pith. machine review for the scientific record. sign in

arxiv: 2604.06200 · v1 · submitted 2026-03-13 · 💻 cs.CY · cs.AI

Recognition: 2 theorem links

· Lean Theorem

Thinking in Graphs with CoMAP: A Shared Visual Workspace for Designing Project-Based Learning

Ruijia Li , Bo Jiang
Authors on Pith no claims yet

Pith reviewed 2026-05-15 12:11 UTC · model grok-4.3

classification 💻 cs.CY cs.AI
keywords project-based learninggraph-based collaborationshared visual workspacedual-modality AIhuman-AI partnershipeducator design toolsdistributed cognition
0
0 comments X

The pith

A shared graph workspace with dual-modality AI improves educators' project-based learning design over dialogue-only systems.

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

Designing project-based learning requires handling many interdependent parts that linear tools and simple chat AI handle poorly because they lack persistent shared context. CoMAP introduces a graph-based shared visual workspace backed by dual-modality AI to turn design into a visible, nonlinear, collaborative process grounded in distributed cognition. The system changes human-AI interaction from a back-and-forth prompt loop into a transparent partnership where educators can see, edit, and build on the same artifact. A study with 30 educators found that this approach produced clear gains in design expression, divergent thinking, and iterative practice compared with a dialogue-only baseline. If the claim holds, artifact-centered visual methods can lower cognitive load while giving teachers more control over their creative work.

Core claim

CoMAP provides a shared visual workspace with dual-modality AI support that embodies a graph-based collaboration paradigm, transforming the human-AI relationship from a prompt-and-response loop into a transparent and equitable partnership and producing measurable gains in design expression, divergent thinking, and iterative practice among 30 educators.

What carries the argument

CoMAP's graph-based shared visual workspace with dual-modality AI support that supplies persistent, shared context for nonlinear design collaboration.

If this is right

  • Educators can manage interdependent PBL components without forcing them into linear sequences.
  • Persistent shared artifacts support reflective collaboration and reduce the need to restate context.
  • Dual-modality AI assistance helps users stay in control of the creative process instead of following AI suggestions passively.
  • The approach lowers cognitive load while increasing trust in the human-AI partnership.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same graph-plus-AI structure could be tested for collaborative design tasks outside education, such as curriculum planning or product development.
  • Longer deployments might reveal whether improved teacher designs lead to measurable differences in student project outcomes.
  • Adding explicit version history or conflict-resolution tools to the graph workspace could further strengthen iterative practice.

Load-bearing premise

The measured gains come mainly from the graph-based workspace and dual-modality AI rather than from novelty, specific interface choices, or differences in how engaged participants felt.

What would settle it

A follow-up study in which the same educators use both CoMAP and the dialogue baseline for multiple matched sessions while measuring and controlling for novelty effects, then finding no reliable difference in design quality or iteration counts.

Figures

Figures reproduced from arXiv: 2604.06200 by Bo Jiang, Ruijia Li.

Figure 1
Figure 1. Figure 1: This figure conceptually contrasts two distinct paradigms for human-AI collaboration. (a) Represents the traditional [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The two-stage formative study design. In Stage 1, we conducted semi-structured interviews centered on participants’ [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Overview of the CoMAP system’s interactive components and the flow of distributed cognition. This architecture [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The visual grammar and interactive states of CoMAP nodes. (a) illustrates the six basic node types: Learner Analysis [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Two export modes supported by CoMAP: (a) an editable linear lesson plan document for administrative or documen [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The CoMAP Global Agent’s conversational workflow. (a) The Global Agent observes the entire design canvas and [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: The "before-and-after" comparison UI for CoMAP’s Local Agents. (Left) The [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
read the original abstract

