Co-Designing Community-Centered AI Education for Adults: A Midwestern Case Study

Holden Winton; Jared Lee Katzman; Kimberly Sanders; Leonymae Aumentado; Sparkle Berry; Tawanna R. Dillahunt; Yao Lyu; Zachary Rowe

arxiv: 2606.26565 · v1 · pith:3M52CEZLnew · submitted 2026-06-25 · 💻 cs.HC

Co-Designing Community-Centered AI Education for Adults: A Midwestern Case Study

Yao Lyu , Leonymae Aumentado , Holden Winton , Jared Lee Katzman , Sparkle Berry , Zachary Rowe , Kimberly Sanders , Tawanna R. Dillahunt This is my paper

Pith reviewed 2026-06-26 04:02 UTC · model grok-4.3

classification 💻 cs.HC

keywords AI educationcommunity co-designAI literacyadult learnerscommunity capacitycase study

0 comments

The pith

Co-designed AI education for adults shifts concerns from general fears to specific local questions about design and deployment.

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

The paper examines what AI education looks like for adults outside formal systems through a case study of one session with 54 adults in a Midwestern African American community. It finds that a session developed with community partners leaves broad AI concerns intact but makes them more specific and tied to local contexts of design and deployment. The authors frame AI literacy around building community capacity and argue that effective frameworks must be grounded in those local contexts. This approach matters because most AI education targets students and leaves adults underserved. The case study illustrates how community involvement can make literacy efforts more relevant to participants' actual questions.

Core claim

Through a co-designed session developed with community partners, we found that concerns about AI persisted but shifted to specific, locally grounded questions about AI design and deployment. We also discuss AI literacy from a community capacity perspective and argue for AI literacy frameworks grounded in local community contexts that strengthen community capacity.

What carries the argument

The co-designed education session with community partners, which surfaces and refines participant concerns about AI in locally relevant terms.

Load-bearing premise

The single co-designed session with 54 participants produced an authentic, unbiased shift in concerns that can be attributed to the education activity rather than researcher presence, partner influence, or social desirability effects.

What would settle it

A follow-up session in the same community without community partner co-design, with pre- and post-measures of concern specificity, to test whether the shift still occurs.

Figures

Figures reproduced from arXiv: 2606.26565 by Holden Winton, Jared Lee Katzman, Kimberly Sanders, Leonymae Aumentado, Sparkle Berry, Tawanna R. Dillahunt, Yao Lyu, Zachary Rowe.

read the original abstract

Artificial Intelligence (AI) education is increasingly important, yet adults outside higher education receive less attention. We report a case study of an AI education session with 54 adults (48 in-person and 6 virtual) in a predominantly African American community on the east side of a major Midwestern city. We ask: "What does AI education for adults outside formal educational systems look like in practice?" and "What does this AI education session reveal about AI literacy at the community level?" Through a co-designed session developed with community partners, we found that concerns about AI persisted but shifted to specific, locally grounded questions about AI design and deployment. We also discuss AI literacy from a community capacity perspective and argue for AI literacy frameworks grounded in local community contexts that strengthen community capacity.

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.

Desk Editor's Note private letter to a colleague

This is a straightforward case report on one co-designed AI education session in a Midwestern community; the observed shift in concerns is plausible but the methods are too thin to evaluate it properly.

read the letter

The main takeaway is that this paper describes running a co-designed AI education session with 54 adults in a predominantly African American Midwestern community and reports that general concerns about AI shifted toward specific local questions about design and deployment. The authors use the case to argue for AI literacy frameworks that build community capacity rather than generic ones. That is the core content.

What is actually new is the application of participatory co-design methods to adult AI education in this specific setting, outside formal schooling. They partnered with local community organizations, ran an in-person and virtual session, and noted changes in the kinds of questions that came up. This adds a grounded example to the existing HCI literature on participatory design and AI literacy, which often stays at the level of students or broad principles.

