pith. sign in

arxiv: 2606.19216 · v1 · pith:YJBYRH4Enew · submitted 2026-06-17 · 💻 cs.SE · cs.HC

No Two Developers Think Alike: How Problem-Solving Styles and Experience Shape Needs in Conversational Interaction with Copilot

Jonan Richards , Bruno Alves de Oliveira , Iury Oliveira , Igor Wiese , Mairieli Wessel This is my paper

Pith reviewed 2026-06-26 20:11 UTC · model grok-4.3

classification 💻 cs.SE cs.HC
keywords cognitive diversityconversational programming assistantsGitHub Copilotinteraction modesdeveloper needsproblem-solving stylesexperience profiles
0
0 comments X

The pith

Cognitive diversity in problem-solving styles and experience produces five distinct modes and ten needs when developers interact with Copilot chat.

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

The study observes 27 professional developers and students using GitHub Copilot's conversational interface in a think-aloud setting. It identifies five recurring interaction modes and ten underlying needs, then connects both to measurable differences in how participants approach problem solving and to their years of experience. If these links hold, conversational coding tools cannot assume a uniform user and must instead accommodate varied cognitive approaches or risk failing to support sizable groups of developers.

Core claim

Cognitive diversity in problem-solving styles and experience shapes developers' needs and interaction modes with conversational programming assistants, as shown by five distinct modes and ten underlying needs identified in the study, forming a conceptual model that links these elements to developer profiles.

What carries the argument

Conceptual model connecting five interaction modes, ten needs, problem-solving styles, and experience profiles.

If this is right

  • Designers of conversational assistants should support multiple interaction modes rather than a single workflow.
  • Experience level influences which needs dominate, so onboarding or defaults can be adjusted by user background.
  • Researchers can use the model to categorize future observations of developer-AI conversations.
  • Practitioners can match tool features to the problem-solving styles present in their teams.

Where Pith is reading between the lines

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

  • Detecting a developer's style from early chat turns could let the assistant adapt its response style on the fly.
  • The same diversity patterns may appear in other conversational coding tools, suggesting a general principle for AI pair-programming interfaces.

Load-bearing premise

The sample of 27 participants and the think-aloud protocol produce representative observations of real interaction needs that generalize beyond the studied group.

What would settle it

A replication study with a larger and more varied developer sample that finds no systematic association between measured problem-solving styles or experience levels and the observed interaction modes would falsify the central claim.

Figures

Figures reproduced from arXiv: 2606.19216 by Bruno Alves de Oliveira, Igor Wiese, Iury Oliveira, Jonan Richards, Mairieli Wessel.

Figure 1
Figure 1. Figure 1: Distributions in participants’ cognitive profiles, consisting of an [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Interaction mode distributions per participant-task combination. Av [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Expected distributions per mode of the number of prompts per task, [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Developer needs (purple) and interaction modes (blue) when in [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Spearman rank correlations between interaction modes and experience [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
read the original abstract

Conversational LLM-based ``programming assistants'' provide a range of benefits to developers. However, recent studies demonstrate the variety in individual developers' needs regarding programming assistants, and challenges encountered by only specific groups of developers. In this study, we explore the role of cognitive diversity in shaping interactions with GitHub Copilot chat. Through a mixed-methods think aloud study with 27 professional developers and students, we characterize 5 distinct ``interaction modes'' and 10 underlying needs in developers' interactions, forming a conceptual model. We characterize links between these modes, needs, and developers' problem-solving styles and experience profiles, showing how cognitive diversity may shape developers' interactions. We provide insights and recommendations for researchers and practitioners on how to design, research, and employ programming assistants to better account for diverse developer needs.

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 reports results from a mixed-methods think-aloud study with 27 professional developers and students interacting with GitHub Copilot chat. It identifies five distinct interaction modes and ten underlying needs, presents a conceptual model linking these to problem-solving styles and experience profiles, and offers design recommendations for conversational programming assistants that account for cognitive diversity.