Designing project-based learning (PBL) demands managing highly interdependent components, a task that both traditional linear tools and purely conversational AI struggle with. Traditional tools fail to capture the non-linear nature of creative design, while conversational systems lack the persistent, shared context necessary for reflective collaboration. Grounded in theories of distributed cognition, we introduce CoMAP, a system that embodies a graph-based collaboration paradigm. By providing a shared visual workspace with dual-modality AI support, CoMAP transforms the human-AI relationship from a prompt-and-response loop into a transparent and equitable partnership. Our study with 30 educators shows CoMAP significantly improves teachers' design expression, divergent thinking, and iterative practice compared to a dialogue-only baseline. These findings demonstrate how a nonlinear, artifact-centric approach can foster trust, reduce cognitive load, and \textcolor{fix}{support} educators to take control of their creative process. Our contributions are available at: https://comap2025.github.io/.

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

3 major / 2 minor

Summary. The paper introduces CoMAP, a graph-based shared visual workspace with dual-modality AI support for designing project-based learning (PBL). Grounded in distributed cognition theory, the system aims to shift human-AI interaction from linear prompt-response loops to a nonlinear, artifact-centric partnership that supports persistent shared context. A comparative study with 30 educators reports that CoMAP significantly improves design expression, divergent thinking, and iterative practice relative to a dialogue-only baseline.

Significance. If the empirical results hold after rigorous validation, the work could advance HCI and educational technology by demonstrating the value of graph-based interfaces over purely conversational AI for complex, interdependent creative tasks. It provides a concrete system embodiment of distributed cognition principles and highlights potential benefits in reducing cognitive load and building trust during collaborative design.

major comments (3)
  1. [Abstract] Abstract: the central claim that the 30-educator study 'shows CoMAP significantly improves' design expression, divergent thinking, and iterative practice is unsupported by any reported statistical tests, p-values, effect sizes, confidence intervals, or power analysis, leaving the magnitude and reliability of the reported gains unassessable.
  2. [User Study] User Study description: no details are given on experimental controls (e.g., participant blinding, matched novelty between conditions, counterbalancing, or pre-registration), task design, or potential confounds such as differential engagement or interface appeal, which are required to attribute observed differences specifically to the graph workspace and dual-modality AI.
  3. [Abstract] Abstract and system description: the terms 'dual-modality AI support' and 'transparent and equitable partnership' are introduced without precise operational definitions or examples of how the AI integrates with the graph workspace, making it difficult to evaluate the claimed paradigm shift.
minor comments (2)
  1. [Abstract] Abstract: the LaTeX command 'textcolor{fix}{support}' is an artifact and should be replaced with plain text 'support'.
  2. The contributions link (https://comap2025.github.io/) should be checked to ensure all promised materials (code, data, or system artifacts) are actually available and documented.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their thoughtful and constructive comments. We agree that the manuscript requires major revisions to strengthen the reporting of statistical results, experimental controls, and definitional clarity. We will address each point in the revised version.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that the 30-educator study 'shows CoMAP significantly improves' design expression, divergent thinking, and iterative practice is unsupported by any reported statistical tests, p-values, effect sizes, confidence intervals, or power analysis, leaving the magnitude and reliability of the reported gains unassessable.

    Authors: We acknowledge this limitation in the current manuscript. In the revised manuscript, we will include detailed statistical tests (e.g., t-tests or ANOVA with p-values), effect sizes (Cohen's d), confidence intervals, and a post-hoc power analysis to substantiate the claims of significant improvement. revision: yes

  2. Referee: [User Study] User Study description: no details are given on experimental controls (e.g., participant blinding, matched novelty between conditions, counterbalancing, or pre-registration), task design, or potential confounds such as differential engagement or interface appeal, which are required to attribute observed differences specifically to the graph workspace and dual-modality AI.

    Authors: We agree with the referee that these details are missing from the current manuscript. In the revised version, we will include comprehensive descriptions of the experimental controls, including participant assignment, counterbalancing, pre-registration status, task design, and analysis of potential confounds to better attribute the observed differences. revision: yes

  3. Referee: [Abstract] Abstract and system description: the terms 'dual-modality AI support' and 'transparent and equitable partnership' are introduced without precise operational definitions or examples of how the AI integrates with the graph workspace, making it difficult to evaluate the claimed paradigm shift.