The paper does a reasonable job laying out the session structure and the high-level observations. The argument for locally grounded approaches makes sense given the community context they describe, and the participant numbers are respectable for this type of event.

The soft spot is the complete absence of any account of data collection, coding, or analysis. The abstract presents findings about concern shifts and capacity building, yet supplies no information on how those were derived from the session—notes, recordings, post-session feedback, thematic coding, or anything else. Without that, it is hard to judge whether the reported shift reflects the education activity or other factors like who facilitated the discussion. A single session also limits what can be claimed about lasting effects or broader applicability, though that is a common constraint in this genre.

This paper is for HCI researchers and practitioners working on community-based AI education or participatory methods. Someone looking for a detailed methods template or strong causal evidence will not find it here, but a reader wanting a concrete example from a non-university adult setting could get something useful.

I would send it to peer review. The topic is relevant, the approach is standard for the subfield, and the central claim is modest enough that referees could reasonably ask for clearer reporting of evidence without requiring the authors to redo the work.

Referee Report

2 major / 0 minor

Summary. The manuscript reports a case study of a co-designed AI education session involving 54 adults (48 in-person, 6 virtual) in a predominantly African American Midwestern community. Developed with community partners, the session is presented as revealing that general concerns about AI persisted but shifted toward specific, locally grounded questions about AI design and deployment. The authors discuss AI literacy through a community capacity lens and argue for literacy frameworks that are grounded in local community contexts to strengthen capacity.

Significance. If the observations are robustly supported, the work provides a practical example of participatory AI education for adults outside formal systems, particularly in underrepresented communities. It contributes to HCI by illustrating how co-design can surface context-specific concerns and by advancing the case for community-capacity-oriented AI literacy frameworks, which may inform more equitable educational practices.

major comments (2)

The abstract states findings about concern shifts and community capacity but supplies no description of data collection, coding, or analysis procedures; without these details the central empirical claims cannot be evaluated against the paper's own evidence.
The single-session design with 54 participants leaves open whether the reported shift in concerns can be attributed to the education activity itself rather than researcher presence, partner influence, or social desirability effects; a methods section addressing these threats to interpretive validity is needed to support the central claim.

Simulated Author's Rebuttal

2 responses · 0 unresolved

Thank you for the constructive feedback on our case study manuscript. We appreciate the emphasis on methodological transparency and validity considerations. Below we address each major comment point by point, indicating planned revisions where appropriate.

read point-by-point responses

Referee: The abstract states findings about concern shifts and community capacity but supplies no description of data collection, coding, or analysis procedures; without these details the central empirical claims cannot be evaluated against the paper's own evidence.

Authors: We agree that the abstract would benefit from a concise description of the data collection and analysis approach to better contextualize the findings. The full manuscript details the co-design process with community partners, the session format, and how concerns were documented through facilitator notes and group discussions. We will revise the abstract to include a brief statement on the qualitative data collection and thematic analysis procedures. revision: yes
Referee: The single-session design with 54 participants leaves open whether the reported shift in concerns can be attributed to the education activity itself rather than researcher presence, partner influence, or social desirability effects; a methods section addressing these threats to interpretive validity is needed to support the central claim.

Authors: We acknowledge that a single-session case study design limits causal attribution and introduces potential threats such as researcher presence and social desirability. As this work is positioned as an exploratory case study of co-designed education in practice rather than a controlled experiment, we will add a dedicated subsection to the methods describing these threats and our mitigation strategies, including community partner involvement in facilitation and use of open-ended discussion formats. We will also expand the limitations section to discuss implications for interpretive validity. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a qualitative case study of a single co-designed AI education session with 54 adults. Its claims consist of reported observations about shifts in participant concerns and an interpretive argument for community-capacity-based AI literacy frameworks. No equations, fitted parameters, derivations, predictions, or formal models appear anywhere in the text. The central findings are presented as direct outcomes of the session data rather than reductions of any prior quantities defined by the authors, and no self-citation chains are used to justify load-bearing steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The work rests on standard qualitative-research assumptions about the validity of participant self-reports and the value of co-design; no free parameters, invented entities, or ad-hoc mathematical axioms are introduced.

