even if anonymized, to address ethical considerations common in HCI education studies.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive feedback. We have revised the manuscript to expand methodological details and to qualify our claims more carefully in light of the observational data. Point-by-point responses to the major comments are provided below.

read point-by-point responses

  1. Referee: [Abstract / Methods] Abstract and methods description: the claim that 'prompting trajectories serve as promising windows into students' self-regulation and learning orientation' is underdetermined because the manuscript provides no details on the coding scheme used to classify trajectories (e.g., full delegation vs. iterative refinement), inter-rater reliability, or how assignment/course outcomes were operationalized and statistically controlled. Without these, post-hoc correlations cannot isolate self-regulation from confounds such as prior Python experience or external resources.

    Authors: We agree that the original manuscript provided insufficient detail on the classification process. In the revised version, we have added a Methods subsection describing the coding scheme: trajectories were categorized by reviewing prompt sequences and code edits, defining full delegation as minimal changes to AI output, iterative refinement as repeated prompting with student modifications, and hybrids as mixed patterns, supported by illustrative examples from the data. Classification was performed collaboratively by the research team through iterative consensus rather than independent coding of the full set. Assignment outcomes were operationalized via the instructor's rubric scores for correctness and style; course performance used final grades. We have added explicit text noting the absence of prior-experience measures and present findings as descriptive associations, not isolated effects of self-regulation. revision: yes

  2. Referee: [Results / Discussion] Results / Discussion: the contrast between interaction patterns and performance metrics is presented as evidence for the central claim, yet the manuscript does not report controls for prior knowledge, peer collaboration, or non-AI help-seeking. This is load-bearing because the skeptic correctly notes that observational traces alone leave the mapping to internal constructs underdetermined; convergent validation (e.g., self-regulation scales or think-aloud data) would be needed to support the inference.

    Authors: We concur that observational chat logs alone cannot fully determine internal constructs and that controls for prior knowledge or external help would be ideal. The revised Results section reports raw patterns and correlations between trajectory types and performance metrics without claiming causation or isolation from confounds. The Discussion has been updated to frame the work as exploratory, highlighting the ecological value of the 163 authentic logs while explicitly calling for future studies with self-regulation instruments or think-aloud protocols. No such convergent data were collected in the original course assignment logs. revision: partial

standing simulated objections not resolved
  • The dataset consists solely of chat histories and submissions; no self-regulation scales, think-aloud protocols, prior-knowledge surveys, or records of peer/non-AI help-seeking were collected, preventing addition of the requested controls or convergent validation.

Circularity Check

0 steps flagged

No circularity in observational analysis of student-AI trajectories

full rationale

The paper performs an empirical, observational study of 163 students' chat histories and submissions, classifying interaction trajectories (delegation vs. refinement) and contrasting them with performance metrics. No mathematical derivations, equations, parameter fittings, or self-referential definitions appear in the provided abstract or described methods. The central claim—that trajectories serve as windows into self-regulation—is an interpretive inference from data patterns rather than a result forced by construction, self-citation chains, or renamed inputs. This is self-contained against external benchmarks and matches the default expectation of no significant circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Only the abstract was available; the central interpretation rests on the untested premise that prompt sequences directly index self-regulation without confounding variables.

axioms (1)
  • domain assumption Observed chat histories and code submissions accurately reflect students' internal learning strategies and self-regulation
    The claim that trajectories are windows into learning orientation depends on this mapping being valid.

pith-pipeline@v0.9.0 · 5471 in / 1128 out tokens · 49233 ms · 2026-05-10T16:36:20.408783+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

50 extracted references · 50 canonical work pages

  1. [1]

    Friday Joseph Agbo, Chris Olivia, Godsalvation Oguibe, Ismaila Temitayo Sanusi, and Godwin Sani. 2025. Computing education using generative artificial intelligence tools: A systematic literature review.Computers and Education Open9 (2025), 100266. doi:10.1016/j.caeo.2025.100266

    work page doi:10.1016/j.caeo.2025.100266 2025

  2. [2]

