pith. machine review for the scientific record. sign in

arxiv: 2605.00497 · v1 · submitted 2026-05-01 · 💻 cs.HC · cs.AI· cs.CL

Recognition: unknown

"What Are You Really Trying to Do?": Co-Creating Life Goals from Everyday Computer Use

Shardul Sapkota , Matthew J\"orke , Zane Sabbagh , Omar Shaikh , Grace Wang , James A. Landay
Authors on Pith no claims yet

Pith reviewed 2026-05-09 18:58 UTC · model grok-4.3

classification 💻 cs.HC cs.AIcs.CL
keywords striving co-creationpersonal strivingsactivity theorygoal inferenceuser editingcomputer use modelinghuman-computer interaction
0
0 comments X

The pith

A co-creation process lets users edit AI inferences of their life goals from daily computer use, yielding strivings that better match long-term aims.

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

The paper presents striving co-creation as a way to infer broader personal goals from unstructured computer activity logs instead of only recording immediate actions. It builds hierarchical activity representations grounded in activity theory, then adds an editing step so users can correct the inferred goals and feed those changes back into later rounds. A week-long study with 14 participants found that the resulting strivings aligned more closely with their stated long-term goals and gave them greater sense of control than methods that skip user input.

Core claim

Striving co-creation progressively constructs a hierarchical representation of activities from computer use observations. Because the same action can serve many goals, the system provides an editing interface that lets users revise the inferred personal strivings and incorporates those revisions into future inferences. In a week-long field deployment with 14 participants, this process produced strivings representative of long-term goals while granting greater agency than baseline approaches.

What carries the argument

Striving co-creation, the iterative process that builds activity hierarchies from logs and refines personal strivings through user edits.

If this is right

  • Systems could shift from moment-to-moment task support to assistance aligned with users' ongoing purposes.
  • Users retain explicit control over how their digital traces are interpreted as goals.
  • Repeated edits could allow goal models to evolve as life priorities change.
  • The same editing loop might apply to other logged activities such as document work or web browsing.

Where Pith is reading between the lines

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

  • Combining computer logs with other traces like phone data could produce fuller goal representations.
  • Productivity tools might use the strivings to suggest tasks that serve longer-term aims.
  • Privacy protections would be needed if systems retain and refine personal goal information over months or years.
  • Longer deployments could test whether co-created strivings actually guide behavior changes.

Load-bearing premise

Observations of computer use can be turned into accurate hierarchical activity models that map onto personal strivings, and user corrections will improve later inferences without adding bias or inconsistency.

What would settle it

If an independent rating task shows that strivings produced with user editing are no more representative of participants' long-term goals than those from automated inference alone, the central claim would be falsified.

Figures

Figures reproduced from arXiv: 2605.00497 by Grace Wang, James A. Landay, Matthew J\"orke, Omar Shaikh, Shardul Sapkota, Zane Sabbagh.

Figure 1
Figure 1. Figure 1: Striving co-creation is a process in which a person and a system jointly construct a representation of the person’s view at source ↗
Figure 2
Figure 2. Figure 2: Tempo stores the striving hierarchy as a property graph. Each operation, action, activity, and striving is stored as a node connected by parent-child edges and by the tem￾poral edges (follows, co-occurs, overlaps) the pipeline accu￾mulates between action nodes and between activity nodes as new observations arrive. constructing strivings from observed behavior; the user provides the interpretive frame that … view at source ↗
Figure 3
Figure 3. Figure 3: The four operations Tempo exposes for editing the hierarchy: inline edit (A), reassign (B), remove (C), and merge (D). All edits persist as constraints on subsequent induction cycles (§3.2). 3.3.1 User-Facing Controls. Tempo’s dashboard lets users exclude specific applications and websites from capture, and users can pause recording at any time. During editing (§3.2), users can remove individual screenshot… view at source ↗
Figure 4
Figure 4. Figure 4: Estimated marginal means for per-striving preci view at source ↗
Figure 5
Figure 5. Figure 5: Estimated marginal means for set-level representa view at source ↗
Figure 6
Figure 6. Figure 6: Estimated marginal means for the editing experi view at source ↗
Figure 7
Figure 7. Figure 7: The hierarchical view used in the evaluation of the editing module (§ view at source ↗
Figure 8
Figure 8. Figure 8: The screenshot view used as the baseline condition in the evaluation of the editing module (§ view at source ↗
read the original abstract

Recent advances in user modeling make it feasible to conduct open-ended inference over a person's everyday computer use. Despite longstanding visions of systems that deeply understand our actions and the purposes they serve in our lives, existing systems only capture what a person is doing in the moment -- not why they are doing it -- limiting these systems to surface-level support. We introduce striving co-creation, a process for inferring broader life goals from unstructured observations of computer use. Grounded in Activity Theory and Emmons' personal strivings framework, our system progressively constructs a hierarchical representation of a person's activities. Crucially, strivings are difficult to fully resolve from observation alone, as the same action can be driven by many different goals. Our system therefore supports an editing interface that gives people agency over how they are understood by the system, feeding their corrections back into subsequent rounds of striving induction. In a week-long field deployment (N=14), we find that our co-creation process produces strivings that are representative of participants' long-term goals and gives them greater agency than baseline methods.

Editorial analysis

A structured set of objections, weighed in public.