axioms (1)

domain assumption Participant responses in a co-designed community session can be treated as reliable indicators of authentic local concerns about AI.
Implicit in the interpretation of the observed shift in concerns.

pith-pipeline@v0.9.1-grok · 5685 in / 1236 out tokens · 64551 ms · 2026-06-26T04:02:54.054443+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

20 extracted references · 17 canonical work pages

[1]

Foriest, Jordan Taylor, Kyle Pittman, Sarah Gilbert, and Michael Ann DeVito

Leah Hope Ajmani, Jasmine C. Foriest, Jordan Taylor, Kyle Pittman, Sarah Gilbert, and Michael Ann DeVito. 2024. Whose Knowledge is Valued? Epistemic Injustice in CSCW Applications.Proc. ACM Hum.-Comput. Interact.8, CSCW2 (Nov. 2024), 523:1–523:28. https://doi.org/10.1145/3687062

work page doi:10.1145/3687062 2024
[2]

Omaima Almatrafi, Aditya Johri, and Hyuna Lee. 2024. A systematic review of AI literacy conceptualization, constructs, and implementation and assessment efforts (2019–2023).Computers and Education Open6 (June 2024), 100173. https://doi.org/10.1016/j.caeo.2024.100173

work page doi:10.1016/j.caeo.2024.100173 2024
[3]

Robert J. Chaskin. 2001. Building Community Capacity: A Definitional Framework and Case Studies from a Comprehensive Community Initiative. Urban Affairs Review36, 3 (Jan. 2001), 291–323. https://doi.org/10.1177/10780870122184876

work page doi:10.1177/10780870122184876 2001
[4]

Marios Constantinides and Daniele Quercia. 2025. AI, Jobs, and the Automation Trap: Where Is HCI?. InProceedings of the 4th Annual Symposium on Human-Computer Interaction for Work (CHIWORK ’25). Association for Computing Machinery, New York, NY, USA, 1–8. https://doi.org/10.1145/ 3729176.3729191

arXiv 2025
[5]

Yngve Dahl, Kshitij Sharma, and Dag Svanæs. 2025. Facilitation Skills in Participatory Design. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/3706598.3713658

work page doi:10.1145/3706598.3713658 2025
[6]

Tawanna R Dillahunt. 2025. The Development of a New Measure for Community Digital Capacity.Proc. ACM Hum.-Comput. Interact.9, 2, Article 27 (2025), 30 pages

2025
[7]

Tawanna R Dillahunt, Kerby Shedden, Mila Ekaterina Filipof, Soyoung Lee, Mustafa Naseem, Kentaro Toyama, and Julie Hui. 2024. Toward a measure of collective digital capacity: An exploratory analysis. InExtended abstracts of the 2024 CHI conference on human factors in computing systems (Chi ea ’24). Association for Computing Machinery, New York, NY, USA, 3...

work page doi:10.1145/3613905.3650811 2024
[8]

Sanjana Gautam, Xiaolong Zhang, and Mary Beth Rosson. 2024. Towards Dynamic Learning: A Framework for Simulating Adaptive Learning Systems. InCompanion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing (CSCW Companion ’24). Association for Computing Machinery, New York, NY, USA, 603–608. https://doi.org/10.1145...

work page doi:10.1145/3678884.3681913 2024
[9]

Divya Gupta, Jaspreet Kaur, and Simarjeet Kaur. 2024. Transforming Healthcare through Machine Learning: A Revolution in Patient Care. In Proceedings of the 5th International Conference on Information Management & Machine Intelligence (ICIMMI ’23). Association for Computing Machinery, New York, NY, USA, 1–4. https://doi.org/10.1145/3647444.3647842

work page doi:10.1145/3647444.3647842 2024
[10]