Significance. If the modes and needs are shown to be robust, the work provides empirical evidence that individual differences in problem-solving and experience materially affect how developers use LLM-based assistants. This supplies a concrete vocabulary (five modes, ten needs) that can guide future tool design and evaluation studies; the think-aloud data collection is a direct strength when the analysis is adequately documented.

major comments (3)
  1. [Methods] Methods section: the description of the qualitative analysis supplies no information on the coding process, inter-rater agreement, participant selection criteria, or validation steps. Because the five modes and ten needs are presented as direct empirical outcomes of this analysis, the absence of these details makes it impossible to assess whether the conceptual model is over-fitted to the observed cohort.
  2. [Results] Results / §4 (or equivalent): the reported links between interaction modes, needs, and experience profiles rest on a 27-participant non-probability sample without evidence of theoretical saturation or stratification by experience level. This directly affects the central claim that cognitive diversity shapes the observed modes and needs.
  3. [Discussion] Discussion: the reactivity of the think-aloud protocol (known to alter natural strategy and verbalization) is not addressed, yet the interaction modes are defined from these verbalized sessions; this is load-bearing for claims about unprompted developer behavior.
minor comments (2)
  1. [Abstract] Abstract: the phrase 'mixed-methods' is used but the quantitative component is not described; clarify whether any quantitative measures (e.g., frequency counts of modes) were collected and how they were analyzed.
  2. [Introduction] Notation: the terms 'interaction modes' and 'needs' are introduced without an early explicit definition or table summarizing the ten needs; a summary table would improve readability.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive feedback. We address each major comment below, indicating planned revisions where appropriate.

read point-by-point responses

  1. Referee: [Methods] Methods section: the description of the qualitative analysis supplies no information on the coding process, inter-rater agreement, participant selection criteria, or validation steps. Because the five modes and ten needs are presented as direct empirical outcomes of this analysis, the absence of these details makes it impossible to assess whether the conceptual model is over-fitted to the observed cohort.

    Authors: We agree that the Methods section lacks sufficient detail on the qualitative analysis. In the revised manuscript we will expand this section to describe the iterative coding process (open coding followed by thematic grouping), inter-rater reliability procedures (including how disagreements were resolved), participant selection criteria (purposive sampling targeting diversity in roles and experience), and validation steps such as peer review of codes. These additions will allow readers to evaluate the derivation of the five modes and ten needs. revision: yes

  2. Referee: [Results] Results / §4 (or equivalent): the reported links between interaction modes, needs, and experience profiles rest on a 27-participant non-probability sample without evidence of theoretical saturation or stratification by experience level. This directly affects the central claim that cognitive diversity shapes the observed modes and needs.

    Authors: The referee is correct that the manuscript provides no formal evidence of theoretical saturation and does not describe stratification. In revision we will add an explicit limitations paragraph noting the convenience sample of 27 participants, the absence of a formal saturation assessment, and the non-stratified recruitment. We will reframe the central claims as exploratory patterns observed in a diverse but non-probability sample rather than generalizable conclusions about cognitive diversity. revision: yes

  3. Referee: [Discussion] Discussion: the reactivity of the think-aloud protocol (known to alter natural strategy and verbalization) is not addressed, yet the interaction modes are defined from these verbalized sessions; this is load-bearing for claims about unprompted developer behavior.

    Authors: We acknowledge that the potential reactivity of the think-aloud method is not discussed. In the revised Discussion we will add a paragraph addressing this issue, citing relevant HCI literature on think-aloud reactivity, noting its possible influence on verbalized strategies, and suggesting that future studies could triangulate with less intrusive methods such as silent observation or log analysis. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical inductive model from qualitative data

full rationale

The paper reports a mixed-methods think-aloud study with 27 participants that inductively identifies five interaction modes and ten needs, then links them to problem-solving styles and experience. No equations, fitted parameters, predictions, or first-principles derivations exist. The conceptual model is presented as an outcome of direct observation and thematic analysis rather than any self-definitional loop, renamed known result, or load-bearing self-citation chain. The central claim therefore does not reduce to its own inputs by construction and remains self-contained as standard empirical work.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