    A Ali and K Wibowo. 2023. Assessment of ChatGPT-generated programming code based on exercises in an introductory programming course. Issues in Information Systems24, 2 (2023), 203–212. doi:10.48009/2_iis_2023_117

    work page doi:10.48009/2_iis_2023_117 2023

  3. [3]

    E Ambikairajah, T Sirojan, T Thiruvaran, and V Sethu. 2024. ChatGPT in the Classroom: A Shift in Engineering Design Education. In2024 IEEE Global Engineering Education Conference (EDUCON). IEEE, 1–5. doi:10.1109/EDUCON60312.2024.10578884

    work page doi:10.1109/educon60312.2024.10578884 2024

  4. [4]

    Matin Amoozadeh, Daye Nam, Daniel Prol, Ali Alfageeh, James Prather, Michael Hilton, Sruti S Ragavan, and Amin Alipour. 2024. Student-AI Interaction: A Case Study of CS1 students. InProceedings of the 24th Koli Calling International Conference on Computing Education Research (Koli Calling ’24). Association for Computing Machinery, 1–13. doi:10.1145/369953...

    work page doi:10.1145/3699538.3699567 2024

  5. [5]

    Joana Arantes. 2024. Understanding Intersections Between GenAI and Pre-Service Teacher Education: What Do We Need to Understand About the Changing Face of Truth in Science Education?Journal of Science Education and Technology(2024). doi:10.1007/s10956-024-10189-7

    work page doi:10.1007/s10956-024-10189-7 2024

  6. [6]

    Jose Barambones, Cristian Moral, Angélica de Antonio, Ricardo Imbert, Loïc Martínez-Normand, and Elena Villalba-Mora. 2024. ChatGPT for Learning HCI Techniques: A Case Study on Interviews for Personas.IEEE Transactions on Learning Technologies17 (2024), 1486–1501. doi:10.1109/TLT.2024.3386095

    work page doi:10.1109/tlt.2024.3386095 2024

  7. [7]

    1964.Taxonomy of educational objectives

    Benjamin Samuel Bloom, Max D Engelhart, Edward J Furst, Walker H Hill, and David R Krathwohl. 1964.Taxonomy of educational objectives. Vol. 2. Longmans, Green New York

    work page 1964

  8. [8]

    It’s not like Jarvis, but it’s pretty close!

    R Budhiraja, I Joshi, J S Challa, H D Akolekar, and D Kumar. 2024. “It’s not like Jarvis, but it’s pretty close!” - Examining ChatGPT’s Usage among Undergraduate Students in Computer Science. InProceedings of the 26th Australasian Computing Education Conference. Association for Computing Machinery, 124–133. doi:10.1145/3636243.3636257

    work page doi:10.1145/3636243.3636257 2024

  9. [9]

    Ángel Alexander Cabrera, Adam Perer, and Jason I Hong. 2023. Improving Human-AI Collaboration With Descriptions of AI Behavior.Proceedings of the ACM on Human-Computer Interaction7, CSCW1 (2023), 136. doi:10.1145/3579612

    work page doi:10.1145/3579612 2023

  10. [10]

    Eduardo Carneiro Oliveira, Hieke Keuning, and Johan Jeuring. 2025. ’Can You Refactor This for Me?’: Investigating How Students Use ChatGPT in Code Refactoring Exercises. InProceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education V. 2 (ITiCSE 2025). Association for Computing Machinery

    work page 2025

  11. [11]

    Bill Cope and Mary Kalantzis. 2024. Platformed Learning: Reshaping Education in the Era of Learning Management Systems. InCritical EdTech Studies and Digital Platforms in Higher Education: Varieties of Platformisation, Duncan A Thomas and Vito Laterza (Eds.). Palgrave Macmillan, London

    work page 2024

  12. [12]

    Lei Ding, Tao Li, Shuai Jiang, and et al. 2023. Students’ perceptions of using ChatGPT in a physics class as a virtual tutor.International Journal of Educational Technology in Higher Education20, 63 (2023). doi:10.1186/s41239-023-00434-1

    work page doi:10.1186/s41239-023-00434-1 2023

  13. [13]