    Authors: We will revise the abstract and system description to provide precise operational definitions. 'Dual-modality AI support' will be defined as the AI's capability to both interpret user inputs in text and directly manipulate the graph structure. 'Transparent and equitable partnership' will be operationalized as the AI's suggestions being visible, editable, and reversible within the shared workspace. Concrete examples of AI-graph integration will be added. revision: yes

Circularity Check

0 steps flagged

No significant circularity: empirical study claim stands independently

full rationale

The paper's central claim rests on an empirical user study with 30 educators comparing CoMAP to a dialogue-only baseline, reporting improvements in design expression, divergent thinking, and iterative practice. No mathematical derivations, equations, fitted parameters, or predictive models are present that could reduce to inputs by construction. The system description references grounding in distributed cognition theories, but this serves as external conceptual framing rather than a self-citation chain or self-definitional loop that bears the load of the results. The study findings are presented as direct observations, rendering the overall argument self-contained against external benchmarks with no circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on the assumption that distributed cognition theory applies directly to AI-augmented design tools and that a 30-participant study can demonstrate general improvements in creative practice.

axioms (1)
  • domain assumption Distributed cognition theory provides a valid foundation for designing shared visual AI workspaces.
    Invoked in the abstract to ground the graph-based paradigm.
invented entities (1)
  • CoMAP system no independent evidence
    purpose: Embodiment of graph-based collaboration paradigm with dual-modality AI
    New artifact introduced to transform human-AI interaction; no independent evidence outside the paper's own description and study.

pith-pipeline@v0.9.0 · 5463 in / 1278 out tokens · 56810 ms · 2026-05-15T12:11:47.832030+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

84 extracted references · 84 canonical work pages

  1. [1]

    Chadia Abras, Diane Maloney-Krichmar, Jenny Preece, et al. 2004. User-centered design.Bainbridge, W. Encyclopedia of Human-Computer Interaction. Thousand Oaks: Sage Publications37, 4 (2004), 445–456

    work page 2004

  2. [2]

    Ian Arawjo, Chelse Swoopes, Priyan Vaithilingam, Martin Wattenberg, and Elena L Glassman. 2024. Chainforge: A visual toolkit for prompt engineering and llm hypothesis testing. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–18

    work page 2024

  3. [3]

    Michael A Arbib. 1992. Schema theory.The encyclopedia of artificial intelligence 2 (1992), 1427–1443

    work page 1992

  4. [4]

    Jiwak Raj Bajracharya. 2019. Instructional design and models: ASSURE and Kemp. Journal of Education and Research9, 2 (2019), 1–8

    work page 2019

  5. [5]

    Liam J Bannon. 1995. From human factors to human actors: The role of psychology and human-computer interaction studies in system design. InReadings in human– computer interaction. Elsevier, 205–214

    work page 1995

  6. [6]

    Brigid JS Barron, Daniel L Schwartz, Nancy J Vye, Allison Moore, Anthony Petrosino, Linda Zech, and John D Bransford. 2014. Doing with understanding: Lessons from research on problem-and project-based learning. InLearning through problem solving. Psychology Press, 271–311

    work page 2014

  7. [7]

    Mary Jo Bitner, Amy L Ostrom, and Felicia N Morgan. 2008. Service blueprinting: a practical technique for service innovation.California management review50, 3 (2008), 66–94

    work page 2008

  8. [8]

    Javier Borge-Holthoefer and Alex Arenas. 2010. Semantic networks: Structure and dynamics.Entropy12, 5 (2010), 1264–1302

    work page 2010

  9. [9]

    2009.Instructional design: The ADDIE approach

    Robert Maribe Branch and İlhan Varank. 2009.Instructional design: The ADDIE approach. Vol. 722. Springer

    work page 2009

  10. [10]