I was able to give her the confidence

Julie Hui, Kristin Seefeldt, Lutalo Sanifu, Christie Baer, Jeanette Szomstein, and Tawanna R Dillahunt. 2024. “I was able to give her the confidence”: Reciprocal capacity building in a community-based program for digital engagement. InProceedings of the CHI conference on human factors in computing systems (Chi ’24). Association for Computing Machinery, Ne...

work page doi:10.1145/3613904.3642209 2024
[11]

We need to avail ourselves of [GenAI] to enhance knowledge distribution

Eunhye Grace Ko, Shaini Nanayakkara, and Earl W Huff. 2025. "We need to avail ourselves of [GenAI] to enhance knowledge distribution": Empowering Older Adults through GenAI Literacy. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, 1–7....

work page doi:10.1145/3706599.3720032 2025
[12]

Matthias Carl Laupichler, Alexandra Aster, Jana Schirch, and Tobias Raupach. 2022. Artificial intelligence literacy in higher and adult education: A scoping literature review.Computers and Education: Artificial Intelligence3 (Jan. 2022), 100101. https://doi.org/10.1016/j.caeai.2022.100101

work page doi:10.1016/j.caeai.2022.100101 2022
[13]

Dillahunt

Soyoung Lee, Julie Hui, and Tawanna R. Dillahunt. 2025. Sociocultural Factors in Digital Skills Learning: A Community-Based Intervention Among U.S. Public Housing Adults.Proc. ACM Hum.-Comput. Interact.9, 2 (May 2025), CSCW172:1–CSCW172:26. https://doi.org/10.1145/3711070

work page doi:10.1145/3711070 2025
[14]

Davy Tsz Kit Ng, Jac Ka Lok Leung, Kai Wah Samuel Chu, and Maggie Shen Qiao. 2021. AI Literacy: Definition, Teaching, Evaluation and Ethical Issues.Proceedings of the Association for Information Science and Technology58, 1 (2021), 504–509. https://doi.org/10.1002/pra2.487 _eprint: https://asistdl.onlinelibrary.wiley.com/doi/pdf/10.1002/pra2.487

work page doi:10.1002/pra2.487 2021
[15]

Davy Tsz Kit Ng, Jac Ka Lok Leung, Samuel Kai Wah Chu, and Maggie Shen Qiao. 2021. Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence2 (Jan. 2021), 100041. https://doi.org/10.1016/j.caeai.2021.100041

work page doi:10.1016/j.caeai.2021.100041 2021
[16]

Yim Register and Amy J. Ko. 2020. Learning Machine Learning with Personal Data Helps Stakeholders Ground Advocacy Arguments in Model Mechanics. InProceedings of the 2020 ACM Conference on International Computing Education Research (ICER ’20). Association for Computing Machinery, New York, NY, USA, 67–78. https://doi.org/10.1145/3372782.3406252

work page doi:10.1145/3372782.3406252 2020
[17]

Gisela Reyes-Cruz, Velvet Spors, Michael Muller, Marianela Ciolfi Felice, Shaowen Bardzell, Rua Mae Williams, Karin Hansson, and Ivana Feldfeber
[18]

InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25)

Resisting AI Solutionism: Where Do We Go From Here?. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, 1–6. https://doi.org/10.1145/3706599.3706732 7 CSCW ’26, 2026, TBD Lyu, et al

work page doi:10.1145/3706599.3706732 2026
[19]

McLaughlin, and Kenneth R

Jeremy Roschelle, Elizabeth A. McLaughlin, and Kenneth R. Koedinger. 2025. Beyond Benchmarks: Responsible AI in Education Needs Learning Sciences.Commun. ACM68, 12 (Nov. 2025), 37–39. https://doi.org/10.1145/3747174

work page doi:10.1145/3747174 2025
[20]