    Matthew Frazier, Kostadin Damevski, and Lori Pollock. 2024. Customizing ChatGPT to Help Computer Science Principles Students Learn Through Conversation. InProceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1 (ITiCSE 2024). Association for Computing Machinery, 633–639. doi:10.1145/3649217.3653570

    work page doi:10.1145/3649217.3653570 2024

  14. [14]

    M B Garcia. 2025. Teaching and learning computer programming using ChatGPT: A rapid review of literature amid the rise of generative AI technologies.Education and Information Technologies30 (2025), 16721–16745. doi:10.1007/s10639-025-13452-5

    work page doi:10.1007/s10639-025-13452-5 2025

  15. [15]

    Kilem Gwet. 2001. Handbook of inter-rater reliability.Gaithersburg, MD: STATAXIS Publishing Company(2001), 223–246

    work page 2001

  16. [16]

    Philipp Haindl and Gerald Weinberger. 2024. Students’ Experiences of Using ChatGPT in an Undergraduate Programming Course.IEEE Access12 (2024), 43519–43529. doi:10.1109/ACCESS.2024.3380909

    work page doi:10.1109/access.2024.3380909 2024

  17. [17]

    Andrew F Hayes and Klaus Krippendorff. 2007. Answering the Call for a Standard Reliability Measure for Coding Data.Communication Methods and Measures1, 1 (2007), 77–89. doi:10.1080/19312450709336664

    work page doi:10.1080/19312450709336664 2007

  18. [18]

    Sture Holm. 1979. A simple sequentially rejective multiple test procedure.Scandinavian Journal of Statistics6, 2 (1979), 65–70

    work page 1979

  19. [19]

    Ipsita Joshi, Riya Budhiraja, Haimonti Dev, Jai Kadia, Mohammed Omar Ataullah, Snehil Mitra, Harshil D Akolekar, and Divya Kumar. 2024. ChatGPT in the Classroom: An Analysis of Its Strengths and Weaknesses for Solving Undergraduate Computer Science Questions. InProceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1. Association...

    work page doi:10.1145/3626252.3630803 2024

  20. [20]

    Gregor Jošt, Vlatko Taneski, and Sašo Karakatič. 2024. The impact of large language models on programming education and student learning outcomes.Applied Sciences14, 10 (2024), 1–15. doi:10.3390/app14104115

    work page doi:10.3390/app14104115 2024

  21. [21]

    Majeed Kazemitabaar, Justin Chow, Carl Ka To Ma, Barbara J Ericson, David Weintrop, and Tovi Grossman. 2023. Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23). Association for Computing Machinery, 1–23. doi:10.1145/35...

    work page doi:10.1145/3544548.3580919 2023

  22. [22]

    Majeed Kazemitabaar, Xinying Hou, Austin Henley, Barbara Jane Ericson, David Weintrop, and Tovi Grossman. 2024. How Novices Use LLM-based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment. InProceedings of the 23rd Koli Calling International Conference on Computing Education Research. Association for Computing Machinery

    work page 2024

  23. [23]

    Piet A. M. Kommers, David H. Jonassen, J. Terry Mayes, and Alcindo Ferreira (Eds.). 1992.Cognitive Tools for Learning. Springer Berlin, Heidelberg. doi:10.1007/978-3-642-77222-1

    work page doi:10.1007/978-3-642-77222-1 1992

  24. [24]

    William H Kruskal and W Allen Wallis. 1952. Use of ranks in one-criterion variance analysis.J. Amer. Statist. Assoc.47 (1952), 583–621

    work page 1952

  25. [25]

    Harsh Kumar, Ilya Musabirov, Mohi Reza, Jiakai Shi, Xinyuan Wang, Joseph Jay Williams, Anastasia Kuzminykh, and Michael Liut. 2024. Guiding Students in Using LLMs in Supported Learning Environments: Effects on Interaction Dynamics, Learner Performance, Confidence, and Trust.Proc. ACM Hum.-Comput. Interact. 8, CSCW2, Article 499(2024), 1–30. doi:10.1145/3687038

    work page doi:10.1145/3687038 2024

  26. [26]

