pith. machine review for the scientific record. sign in

arxiv: 2604.08529 · v1 · submitted 2026-04-09 · 💻 cs.HC · cs.AI

Recognition: 2 theorem links

· Lean Theorem

PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents

Zhiyuan Wang , Erzhen Hu , Mark Rucker , Laura E. Barnes
Authors on Pith no claims yet

Pith reviewed 2026-05-10 16:53 UTC · model grok-4.3

classification 💻 cs.HC cs.AI
keywords shared statepersonal AI agentsAI-generated instrumentscoherent environmentspersonal-context buscross-module integrationchat interfaces
0
0 comments X

The pith

Shared state architecture integrates independently generated AI modules into coherent personal environments.

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

Personal AI tools generated from natural language often end up isolated. PSI presents a shared-state system that publishes module state and write-back capabilities to a common bus. This allows modules to reason across each other and synchronize actions through both graphical interfaces and chat. The approach was tested in a three-week personal deployment where new instruments integrated automatically. If correct, it changes AI-generated software from standalone apps to parts of a unified personal computing setup.

Core claim

By defining a contract where each module exposes its current state and affordances on a shared personal-context bus, PSI enables AI-generated instruments to become persistent, connected, and complementary to chat interfaces, allowing automatic integration of subsequent modules without additional engineering.

What carries the argument

The personal-context bus, which serves as the shared state layer for publishing current state and write-back affordances to enable cross-module interactions.

If this is right

  • Modules gain the ability to perform cross-module reasoning and synchronized actions.
  • Instruments remain accessible through both dedicated GUIs and a generic chat agent.
  • Newly generated instruments integrate automatically into the existing environment.
  • AI-generated personal software shifts from isolated applications to coherent computing environments.

Where Pith is reading between the lines

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

  • Broader adoption could lead to standardized interfaces for state sharing in personal AI ecosystems.
  • Similar architectures might apply to collaborative or multi-agent systems beyond personal use.
  • Developers of personal AI tools could focus on module logic rather than integration concerns.
  • Long-term use might reveal patterns in how state evolves across many instruments.

Load-bearing premise

A single three-week autobiographical deployment suffices to show that the shared-state contract enables automatic integration for general users and environments.

What would settle it

If a newly generated instrument in a different setup does not automatically publish to and read from the shared bus to integrate with prior modules, the automatic integration claim would be falsified.

Figures

Figures reproduced from arXiv: 2604.08529 by Erzhen Hu, Laura E. Barnes, Mark Rucker, Zhiyuan Wang.

Figure 1
Figure 1. Figure 1: PSI at a glance. (1) A user describes a personal need in natural language; an AI generation engine produces a shared-state [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: PSI pipeline and interface walkthrough: PSI turns generated personal apps into persistent, connected, and chat [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Automated Parking Example (behavioral timeline, health entries, parking state) persisted as local JSON files; (3) a Python dispatcher maintaining WebSocket sessions with the iOS client, injecting shared context server-side, and routing tool calls through the LLM; All services run on localhost; personal data stays on-device by default. 4.1 Versatile Applications PSI supports one shared personal-context cont… view at source ↗
Figure 4
Figure 4. Figure 4: Benchmark illustrations. C = Context; M = Module. [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
read the original abstract

Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and write-back affordances to a shared personal-context bus, modules enable cross-module reasoning and synchronized actions across interfaces. We study PSI through a three-week autobiographical deployment in a self-developed personal AI environment and show that later-generated instruments can be integrated automatically through the same contract. PSI identifies shared state as the missing systems layer that transforms AI-generated personal software from isolated apps into coherent personal computing environments.

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 / 1 minor

Summary. The paper presents PSI, a shared-state architecture for personal AI agents that enables independently generated modules to function as coherent instruments. By publishing current state and write-back affordances to a shared personal-context bus, modules support cross-module reasoning, synchronized actions, and accessibility via both GUIs and chat agents. The central claim is that this shared-state contract transforms isolated AI-generated personal software into persistent, connected computing environments, as evidenced by automatic integration of later-generated instruments in a three-week autobiographical deployment within a self-developed personal AI environment.