    Andrew Brasher, Gráinne Conole, Simon Cross, Martin Weller, Paul Clark, and Juliette White. 2008. CompendiumLD–a tool for effective, efficient and creative learning design. (2008)

    work page 2008

  11. [11]

    2011.The violent effigy: a study of Dickens’ imagination

    John Carey. 2011.The violent effigy: a study of Dickens’ imagination. Faber & Faber

    work page 2011

  12. [12]

    Ismail Celik. 2023. Towards Intelligent-TPACK: An empirical study on teachers’ professional knowledge to ethically integrate artificial intelligence (AI)-based tools into education.Computers in human behavior138 (2023), 107468

    work page 2023

  13. [13]

    Xiaojun Chen, Shengbin Jia, and Yang Xiang. 2020. A review: Knowledge reason- ing over knowledge graph.Expert systems with applications141 (2020), 112948

    work page 2020

  14. [14]

    Christine Chin and Li-Gek Chia. 2006. Problem-based learning: Using ill- structured problems in biology project work.Science Education90, 1 (2006), 44–67

    work page 2006

  15. [15]

    Allan M Collins and Elizabeth F Loftus. 1975. A spreading-activation theory of semantic processing.Psychological review82, 6 (1975), 407

    work page 1975

  16. [16]

    Allan M Collins and M Ross Quillian. 1969. Retrieval time from semantic memory. Journal of verbal learning and verbal behavior8, 2 (1969), 240–247

    work page 1969

  17. [17]

    Bill Cope, Mary Kalantzis, and Duane Searsmith. 2021. Artificial intelligence for education: Knowledge and its assessment in AI-enabled learning ecologies. Educational philosophy and theory53, 12 (2021), 1229–1245

    work page 2021

  18. [18]

    James Dalziel. 2003. Implementing learning design: The learning activity man- agement system (LAMS). InAustralasian Society for Computers in Learning in Tertiary Education Conference (20th: 2003). Australasian Society for Computers in Learning in Tertiary Education, 593–596

    work page 2003

  19. [19]

    Walter Dick. 1996. The Dick and Carey model: Will it survive the decade? Educational technology research and development44, 3 (1996), 55–63

    work page 1996

  20. [20]

    Shelley D Dionne, Hiroki Sayama, Chanyu Hao, and Benjamin James Bush. 2010. The role of leadership in shared mental model convergence and team performance improvement: An agent-based computational model.The Leadership Quarterly 21, 6 (2010), 1035–1049

    work page 2010

  21. [21]

    Diana HJM Dolmans, Willem De Grave, Ineke HAP Wolfhagen, and Cees PM Van Der Vleuten. 2005. Problem-based learning: Future challenges for educational practice and research.Medical education39, 7 (2005), 732–741

    work page 2005

  22. [22]

    Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, et al . 2024. A survey on in-context learning. InProceedings of the 2024 conference on empirical methods in natural language processing. 1107–1128

    work page 2024

  23. [23]

    Paul Dourish and Victoria Bellotti. 1992. Awareness and coordination in shared workspaces. InProceedings of the 1992 ACM conference on Computer-supported cooperative work. 107–114

    work page 1992

  24. [24]

    Carla M Evans. 2019. Student outcomes from high-quality project-based learning: A case study for PBLWorks.National Center for the Improvement of Educational Assessment135 (2019), 2020–2001

    work page 2019

  25. [25]

    Klaus Fiedler. 2013. Affective states trigger processes of assimilation and accom- modation. InTheories of mood and cognition. Psychology Press, 85–98

    work page 2013

  26. [26]

    Nitesh Goyal and Susan R Fussell. 2016. Effects of sensemaking translucence on distributed collaborative analysis. InProceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing. 288–302

    work page 2016

  27. [27]

    Sandra G Hart and Lowell E Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. InAdvances in psy- chology. Vol. 52. Elsevier, 139–183

    work page 1988

  28. [28]