KangJie Tang, Eugene, Tianqi Song, Zicheng Zhu, Jingshu Li, and Yi-Chieh Lee. 2025. AI Literacy Education for Older Adults: Motivations, Challenges and Preferences. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1–15. https://doi.org/10.1145/3706599.3720033 8

work page doi:10.1145/3706599.3720033 2025

[1] [1]

Foriest, Jordan Taylor, Kyle Pittman, Sarah Gilbert, and Michael Ann DeVito

Leah Hope Ajmani, Jasmine C. Foriest, Jordan Taylor, Kyle Pittman, Sarah Gilbert, and Michael Ann DeVito. 2024. Whose Knowledge is Valued? Epistemic Injustice in CSCW Applications.Proc. ACM Hum.-Comput. Interact.8, CSCW2 (Nov. 2024), 523:1–523:28. https://doi.org/10.1145/3687062

work page doi:10.1145/3687062 2024

[2] [2]

Omaima Almatrafi, Aditya Johri, and Hyuna Lee. 2024. A systematic review of AI literacy conceptualization, constructs, and implementation and assessment efforts (2019–2023).Computers and Education Open6 (June 2024), 100173. https://doi.org/10.1016/j.caeo.2024.100173

work page doi:10.1016/j.caeo.2024.100173 2024

[3] [3]

Robert J. Chaskin. 2001. Building Community Capacity: A Definitional Framework and Case Studies from a Comprehensive Community Initiative. Urban Affairs Review36, 3 (Jan. 2001), 291–323. https://doi.org/10.1177/10780870122184876

work page doi:10.1177/10780870122184876 2001

[4] [4]

Marios Constantinides and Daniele Quercia. 2025. AI, Jobs, and the Automation Trap: Where Is HCI?. InProceedings of the 4th Annual Symposium on Human-Computer Interaction for Work (CHIWORK ’25). Association for Computing Machinery, New York, NY, USA, 1–8. https://doi.org/10.1145/ 3729176.3729191

arXiv 2025

[5] [5]

Yngve Dahl, Kshitij Sharma, and Dag Svanæs. 2025. Facilitation Skills in Participatory Design. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/3706598.3713658

work page doi:10.1145/3706598.3713658 2025

[6] [6]

Tawanna R Dillahunt. 2025. The Development of a New Measure for Community Digital Capacity.Proc. ACM Hum.-Comput. Interact.9, 2, Article 27 (2025), 30 pages

2025

[7] [7]

Tawanna R Dillahunt, Kerby Shedden, Mila Ekaterina Filipof, Soyoung Lee, Mustafa Naseem, Kentaro Toyama, and Julie Hui. 2024. Toward a measure of collective digital capacity: An exploratory analysis. InExtended abstracts of the 2024 CHI conference on human factors in computing systems (Chi ea ’24). Association for Computing Machinery, New York, NY, USA, 3...

work page doi:10.1145/3613905.3650811 2024

[8] [8]

Sanjana Gautam, Xiaolong Zhang, and Mary Beth Rosson. 2024. Towards Dynamic Learning: A Framework for Simulating Adaptive Learning Systems. InCompanion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing (CSCW Companion ’24). Association for Computing Machinery, New York, NY, USA, 603–608. https://doi.org/10.1145...

work page doi:10.1145/3678884.3681913 2024

[9] [9]

Divya Gupta, Jaspreet Kaur, and Simarjeet Kaur. 2024. Transforming Healthcare through Machine Learning: A Revolution in Patient Care. In Proceedings of the 5th International Conference on Information Management & Machine Intelligence (ICIMMI ’23). Association for Computing Machinery, New York, NY, USA, 1–4. https://doi.org/10.1145/3647444.3647842

work page doi:10.1145/3647444.3647842 2024

[10] [10]

I was able to give her the confidence

Julie Hui, Kristin Seefeldt, Lutalo Sanifu, Christie Baer, Jeanette Szomstein, and Tawanna R Dillahunt. 2024. “I was able to give her the confidence”: Reciprocal capacity building in a community-based program for digital engagement. InProceedings of the CHI conference on human factors in computing systems (Chi ’24). Association for Computing Machinery, Ne...