Significance. If the result holds, PSI could address fragmentation in AI-generated personal tools by supplying a missing systems layer for coherence and integration, with relevance to HCI research on personal agents and end-user programming. The emphasis on a contract-based approach for state sharing offers a concrete architectural proposal that could inform future agent platforms.

major comments (2)
  1. [Deployment Study / Evaluation] The evaluation consists solely of qualitative autobiographical observations from a three-week deployment in the authors' self-developed environment, with no quantitative metrics, error analysis, failure cases, baseline comparisons (e.g., identical generation workflow without the shared-state layer), or replication outside the author's stack. This leaves the claim that the shared-state contract enables automatic cross-module integration vulnerable to author-specific implementation details and selection biases.
  2. [Abstract and Claims] The generalization that later-generated instruments integrate automatically through the same contract is supported only by the single self-reported case; the manuscript does not address how the approach would perform with different base agents, generation processes, or user contexts, undermining the broader assertion that shared state is the 'missing layer' for coherent personal computing environments.
minor comments (1)
  1. [Introduction / Architecture] The abstract and introduction use terms such as 'personal-context bus' and 'write-back affordances' without an early, precise definition or diagram; adding a dedicated subsection or figure in the architecture description would improve clarity.

Simulated Author's Rebuttal

2 responses · 2 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below, acknowledging the limitations of our evaluation while defending the value of the autobiographical deployment as an initial demonstration of the PSI architecture.

read point-by-point responses

  1. Referee: [Deployment Study / Evaluation] The evaluation consists solely of qualitative autobiographical observations from a three-week deployment in the authors' self-developed environment, with no quantitative metrics, error analysis, failure cases, baseline comparisons (e.g., identical generation workflow without the shared-state layer), or replication outside the author's stack. This leaves the claim that the shared-state contract enables automatic cross-module integration vulnerable to author-specific implementation details and selection biases.

    Authors: We agree that the evaluation is limited to qualitative observations from a single autobiographical deployment and lacks quantitative metrics, baselines, or external replication. This was a deliberate choice to capture longitudinal, real-world integration behavior in a personal context that controlled studies cannot easily replicate. We will revise the manuscript to explicitly discuss observed failure modes, selection biases, and the exploratory nature of the study, while adding a dedicated limitations section and outlining future controlled experiments with baselines. revision: partial

  2. Referee: [Abstract and Claims] The generalization that later-generated instruments integrate automatically through the same contract is supported only by the single self-reported case; the manuscript does not address how the approach would perform with different base agents, generation processes, or user contexts, undermining the broader assertion that shared state is the 'missing layer' for coherent personal computing environments.

    Authors: The paper frames PSI as an architectural contract demonstrated through one extended case, not as a universally validated solution. We will revise the abstract and conclusion to qualify the 'missing layer' claim as a hypothesis grounded in the observed automatic integration, and we will add discussion of how the contract could transfer to other agents while noting the need for broader validation across contexts. revision: partial

standing simulated objections not resolved
  • We cannot supply quantitative metrics, error analysis, or baseline comparisons without new experiments outside the current scope.
  • Replication with different base agents or user stacks is not possible in this revision as it requires external environments and participants.

Circularity Check

0 steps flagged

No significant circularity in the derivation chain

full rationale

The paper proposes the PSI shared-state architecture as a systems layer for coherent AI-generated instruments and validates it via a three-week autobiographical deployment in the authors' self-developed environment. No equations, formal derivations, fitted parameters, or predictions appear in the provided text. The central claim that the shared-state contract enables automatic cross-module integration does not reduce by construction to any input; it is presented as an observed outcome of the proposed contract rather than a self-definitional or statistically forced result. No load-bearing self-citations, uniqueness theorems, or ansatzes imported from prior author work are invoked. The argument remains self-contained as an architectural proposal grounded in direct experience.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies no technical details on parameters, axioms, or new entities.

pith-pipeline@v0.9.0 · 5424 in / 1040 out tokens · 62483 ms · 2026-05-10T16:53:06.940494+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

43 extracted references · 32 canonical work pages

  1. [1]

    OpenClaw: An Open-Source Framework for Personal AI Agents

    2025. OpenClaw: An Open-Source Framework for Personal AI Agents. https: //github.com/openclaw/openclaw

    2025

  2. [2]