    Jeffrey Heer and Ben Shneiderman. 2012. Interactive dynamics for visual analysis: A taxonomy of tools that support the fluent and flexible use of visualizations. Queue10, 2 (2012), 30–55

    work page 2012

  29. [29]

    Davinia Hernández-Leo, Eloy D Villasclaras Fernandez, Juan I Asensio-Pérez, Yannis Dimitriadis, Iván Jorrín-Abellán, Inés Ruiz-Requies, and Bartolomé Rubia- Avi. 2006. COLLAGE: A collaborative Learning Design editor based on patterns. Educational Technology & Society9, 1 (2006), 58–71

    work page 2006

  30. [30]

    2002.Understanding evolutionary use of groupware

    Marike Hettinga. 2002.Understanding evolutionary use of groupware. Telematica Instituut The Netherlands

    work page 2002

  31. [31]

    James Hollan, Edwin Hutchins, and David Kirsh. 2000. Distributed cognition: toward a new foundation for human-computer interaction research.ACM Trans- actions on Computer-Human Interaction (TOCHI)7, 2 (2000), 174–196. CHI ’26, April 13–17, 2026, Barcelona, Spain Ruijia Li et al

    work page 2000

  32. [32]

    Bihao Hu, Longwei Zheng, Jiayi Zhu, Lishan Ding, Yilei Wang, and Xiaoqing Gu. 2024. Teaching plan generation and evaluation with GPT-4: Unleashing the potential of LLM in instructional design.IEEE Transactions on Learning Technologies17 (2024), 1445–1459

    work page 2024

  33. [33]

    1995.Cognition in the Wild

    Edwin Hutchins. 1995.Cognition in the Wild. MIT press

    work page 1995

  34. [34]

    Edwin Hutchins. 2000. Distributed cognition.International encyclopedia of the social and behavioral sciences138, 1 (2000), 1–10

    work page 2000

  35. [35]

    Rui Jia, Yuang Wei, Ruijia Li, Yuan-Hao Jiang, Xinyu Xie, Yaomin Shen, Min Zhang, and Bo Jiang. 2025. DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation Framework.arXiv preprint arXiv:2509.24821(2025)

    work page arXiv 2025

  36. [36]

    Yuan-Hao Jiang, Ruijia Li, Yizhou Zhou, Changyong Qi, Hanglei Hu, Yuang Wei, Bo Jiang, and Yonghe Wu. 2024. AI agent for education: von Neumann multi-agent system framework.arXiv preprint arXiv:2501.00083(2024)

    work page arXiv 2024

  37. [37]

    Yuan-Hao Jiang, Tian-Yi Liu, Xinlin Zhuang, Hanglei Hu, Ruijia Li, and Rui Jia. 2024. Enhancing educational practices with multi-agent systems: A review. Enhancing Educational Practices: Strategies for Assessing and Improving Learning Outcomes(2024), 47–65

    work page 2024

  38. [38]

    Eulho Jung, Rachel Lim, and Dongho Kim. 2022. A schema-based instructional design model for self-paced learning environments.Education Sciences12, 4 (2022), 271

    work page 2022

  39. [39]

    Maaike Kleinsmann, Jan Buijs, and Rianne Valkenburg. 2005. Managing shared understanding in collaborative design projects. InDS 35: Proceedings ICED 05, the 15th International Conference on Engineering Design, Melbourne, Australia, 15.-18.08. 2005

    work page 2005

  40. [40]

    2013.Principles of Gestalt psychology

    Kurt Koffka. 2013.Principles of Gestalt psychology. routledge

    work page 2013

  41. [41]

    Spencer C Kohn, Ewart J De Visser, Eva Wiese, Yi-Ching Lee, and Tyler H Shaw

    work page

  42. [42]

    Measurement of trust in automation: A narrative review and reference guide.Frontiers in psychology12 (2021), 604977

    work page 2021

  43. [43]