This is a qualitative empirical study; the central claim rests on standard HCI assumptions about think-aloud validity and participant representativeness rather than formal axioms or fitted parameters.

axioms (1)
  • domain assumption Think-aloud verbalizations accurately reflect participants' internal problem-solving processes without substantial distortion from the act of speaking.
    Invoked implicitly by the choice of think-aloud method in the abstract.
invented entities (1)
  • Interaction modes no independent evidence
    purpose: Categorize observed developer behaviors with Copilot chat
    Derived categories presented as new constructs; no external validation or falsifiable prediction mentioned in abstract.

pith-pipeline@v0.9.1-grok · 5684 in / 1126 out tokens · 24141 ms · 2026-06-26T20:11:33.598181+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

36 extracted references · 17 canonical work pages

  1. [1]

    ACM Transactions on Software Engineering and Methodology33(8), 1–79 (2024)

    X. Hou, Y . Zhao, Y . Liu, Z. Yang, K. Wang, L. Li, X. Luo, D. Lo, J. Grundy, and H. Wang, “Large Language Models for Software Engineering: A Systematic Literature Review,”ACM Transactions on Software Engineering and Methodology, p. 3695988, Sep. 2024. [Online]. Available: https://dl.acm.org/doi/10.1145/3695988

    work page doi:10.1145/3695988 2024

  2. [2]

    Program Synthesis with Large Language Models,

    J. Austin, A. Odena, M. Nye, M. Bosma, H. Michalewski, D. Dohan, E. Jiang, C. Cai, M. Terry, Q. Le, and C. Sutton, “Program Synthesis with Large Language Models,” Aug. 2021, arXiv:2108.07732 [cs]. [Online]. Available: http://arxiv.org/abs/2108.07732

    Pith/arXiv arXiv 2021

  3. [3]

    Hearst, and Daniel S

    S. I. Ross, F. Martinez, S. Houde, M. Muller, and J. D. Weisz, “The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development,” inProceedings of the 28th International Conference on Intelligent User Interfaces. Sydney NSW Australia: ACM, Mar. 2023, pp. 491–514. [Online]. Available: https://dl.acm.org/doi/10.11...

    work page doi:10.1145/3581641.3584037 2023

  4. [4]

    A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges,

    J. T. Liang, C. Yang, and B. A. Myers, “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, ser. ICSE ’24. New York, NY , USA: Association for Computing Machinery, Feb. 2024, pp. 1–13. [Online]. Available: https://dl.acm.org/doi/...

    work page doi:10.1145/3597503.3608128 2024

  5. [5]

    DevGPT: Studying Developer-ChatGPT Conversations,

    T. Xiao, C. Treude, H. Hata, and K. Matsumoto, “DevGPT: Studying Developer-ChatGPT Conversations,” in2024 IEEE/ACM 21st International Conference on Mining Software Repositories (MSR), Apr. 2024, pp. 227–230. [Online]. Available: https://ieeexplore.ieee.org/ document/10555646/?arnumber=10555646

    arXiv 2024

  6. [6]

    Cognitive Diversity in Teams: A Multidisciplinary Review,

    A. L. Mello and J. R. Rentsch, “Cognitive Diversity in Teams: A Multidisciplinary Review,”Small Group Research, vol. 46, no. 6, pp. 623–658, Dec. 2015. [Online]. Available: https://journals.sagepub.com/ doi/10.1177/1046496415602558

    work page doi:10.1177/1046496415602558 2015

  7. [7]

    Gender and Tenure Diversity in GitHub Teams,

    B. Vasilescu, D. Posnett, B. Ray, M. G. Van Den Brand, A. Serebrenik, P. Devanbu, and V . Filkov, “Gender and Tenure Diversity in GitHub Teams,” inProceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. Seoul Republic of Korea: ACM, Apr. 2015, pp. 3789–3798. [Online]. Available: https://dl.acm.org/doi/10.1145/2702123.2702549

    work page doi:10.1145/2702123.2702549 2015

  8. [8]

    Software engineering team diversity and performance,

    V . Pieterse, D. G. Kourie, and I. P. Sonnekus, “Software engineering team diversity and performance,” inProceedings of the 2006 annual research conference of the South African institute of computer scientists and information technologists on IT research in developing countries. Somerset West South Africa: South African Institute for Computer Scientists a...

    work page doi:10.1145/1216262.1216282 2006

  9. [9]

    Why do we need personality diversity in software engineering?