    Anthropic. 2025. Claude Code: Anthropic’s Agentic Coding Tool. https://docs. anthropic.com/en/docs/claude-code

    2025

  3. [3]

    Michel Beaudouin-Lafon. 2000. Instrumental Interaction: An Interaction Model for Designing Post-WIMP User Interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’00). 446–453. doi:10.1145/332040. 332473

    work page doi:10.1145/332040 2000

  4. [4]

    Yining Cao, Peiling Jiang, and Haijun Xia. 2025. Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Article 686, 20 pages. doi:10.1145/3706598.3713285

    work page doi:10.1145/3706598.3713285 2025

  5. [5]

    Lee, Bongshin Lee, Wanda Pratt, and Julie A

    Eun Kyoung Choe, Nicole B. Lee, Bongshin Lee, Wanda Pratt, and Julie A. Kientz

  6. [6]

    InProceedings of the SIGCHI Conference on Human Factors in Com- puting Systems(Toronto, Ontario, Canada)(CHI ’14)

    Understanding quantified-selfers’ practices in collecting and exploring personal data. InProceedings of the SIGCHI Conference on Human Factors in Com- puting Systems(Toronto, Ontario, Canada)(CHI ’14). Association for Computing Machinery, New York, NY, USA, 1143–1152. doi:10.1145/2556288.2557372

    work page doi:10.1145/2556288.2557372

  7. [7]

    Akshat Choube, Ha Le, Jiachen Li, Kaixin Ji, Vedant Das Swain, and Varun Mishra

  8. [8]

    ACM Interact

    GLOSS: Group of LLMs for Open-ended Sensemaking of Passive Sensing Data for Health and Wellbeing.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.9, 3, Article 76 (Sept. 2025), 32 pages. doi:10.1145/3749474

    work page doi:10.1145/3749474 2025

  9. [9]

    Audrey Desjardins and Aubree Ball. 2018. Revealing Tensions in Autobiographical Design in HCI. InProceedings of the 2018 Designing Interactive Systems Conference (Hong Kong, China)(DIS ’18). Association for Computing Machinery, New York, NY, USA, 753–764. doi:10.1145/3196709.3196781

    work page doi:10.1145/3196709.3196781 2018

  10. [10]

    Anind K. Dey. 2001. Understanding and Using Context.Personal Ubiquitous Comput.5, 1 (Jan. 2001), 4–7. doi:10.1007/s007790170019

    work page doi:10.1007/s007790170019 2001

  11. [11]

    InProceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp ’15)

    Daniel A. Epstein, An Ping, James Fogarty, and Sean A. Munson. 2015. A lived informatics model of personal informatics. InProceedings of the 2015 ACM Interna- tional Joint Conference on Pervasive and Ubiquitous Computing(Osaka, Japan)(Ubi- Comp ’15). Association for Computing Machinery, New York, NY, USA, 731–742. doi:10.1145/2750858.2804250

    work page doi:10.1145/2750858.2804250 2015

  12. [12]

    Bill Gaver, Tony Dunne, and Elena Pacenti. 1999. Design: Cultural probes.Inter- actions6, 1 (Jan. 1999), 21–29. doi:10.1145/291224.291235

    work page doi:10.1145/291224.291235 1999

  13. [13]

    William W. Gaver. 2012. What Should We Expect from Research Through Design?. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’12). 937–946. doi:10.1145/2207676.2208538

    work page doi:10.1145/2207676.2208538 2012

  14. [14]

    GitHub. 2021. GitHub Copilot. https://github.com/features/copilot

    2021

  15. [15]

    Saul Greenberg and Bill Buxton. 2008. Usability Evaluation Considered Harmful (Some of the Time). InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 111–120. doi:10.1145/1357054.1357074

    work page doi:10.1145/1357054.1357074 2008

  16. [16]

    Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Pittsburgh, Pennsylvania, USA)(CHI ’99). Association for Computing Machinery, New York, NY, USA, 159–166. doi:10.1145/302979.303030

    work page doi:10.1145/302979.303030 1999

  17. [17]

    Bederson, Al- lison Druin, Catherine Plaisant, Michel Beaudouin-Lafon, Stéphane Conversy, Helen Evans, Heiko Hansen, Nicolas Roussel, and Björn Eiderbäck