    Jenny T Liang, Chenyang Yang, and Brad A Myers. 2024. A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). Association for Computing Machinery

    work page 2024

  27. [27]

    Wenhan Lyu, Yimeng Wang, Tingting (Rachel) Chung, Yifan Sun, and Yixuan Zhang. 2024. Evaluating the Effectiveness of LLMs in Introductory Computer Science Education: A Semester-Long Field Study. InProceedings of the Eleventh ACM Conference on Learning @ Scale (L@S ’24). Association for Computing Machinery

    work page 2024

  28. [28]

    Shuai Ma, Qiaoyi Chen, Xinru Wang, Chengbo Zheng, Zhenhui Peng, Ming Yin, and Xiaojuan Ma. 2025. Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery

    work page 2025

  29. [29]

    Henry B Mann and Donald R Whitney. 1947. On a test of whether one of two random variables is stochastically larger than the other.Annals of Mathematical Statistics18 (1947), 50–60

    work page 1947

  30. [30]

    Giacomo Marzi, Marco Balzano, and Davide Marchiori. 2024. K-Alpha Calculator–Krippendorff’s Alpha Calculator: A user-friendly tool for computing Krippendorff’s Alpha inter-rater reliability coefficient.MethodsX12 (2024), 102545. doi:10.1016/j.mex.2023.102541

    work page doi:10.1016/j.mex.2023.102541 2024

  31. [31]

    2023.ChatGPT in STEM Teaching: An introduction to using LLM-based tools in Higher Ed

    Melanie Misanchuk. 2023.ChatGPT in STEM Teaching: An introduction to using LLM-based tools in Higher Ed. eCampusOntario

    work page 2023

  32. [32]

    Sydney Nguyen, Hannah McLean Babe, Yangtian Zi, Arjun Guha, Carolyn Jane Anderson, and Molly Q Feldman. 2024. How Beginning Programmers and Code LLMs (Mis)read Each Other. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery

    work page 2024

  33. [33]

    Lisa Ordonez and Lehman Benson III. 1997. Decisions under time pressure: How time constraint affects risky decision making.Organizational Behavior and Human Decision Processes71, 2 (1997), 121–140

    work page 1997

  34. [34]

    Penney, B

    T. Penney, B. Stephenson, P. Denny, A. Luxton-Reilly, and A. Petersen. 2023. Assessing and Designing LLM-Based Conversational Agents for Introductory Computer Science Education. InProceedings of the 18th Workshop in Primary and Secondary Computing Education (WiPSCE). ACM, 1–11. doi:10.1145/3621714.3621733

    work page doi:10.1145/3621714.3621733 2023

  35. [35]

    F A Pirzado, A Ahmed, R A Mendoza-Urdiales, and H Terashima-Marin. 2024. Navigating the Pitfalls: Analyzing the Behavior of LLMs as a Coding Assistant for Computer Science Students—A Systematic Review of the Literature.IEEE Access12 (2024), 112605–112625. doi:10.1109/ACCESS.2024. 3443621

    work page doi:10.1109/access.2024 2024

  36. [36]

    Felicitas Reinhold, Timo Leuders, Katharina Loibl, and et al. 2024. Learning Mechanisms Explaining Learning With Digital Tools in Educational Settings: a Cognitive Process Framework.Educational Psychology Review36, 14 (2024). doi:10.1007/s10648-024-09845-6

    work page doi:10.1007/s10648-024-09845-6 2024

  37. [37]

    Peter J Rousseeuw. 1987. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis.J. Comput. Appl. Math.20 (1987), 53–65

    work page 1987

  38. [38]

    Joni Salminen, Soon-gyo Jung, Johanne Medina, Kholoud Aldous, Jinan Azem, Waleed Akhtar, and Bernard J Jansen. 2024. Using Cipherbot: An Exploratory Analysis of Student Interaction with an LLM-Based Educational Chatbot. InProceedings of the Eleventh ACM Conference on Learning @ Scale (L@S ’24). Association for Computing Machinery

    work page 2024

  39. [39]