    L. F. Capretz and F. Ahmed, “Why do we need personality diversity in software engineering?”ACM SIGSOFT Software Engineering Notes, vol. 35, no. 2, pp. 1–11, Mar. 2010. [Online]. Available: https://dl.acm.org/doi/10.1145/1734103.1734111

    work page doi:10.1145/1734103.1734111 2010

  10. [10]

    Page,The difference: How the power of diversity creates better groups, firms, schools, and societies-new edition

    S. Page,The difference: How the power of diversity creates better groups, firms, schools, and societies-new edition. Princeton University Press, 2008

    2008

  11. [11]

    GenderMag: A Method for Evaluating Software’s Gender Inclusiveness,

    M. Burnett, S. Stumpf, J. Macbeth, S. Makri, L. Beckwith, I. Kwan, A. Peters, and W. Jernigan, “GenderMag: A Method for Evaluating Software’s Gender Inclusiveness,”Interacting with Computers, vol. 28, no. 6, pp. 760–787, Nov. 2016. [Online]. Available: https://doi.org/10.1093/iwc/iwv046

    work page doi:10.1093/iwc/iwv046 2016

  12. [12]

    Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMs,

    F. Draxler, D. Buschek, M. Tavast, P. H ¨am¨al¨ainen, A. Schmidt, J. Kulshrestha, and R. Welsch, “Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMs,” Oct. 2023, arXiv:2310.06556 [cs]. [Online]. Available: http://arxiv.org/abs/ 2310.06556

    arXiv 2023

  13. [13]

    Navigating the Complexity of Generative AI Adoption in Software Engineering,

    D. Russo, “Navigating the Complexity of Generative AI Adoption in Software Engineering,”ACM Trans. Softw. Eng. Methodol., vol. 33, no. 5, pp. 135:1–135:50, Jun. 2024. [Online]. Available: https://dl.acm.org/doi/10.1145/3652154

    work page doi:10.1145/3652154 2024

  14. [14]

    Using an LLM to Help With Code Understanding,

    D. Nam, A. Macvean, V . Hellendoorn, B. Vasilescu, and B. Myers, “Using an LLM to Help With Code Understanding,” inProceedings of the IEEE/ACM 46th International Conference on Software Engineering. Lisbon Portugal: ACM, Apr. 2024, pp. 1–13. [Online]. Available: https://dl.acm.org/doi/10.1145/3597503.3639187

    work page doi:10.1145/3597503.3639187 2024

  15. [15]

    An LLM’s Attempts to Adapt to Diverse Software Engineers’ Problem-Solving Styles: More Inclusive & Equitable?

    A. Anderson, D. Piorkowski, M. Burnett, and J. Weisz, “An LLM’s Attempts to Adapt to Diverse Software Engineers’ Problem-Solving Styles: More Inclusive & Equitable?” Mar. 2025, arXiv:2503.11018 [cs]. [Online]. Available: http://arxiv.org/abs/2503.11018

    arXiv 2025

  16. [16]

    How Beginning Programmers and Code LLMs (Mis)read Each Other,

    S. Nguyen, H. M. Babe, Y . Zi, A. Guha, C. J. Anderson, and M. Q. Feldman, “How Beginning Programmers and Code LLMs (Mis)read Each Other,” inProceedings of the CHI Conference on Human Factors in Computing Systems. Honolulu HI USA: ACM, May 2024, pp. 1–26. [Online]. Available: https://dl.acm.org/doi/10.1145/3613904.3642706

    work page doi:10.1145/3613904.3642706 2024

  17. [17]

    Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming,

    M. Kazemitabaar, J. Chow, C. K. T. Ma, B. J. Ericson, D. Weintrop, and T. Grossman, “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. Hamburg Germany: ACM, Apr. 2023, pp. 1–23. [Online]. Available: https://dl.acm.org/doi/10....

    work page doi:10.1145/3544548.3580919 2023

  18. [18]

    How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering,

    R. Choudhuri, D. Liu, I. Steinmacher, M. Gerosa, and A. Sarma, “How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering,” inProceedings of the IEEE/ACM 46th International Conference on Software Engineering. Lisbon Portugal: ACM, Apr. 2024, pp. 1–13. [Online]. Available: https://dl.acm.org/doi/10.1145/3597503.3639201

    work page doi:10.1145/3597503.3639201 2024

  19. [19]

    Grounded Copilot: How Programmers Interact with Code-Generating Models,

    S. Barke, M. B. James, and N. Polikarpova, “Grounded Copilot: How Programmers Interact with Code-Generating Models,”Proceedings of the ACM on Programming Languages, vol. 7, no. OOPSLA1, pp. 78:85– 78:111, Apr. 2023

    2023

  20. [20]

    Cognition in Software Engineering: A Taxonomy and Survey of a Half-Century of Research,

    F. Fagerholm, M. Felderer, D. Fucci, M. Unterkalmsteiner, B. Marculescu, M. Martini, L. G. W. Tengberg, R. Feldt, B. Lehtel ¨a, B. Nagyv ´aradi, and J. Khattak, “Cognition in Software Engineering: A Taxonomy and Survey of a Half-Century of Research,”ACM Computing Surveys, vol. 54, no. 11s, pp. 1–36, Jan. 2022. [Online]. Available: https://dl.acm.org/doi/1...

    work page doi:10.1145/3508359 2022

  21. [21]

    How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering,

    C. Treude and M. A. Gerosa, “How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering,” in 2025 IEEE/ACM Second International Conference on AI Foundation Models and Software Engineering (Forge), Apr. 2025, pp. 236–240

    2025

  22. [22]

    Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice,

    R. Khojah, M. Mohamad, P. Leitner, and F. G. De Oliveira Neto, “Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice,”Proceedings of the ACM on Software Engineering, vol. 1, no. FSE, pp. 1819–1840, Jul. 2024

    2024

  23. [23]

    LLMs are Imperfect, Then What? An Empirical Study on LLM Failures in Software Engineering,

    J. Tie, B. Yao, T. Li, S. I. Ahmed, D. Wang, and S. Zhou, “LLMs are Imperfect, Then What? An Empirical Study on LLM Failures in Software Engineering,” Nov. 2024, arXiv:2411.09916. [Online]. Available: http://arxiv.org/abs/2411.09916

    Pith/arXiv arXiv 2024

  24. [24]

    Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code,

    J. Shin, C. Tang, T. Mohati, M. Nayebi, S. Wang, and H. Hemmati, “Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code,” arXiv:2310.10508, Feb. 2025

    arXiv 2025

  25. [25]

    Gender Differences in Personality Traits of Software Engineers,

    D. Russo and K.-J. Stol, “Gender Differences in Personality Traits of Software Engineers,”IEEE Transactions on Software Engineering, vol. 48, no. 3, pp. 819–834, Mar. 2022, conference Name: IEEE Transactions on Software Engineering. [Online]. Available: https://ieeexplore.ieee.org/document/9120355/?arnumber=9120355

    arXiv 2022

  26. [26]

    How to measure diversity actionably in technology,

    M. M. Hamid, A. Chatterjee, M. Guizani, A. Anderson, F. Moussaoui, S. Yang, I. Escobar, A. Sarma, and M. Burnett, “How to measure diversity actionably in technology,” inEquity, diversity, and inclusion in software engineering: Best practices and insights. Apress Berkeley, CA, 2024, pp. 469–485