    Dimitra Kokotsaki, Victoria Menzies, and Andy Wiggins. 2016. Project-based learning: A review of the literature.Improving schools19, 3 (2016), 267–277

    work page 2016

  44. [44]

    Glenn E Krasner, Stephen T Pope, et al. 1988. A description of the model-view- controller user interface paradigm in the smalltalk-80 system.Journal of object oriented programming1, 3 (1988), 26–49

    work page 1988

  45. [45]

    Jill H Larkin and Herbert A Simon. 1987. Why a diagram is (sometimes) worth ten thousand words.Cognitive science11, 1 (1987), 65–100

    work page 1987

  46. [46]

    2015.Setting the standard for project based learning

    John Larmer, John Mergendoller, and Suzie Boss. 2015.Setting the standard for project based learning. Ascd

    work page 2015

  47. [47]

    Susan Leigh Star. 2010. This is not a boundary object: Reflections on the origin of a concept.Science, technology, & human values35, 5 (2010), 601–617

    work page 2010

  48. [48]

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems33 (2020), 9459–9474

    work page 2020

  49. [49]

    Ruijia Li, Yuan-Hao Jiang, Jiatong Wang, and Bo Jiang. 2025. How Real Is AI Tu- toring? Comparing Simulated and Human Dialogues in One-on-One Instruction. arXiv preprint arXiv:2509.01914(2025)

    work page arXiv 2025

  50. [50]

    Ruijia Li, Yuan-Hao Jiang, Yiting Wang, Hanglei Hu, and Bo Jiang. 2024. A Large Language Model-Enabled Solution for the Automatic Generation of Situated Multiple-Choice Math Questions. InConference Proceedings of the 28th Global Chinese Conference on Computers in Education (GCCCE 2024). 130–136

    work page 2024

  51. [51]

    Ruijia Li, Yiting Wang, Chanjin Zheng, Yuan-Hao Jiang, and Bo Jiang. 2024. Generating contextualized mathematics multiple-choice questions utilizing large language models. InInternational Conference on Artificial Intelligence in Education. Springer, 494–501

    work page 2024

  52. [52]

    Marcia C Linn, Douglas Clark, and James D Slotta. 2003. WISE design for knowl- edge integration.Science education87, 4 (2003), 517–538

    work page 2003

  53. [53]

    Thom Markham, John Larmer, and Jason Ravitz. 2003. Project based learning handbook: A guide to standards-focused project based learning for middle and high school teachers.(No Title)(2003)

    work page 2003

  54. [54]

    John A McLaughlin and Gretchen B Jordan. 1999. Logic models: a tool for telling your programs performance story.Evaluation and program planning22, 1 (1999), 65–72

    work page 1999

  55. [55]

    John R Mergendoller. 2018. Defining high quality PBL: A look at the research. High Quality Project Based Learning(2018)

    work page 2018

  56. [56]

    Emily C Miller and Joseph S Krajcik. 2019. Promoting deep learning through project-based learning: A design problem.Disciplinary and interdisciplinary science education research1, 1 (2019), 7

    work page 2019

  57. [57]

    2014.Things that make us smart

    Don Norman. 2014.Things that make us smart. Diversion Books

    work page 2014

  58. [58]

    Rock Yuren Pang, Hope Schroeder, Kynnedy Simone Smith, Solon Barocas, Ziang Xiao, Emily Tseng, and Danielle Bragg. 2025. Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–20

    work page 2025

  59. [59]

    Jeff Pankin. 2013. Schema theory.Massachusetts Institute of Technology(2013)

    work page 2013

  60. [60]

    LM Paquette Gilbert and Lundgren-Cayrol Karin. 2011. The mot+ visual language for knowledge based instructional design

    work page 2011

  61. [61]

    1966.Semantic memory

    M Ross Quillan. 1966.Semantic memory. Technical Report

    work page 1966

  62. [62]