    Abigail Sellen. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools.SSRN Electronic Journal(February 2025)

    work page 2025

  40. [40]

    Abdulhadi Shoufan. 2023. Can Students without Prior Knowledge Use ChatGPT to Answer Test Questions? An Empirical Study.ACM Trans. Comput. Educ.23, 4 (2023). doi:10.1145/3628162

    work page doi:10.1145/3628162 2023

  41. [41]

    Philipp Spitzer, Joshua Holstein, Patrick Hemmer, Michael Vössing, Niklas Kühl, Dominik Martin, and Gerhard Satzger. 2025. Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information.Proceedings of the ACM on Human-Computer Interaction9, 2 (2025), 101. doi:10.1145/3710999

    work page doi:10.1145/3710999 2025

  42. [42]

    Yu-Fang Su, Ya-Fen Lin, and Chia-Wen Lai. 2023. Collaborating with ChatGPT in argumentative writing classrooms.Assessing Writing57 (2023), 100752

    work page 2023

  43. [43]

    John Sweller. 2011. CHAPTER TWO - Cognitive Load Theory. Psychology of Learning and Motivation, Vol. 55. Academic Press, 37–76. doi:10.1016/ B978-0-12-387691-1.00002-8

    work page 2011

  44. [44]

    Lev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott, Advait Sarkar, Abigail Sellen, and Sean Rintel. 2024. The Metacognitive Demands and Opportunities of Generative AI. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery

    work page 2024

  45. [45]

    Annapurna Vadaparty, Daniel Zingaro, David H Smith IV, Mounika Padala, Christine Alvarado, Jamie Gorson Benario, and Leo Porter. 2024. CS1-LLM: Integrating LLMs into CS1 Instruction. InProceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1 (ITiCSE 2024). Association for Computing Machinery. 22 Shao et al

    work page 2024

  46. [46]

    Ton van Gog, Fred Paas, and John Sweller. 2010. Cognitive Load Theory: Advances in Research on Worked Examples, Animations, and Cognitive Load Measurement.Educational Psychology Review22, 3 (2010), 375–378. doi:10.1007/s10648-010-9145-4

    work page doi:10.1007/s10648-010-9145-4 2010

  47. [47]

    1978.Mind in Society: Development of Higher Psychological Processes

    Lev Semenovich Vygotsky. 1978.Mind in Society: Development of Higher Psychological Processes. Harvard University Press, Cambridge, MA. doi:10.2307/j.ctvjf9vz4

    work page doi:10.2307/j.ctvjf9vz4 1978

  48. [48]

    Nahathai Wongpakaran, Tinakon Wongpakaran, Danny Wedding, and Kilem L Gwet. 2013. A comparison of Cohen’s Kappa and Gwet’s AC1 when calculating inter-rater reliability coefficients: a study conducted with personality disorder samples.BMC Medical Research Methodology13 (2013), 61. doi:10.1186/1471-2288-13-61

    work page doi:10.1186/1471-2288-13-61 2013

  49. [49]

    Caroline M Wu, Esther Schulz, Timothy J Pleskac, and Maarten Speekenbrink. 2022. Time pressure changes how people explore and respond to uncertainty.Scientific Reports12, 1 (2022), 4122. doi:10.1038/s41598-022-07901-1

    work page doi:10.1038/s41598-022-07901-1 2022

  50. [50]

    Make a program using the pdf document instructions and the outline provided in the .py file

    Zihan Zhou, Wei Gao, Yifei Li, and Jie Yu. 2024. Developing an interaction framework for human-large language models collaboration in creative tasks: Insights from UX professionals’ communication with ChatGPT.A vailable at SSRN6 (2024), 1–47. doi:10.2139/ssrn.4853257 Tracing Prompt-Level Trajectories to Understand Student Learning with AI in Programming E...

    work page doi:10.2139/ssrn.4853257 2024