    2024

  27. [27]

    The think aloud method: a practical approach to modelling cognitive processes,

    M. W. Van Someren, Y . F. Barnard, and J. A. Sandberg, “The think aloud method: a practical approach to modelling cognitive processes,” London: AcademicPress, vol. 11, no. 6, 1994. [Online]. Available: https://pure.uva.nl/ws/files/716505/149552 Think aloud method.pdf

    1994

  28. [28]

    Perceived Usefulness, Perceived Ease of Use, and User Acceptance of Information Technology,

    F. D. Davis, “Perceived Usefulness, Perceived Ease of Use, and User Acceptance of Information Technology,”MIS Quarterly, vol. 13, no. 3, pp. 319–340, 1989. [Online]. Available: https: //www.jstor.org/stable/249008

    1989

  29. [29]

    Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research,

    S. G. Hart and L. E. Staveland, “Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research,” in Advances in Psychology, ser. Human Mental Workload, P. A. Hancock and N. Meshkati, Eds. North-Holland, Jan. 1988, vol. 52, pp. 139–183. [Online]. Available: https://www.sciencedirect.com/science/ article/pii/S0166411508623869

    1988

  30. [30]

    Replication package for

    J. Richards, B. Alves de Oliveira, I. Oliveira, I. Wiese, and M. Wessel, “Replication package for ”No Two Developers Think Alike: How Problem-Solving Styles and Experience Shape Needs in Conversational Interaction with Copilot”,” Jun. 2026. [Online]. Available: https://doi.org/10.5281/zenodo.20734142

    work page doi:10.5281/zenodo.20734142 2026

  31. [31]

    J. M. Corbin and A. L. Strauss,Basics of qualitative research: techniques and procedures for developing grounded theory, 4th ed. Los Angeles: SAGE, 2015

    2015

  32. [32]

    Discovery of activity patterns using topic models,

    T. Huynh, M. Fritz, and B. Schiele, “Discovery of activity patterns using topic models,” inProceedings of the 10th international conference on Ubiquitous computing. Seoul Korea: ACM, Sep. 2008, pp. 10–19. [Online]. Available: https://dl.acm.org/doi/10.1145/1409635.1409638

    work page doi:10.1145/1409635.1409638 2008

  33. [33]

    Lecture Notes on Compositional Data Analysis

    V . Pawlowsky-Glahn, J. J. Egozcue, and R. Tolosana-Delgado, “Lecture Notes on Compositional Data Analysis.”

  34. [34]

    Human- AI experience in integrated development environments: A systematic literature review,

    A. Sergeyuk, I. Zakharov, E. Koshchenko, and M. Izadi, “Human- AI experience in integrated development environments: A systematic literature review,”Empirical Software Engineering, vol. 31, no. 3, p. 55, May 2026

    2026

  35. [35]

    Affordances in HCI: toward a mediated action perspective,

    V . Kaptelinin and B. Nardi, “Affordances in HCI: toward a mediated action perspective,” inProceedings of the SIGCHI Conference on Human Factors in Computing Systems. Austin Texas USA: ACM, May 2012, pp. 967–976. [Online]. Available: https://dl.acm.org/doi/10. 1145/2207676.2208541

    arXiv 2012

  36. [36]

    Cai, Emily Reif, Narayan Hegde, Jason Hipp, Been Kim, Daniel Smilkov, Martin Wattenberg, Fernanda Viegas, Greg S

    S. Amershi, D. Weld, M. V orvoreanu, A. Fourney, B. Nushi, P. Collisson, J. Suh, S. Iqbal, P. N. Bennett, K. Inkpen, J. Teevan, R. Kikin-Gil, and E. Horvitz, “Guidelines for Human-AI Interaction,” inProceedings of the 2019 CHI Conference on Human Factors in Computing Systems. Glasgow Scotland Uk: ACM, May 2019, pp. 1–13. [Online]. Available: https://dl.ac...

    work page doi:10.1145/3290605.3300233 2019