work page doi:10.1145/3613904.3642209 2024

[11] [11]

We need to avail ourselves of [GenAI] to enhance knowledge distribution

Eunhye Grace Ko, Shaini Nanayakkara, and Earl W Huff. 2025. "We need to avail ourselves of [GenAI] to enhance knowledge distribution": Empowering Older Adults through GenAI Literacy. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, 1–7....

work page doi:10.1145/3706599.3720032 2025

[12] [12]

Matthias Carl Laupichler, Alexandra Aster, Jana Schirch, and Tobias Raupach. 2022. Artificial intelligence literacy in higher and adult education: A scoping literature review.Computers and Education: Artificial Intelligence3 (Jan. 2022), 100101. https://doi.org/10.1016/j.caeai.2022.100101

work page doi:10.1016/j.caeai.2022.100101 2022

[13] [13]

Dillahunt

Soyoung Lee, Julie Hui, and Tawanna R. Dillahunt. 2025. Sociocultural Factors in Digital Skills Learning: A Community-Based Intervention Among U.S. Public Housing Adults.Proc. ACM Hum.-Comput. Interact.9, 2 (May 2025), CSCW172:1–CSCW172:26. https://doi.org/10.1145/3711070

work page doi:10.1145/3711070 2025

[14] [14]

Davy Tsz Kit Ng, Jac Ka Lok Leung, Kai Wah Samuel Chu, and Maggie Shen Qiao. 2021. AI Literacy: Definition, Teaching, Evaluation and Ethical Issues.Proceedings of the Association for Information Science and Technology58, 1 (2021), 504–509. https://doi.org/10.1002/pra2.487 _eprint: https://asistdl.onlinelibrary.wiley.com/doi/pdf/10.1002/pra2.487

work page doi:10.1002/pra2.487 2021

[15] [15]

Davy Tsz Kit Ng, Jac Ka Lok Leung, Samuel Kai Wah Chu, and Maggie Shen Qiao. 2021. Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence2 (Jan. 2021), 100041. https://doi.org/10.1016/j.caeai.2021.100041

work page doi:10.1016/j.caeai.2021.100041 2021

[16] [16]

Yim Register and Amy J. Ko. 2020. Learning Machine Learning with Personal Data Helps Stakeholders Ground Advocacy Arguments in Model Mechanics. InProceedings of the 2020 ACM Conference on International Computing Education Research (ICER ’20). Association for Computing Machinery, New York, NY, USA, 67–78. https://doi.org/10.1145/3372782.3406252

work page doi:10.1145/3372782.3406252 2020

[17] [17]

Gisela Reyes-Cruz, Velvet Spors, Michael Muller, Marianela Ciolfi Felice, Shaowen Bardzell, Rua Mae Williams, Karin Hansson, and Ivana Feldfeber

[18] [18]

InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25)

Resisting AI Solutionism: Where Do We Go From Here?. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, 1–6. https://doi.org/10.1145/3706599.3706732 7 CSCW ’26, 2026, TBD Lyu, et al

work page doi:10.1145/3706599.3706732 2026

[19] [19]

McLaughlin, and Kenneth R

Jeremy Roschelle, Elizabeth A. McLaughlin, and Kenneth R. Koedinger. 2025. Beyond Benchmarks: Responsible AI in Education Needs Learning Sciences.Commun. ACM68, 12 (Nov. 2025), 37–39. https://doi.org/10.1145/3747174

work page doi:10.1145/3747174 2025

[20] [20]

KangJie Tang, Eugene, Tianqi Song, Zicheng Zhu, Jingshu Li, and Yi-Chieh Lee. 2025. AI Literacy Education for Older Adults: Motivations, Challenges and Preferences. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1–15. https://doi.org/10.1145/3706599.3720033 8

work page doi:10.1145/3706599.3720033 2025