    Mark Rowlands. 2009. Extended cognition and the mark of the cognitive.Philo- sophical Psychology22, 1 (2009), 1–19

    work page 2009

  63. [63]

    David E Rumelhart. 2017. Schemata: The building blocks of cognition. InTheo- retical issues in reading comprehension. Routledge, 33–58

    work page 2017

  64. [64]

    Hanshu Shen, Lyukesheng Shen, Wenqi Wu, and Kejun Zhang. 2025. Ideationweb: Tracking the evolution of design ideas in human-ai co-creation. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–19

    work page 2025

  65. [65]

    Sharon E Smaldino, Deborah L Lowther, James D Russell, and Clif Mims. 2008. Instructional technology and media for learning. (2008)

    work page 2008

  66. [66]

    Neville A Stanton. 2006. Hierarchical task analysis: Developments, applications, and extensions.Applied ergonomics37, 1 (2006), 55–79

    work page 2006

  67. [67]

    Susan Leigh Star and James R Griesemer. 1989. Institutional ecology,translations’ and boundary objects: Amateurs and professionals in Berkeley’s Museum of Vertebrate Zoology, 1907-39.Social studies of science19, 3 (1989), 387–420

    work page 1989

  68. [68]

    Mark Steyvers and Joshua B Tenenbaum. 2005. The large-scale structure of semantic networks: Statistical analyses and a model of semantic growth.Cognitive science29, 1 (2005), 41–78

    work page 2005

  69. [69]

    John W Thomas. 2000. A review of research on project-based learning

    work page 2000

  70. [70]

    Dina Tsybulsky and Yulia Muchnik-Rozanov. 2019. The development of student- teachers’ professional identity while team-teaching science classes using a project- based learning approach: A multi-level analysis.Teaching and Teacher Education 79 (2019), 48–59

    work page 2019

  71. [71]

    Yi-Fu Tuan. 1980. The significance of the artifact.Geographical review(1980), 462–472

    work page 1980

  72. [72]

    Barbara Tversky, Julie Bauer Morrison, and Mireille Betrancourt. 2002. Animation: can it facilitate?International journal of human-computer studies57, 4 (2002), 247–262

    work page 2002

  73. [73]

    Nasanbayar Ulzii-Orshikh and John Dougherty. 2020. Iteration with intention: Project-based learning of computational thinking. InProceedings of the 51st ACM Technical Symposium on Computer Science Education. 1289–1289

    work page 2020

  74. [74]

    Sira Vegas, Cecilia Apa, and Natalia Juristo. 2015. Crossover designs in software engineering experiments: Benefits and perils.IEEE Transactions on Software Engineering42, 2 (2015), 120–135

    work page 2015

  75. [75]

    Brady Wagoner. 2013. Bartlett’s concept of schema in reconstruction.Theory & Psychology23, 5 (2013), 553–575

    work page 2013

  76. [76]

    Jayne Wallace, John McCarthy, Peter C Wright, and Patrick Olivier. 2013. Making design probes work. InProceedings of the SIGCHI conference on human factors in computing systems. 3441–3450

    work page 2013

  77. [77]

    Sharon Alayne Widmayer. 2004. Schema theory: An introduction.Retrieved December26 (2004), 2004

    work page 2004

  78. [78]

    2011.The understanding by design guide to creating high-quality units

    Grant Wiggins and Jay McTighe. 2011.The understanding by design guide to creating high-quality units. ASCD

    work page 2011

  79. [79]

    2005.Understanding by design

    Grant P Wiggins and Jay McTighe. 2005.Understanding by design. Ascd

    work page 2005

  80. [80]

    Tongshuang Wu, Ellen Jiang, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, and Carrie J Cai. 2022. Promptchainer: Chaining large language model prompts through visual programming. InCHI Conference on Human Factors in Computing Systems Extended Abstracts. 1–10

    work page 2022

Showing first 80 references.