    Hilary Hutchinson, Wendy Mackay, Bo Westerlund, Benjamin B. Bederson, Al- lison Druin, Catherine Plaisant, Michel Beaudouin-Lafon, Stéphane Conversy, Helen Evans, Heiko Hansen, Nicolas Roussel, and Björn Eiderbäck. 2003. Technol- ogy probes: inspiring design for and with families. InProceedings of the SIGCHI Conference on Human Factors in Computing System...

    work page doi:10.1145/642611.642616 2003

  18. [18]

    Dow, and Haijun Xia

    Peiling Jiang, Jude Rayan, Steven P. Dow, and Haijun Xia. 2023. Graphologue: Exploring Large Language Model Responses with Interactive Diagrams. InPro- ceedings of the 36th Annual ACM Symposium on User Interface Software and Technology(San Francisco, CA, USA)(UIST ’23). Association for Computing Machinery, New York, NY, USA, Article 3, 20 pages. doi:10.11...

    work page doi:10.1145/3586183.3606737 2023

  19. [19]

    Gajos, Jacob O

    Daniel R. Olsen Jr. 2007. Evaluating User Interface Systems Research. InProceed- ings of the 20th Annual ACM Symposium on User Interface Software and Technology. 251–258. doi:10.1145/1294211.1294256

    work page doi:10.1145/1294211.1294256 2007

  20. [20]

    Young-Ho Kim, Bongshin Lee, Arjun Srinivasan, and Eun Kyoung Choe. 2021. Data@Hand: Fostering Visual Exploration of Personal Data on Smartphones Leveraging Speech and Touch Interaction. InProceedings of the 2021 CHI Con- ference on Human Factors in Computing Systems(Yokohama, Japan)(CHI ’21). Association for Computing Machinery, New York, NY, USA, Article...

    work page doi:10.1145/3411764.3445421 2021

  21. [21]

    Andrew J. Ko, Robin Abraham, Laura Beckwith, Alan Blackwell, Margaret Burnett, Martin Erwig, Chris Scaffidi, Joseph Lawrance, Henry Lieberman, Brad Myers, Mary Beth Rosson, Gregg Rothermel, Mary Shaw, and Susan Wiedenbeck. 2011. The State of the Art in End-User Software Engineering.Comput. Surveys43, 3, Article 21 (2011). doi:10.1145/1922649.1922658

    work page doi:10.1145/1922649.1922658 2011

  22. [22]

    David Ledo, Steven Houben, Jo Vermeulen, Nicolai Marquardt, Lora Oehlberg, and Saul Greenberg. 2018. Evaluation Strategies for HCI Toolkit Research. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Article 36, 17 pages. doi:10.1145/3173574.3173610

    work page doi:10.1145/3173574.3173610 2018

  23. [23]

    Ian Li, Anind Dey, and Jodi Forlizzi. 2010. A stage-based model of personal informatics systems. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Atlanta, Georgia, USA)(CHI ’10). Association for Computing Machinery, New York, NY, USA, 557–566. doi:10.1145/1753326.1753409

    work page doi:10.1145/1753326.1753409 2010

  24. [24]

    Jiahao Nick Li, Yan Xu, Tovi Grossman, Stephanie Santosa, and Michelle Li. 2024. OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 8...

    work page arXiv 2024

  25. [25]

    Toby Jia-Jun Li, Amos Azaria, and Brad A. Myers. 2017. SUGILITE: Creating Multimodal Smartphone Automation by Demonstration. InProceedings of the 2017 CHI Conference on Human Factors in Computing Systems(Denver, Colorado, USA)(CHI ’17). Association for Computing Machinery, New York, NY, USA, 6038–6049. doi:10.1145/3025453.3025483

    work page doi:10.1145/3025453.3025483 2017

  26. [26]

    Mitchell, and Brad A

    Toby Jia-Jun Li, Marissa Radensky, Justin Jia, Kirielle Singarajah, Tom M. Mitchell, and Brad A. Myers. 2019. PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations. InProceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology (New Orleans, LA, USA)(UIST ’19). Association for ...

    work page doi:10.1145/3332165.3347899 2019

  27. [27]

    Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, et al. 2024. Personal llm agents: Insights and survey about the capability, efficiency and security.arXiv preprint arXiv:2401.05459(2024)

    work page arXiv 2024

  28. [28]

    Geoffrey Litt. 2023. Malleable Software in the Age of LLMs. https://www. geoffreylitt.com/2023/03/25/llm-end-user-programming.html

    2023

  29. [29]

    Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts.Transactions of the association for computational linguistics12 (2024), 157–173

    2024

  30. [30]

    Cheema, Hasti Seifi, and Pooyan Fazli

    Wendy E. Mackay and Michel Beaudouin-Lafon. 2025. Interaction Substrates: Combining Power and Simplicity in Interactive Systems. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 687, 16 pages. doi:10. 1145/3706598.3714006

    work page arXiv 2025

  31. [31]

    Pattie Maes. 1994. Agents that reduce work and information overload.Commun. ACM37, 7 (July 1994), 30–40. doi:10.1145/176789.176792

    work page doi:10.1145/176789.176792 1994

  32. [32]

    Damien Masson, Sylvain Malacria, Géry Casiez, and Daniel Vogel. 2024. Direct- GPT: A Direct Manipulation Interface to Interact with Large Language Models. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 975, 16 pages. doi:10.1145/36...

    work page doi:10.1145/3613904.3642462 2024

  33. [33]

    Bonnie A. Nardi. 1993.A Small Matter of Programming: Perspectives on End User Computing. MIT Press

    1993

  34. [34]

    Carman Neustaedter and Phoebe Sengers. 2012. Autobiographical design in HCI research: designing and learning through use-it-yourself. InProceedings of the Designing Interactive Systems Conference(Newcastle Upon Tyne, United Kingdom)(DIS ’12). Association for Computing Machinery, New York, NY, USA, 514–523. doi:10.1145/2317956.2318034

    work page doi:10.1145/2317956.2318034 2012

  35. [35]

    2013.The Design of Everyday Things: Revised and Expanded Edition

    Don Norman. 2013.The Design of Everyday Things: Revised and Expanded Edition. Basic Books

    2013

  36. [36]

    Bernstein

    Joon Sung Park, Joseph C. O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. InProceedings of the 36th Annual ACM Symposium on User PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents Conference’17, July 201...

    work page arXiv 2023

  37. [37]

    Bernstein

    Omar Shaikh, Shardul Sapkota, Shan Rizvi, Eric Horvitz, Joon Sung Park, Diyi Yang, and Michael S. Bernstein. 2025. Creating General User Models from Com- puter Use. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST ’25). doi:10.1145/3746059.3747722

    work page doi:10.1145/3746059.3747722 2025

  38. [38]

    Ben Shneiderman. 1983. Direct Manipulation: A Step Beyond Programming Languages.Computer16, 8 (1983), 57–69

    1983

  39. [39]

    Sangho Suh, Meng Chen, Bryan Min, Toby Jia-Jun Li, and Haijun Xia. 2024. Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Art...

    work page doi:10.1145/3613904.3642400 2024

  40. [40]

    Glassman, Jeevana Priya Inala, and Chenglong Wang

    Priyan Vaithilingam, Elena L. Glassman, Jeevana Priya Inala, and Chenglong Wang. 2024. DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 985, 17 pages. doi:10.1145/...

    work page doi:10.1145/3613904.3642639 2024

  41. [41]

    Mark Weiser. 1991. The Computer for the 21st Century.Scientific American265, 3 (1991), 94–104

    1991

  42. [42]

    Bernstein

    Dora Zhao, Diyi Yang, and Michael S. Bernstein. 2025. Knoll: Creating a Knowl- edge Ecosystem for Large Language Models. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST ’25). Article 140, 23 pages. doi:10.1145/3746059.3747711

    work page doi:10.1145/3746059.3747711 2025

  43. [43]

    John Zimmerman, Jodi Forlizzi, and Shelley Evenson. 2007. Research Through Design as a Method for Interaction Design Research in HCI. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’07). 493–502. doi:10.1145/1240624.1240704 A Evaluation Task Set The evaluation comprises 50 reasoning tasks across three fami- lies (cross-m...

    work page doi:10.1145/1240624.1240704 2007