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

Referee Report

2 major / 2 minor

Summary. The paper introduces 'striving co-creation,' a process and system that infers hierarchical personal strivings (long-term life goals) from unstructured logs of everyday computer use. Grounded in Activity Theory and Emmons' personal strivings framework, the approach builds progressive activity hierarchies from observations and incorporates an editing interface so users can correct inferences, with corrections fed back into subsequent induction rounds. A week-long field deployment with N=14 participants is reported to show that the resulting strivings are representative of participants' long-term goals and that the co-creation process affords greater agency than baseline methods.

Significance. If the empirical claims hold after addressing validation gaps, the work would meaningfully extend user modeling and personal informatics in HCI by moving beyond momentary action capture to purpose-oriented understanding. The theoretical grounding plus the closed-loop editing mechanism offers a concrete path toward systems that respect user agency in self-representation, with potential applications in goal-aligned assistants and reflective tools. The small-scale field deployment provides initial evidence of feasibility, though broader impact depends on stronger validation of the core representativeness claim.

major comments (2)
  1. [Evaluation / Field Deployment] The central claim that the co-creation process 'produces strivings that are representative of participants' long-term goals' (abstract and evaluation) rests on post-deployment self-reports. No pre-study independent elicitation of long-term goals (e.g., via Emmons' strivings questionnaire or a separate baseline interview) is described, so it is impossible to distinguish recovery of pre-existing goals from post-hoc rationalization or demand characteristics after participants have edited the system's output.
  2. [Abstract and Evaluation] The abstract states positive outcomes on agency and representativeness for N=14 but supplies no details on the exact instruments, scales, statistical tests, or baseline definitions used to measure these constructs. Without this information it is not possible to assess whether the data support the headline finding or to evaluate effect sizes relative to the baseline methods.
minor comments (2)
  1. [System Description] Clarify the precise operationalization of 'agency' and how user corrections are quantified and fed back into the inference model; the current description leaves the feedback loop underspecified.
  2. [Evaluation] The manuscript would benefit from a table or figure summarizing the exact questions or prompts used in the post-study questionnaire and any qualitative coding scheme applied to open responses.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for their thoughtful and constructive comments. We address each major point below and indicate where revisions will be made to the manuscript.

read point-by-point responses

  1. Referee: [Evaluation / Field Deployment] The central claim that the co-creation process 'produces strivings that are representative of participants' long-term goals' (abstract and evaluation) rests on post-deployment self-reports. No pre-study independent elicitation of long-term goals (e.g., via Emmons' strivings questionnaire or a separate baseline interview) is described, so it is impossible to distinguish recovery of pre-existing goals from post-hoc rationalization or demand characteristics after participants have edited the system's output.

    Authors: We agree this is a genuine limitation of the current evaluation design. The study was structured around the iterative co-creation loop, with representativeness and agency measured via post-deployment self-reports after participants had edited the system's inferences. This choice reflects the core contribution: demonstrating how user corrections feed back into induction. However, without an independent pre-study baseline (e.g., Emmons-style strivings elicitation before any system exposure), we cannot fully rule out post-hoc rationalization or demand effects. In the revision we will add an explicit limitations subsection in the Evaluation section discussing this issue and outlining a pre-post design for future work. We cannot retroactively collect pre-study data from the completed deployment, but we will strengthen the existing analysis of edit logs to show the specific changes participants made and how these shaped the final strivings. revision: partial

  2. Referee: [Abstract and Evaluation] The abstract states positive outcomes on agency and representativeness for N=14 but supplies no details on the exact instruments, scales, statistical tests, or baseline definitions used to measure these constructs. Without this information it is not possible to assess whether the data support the headline finding or to evaluate effect sizes relative to the baseline methods.

    Authors: The abstract is length-constrained, but the full Evaluation section details the instruments (7-point Likert scales for representativeness and perceived agency), the baseline conditions (non-editable inference and a simple logging baseline), and the statistical comparisons (paired tests with reported p-values and effect sizes). To improve accessibility, we will revise the abstract to include a concise clause such as: 'measured via 7-point Likert scales for representativeness and agency, showing significant gains over baselines (p < .05)'. This addition will not exceed abstract length limits while allowing readers to evaluate the claims directly. revision: yes

standing simulated objections not resolved
  • The absence of pre-study independent elicitation of long-term goals cannot be remedied without a new study, as the week-long field deployment has already concluded.

Circularity Check

0 steps flagged

No circularity; empirical evaluation independent of derivation

full rationale

The paper presents a system for striving co-creation grounded in external frameworks (Activity Theory, Emmons' strivings) and evaluates it through a week-long field deployment (N=14) with user feedback on representativeness and agency. No equations, parameter fitting presented as prediction, self-definitional constructs, or load-bearing self-citations appear in the provided text. The central claim rests on participant self-reports from the deployment rather than any reduction of outputs to inputs by construction. This is a standard empirical HCI study structure with no detectable circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The approach rests on the domain assumption that Activity Theory and Emmons' personal strivings framework can be operationalized on computer-use logs to produce meaningful hierarchies; no free parameters or invented entities are described in the abstract.

axioms (1)
  • domain assumption Activity Theory and Emmons' personal strivings framework provide a suitable basis for constructing hierarchical representations of activities from computer use observations
    Explicitly stated as grounding for the system in the abstract

pith-pipeline@v0.9.0 · 5512 in / 1297 out tokens · 40274 ms · 2026-05-09T18:58:57.968588+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

96 extracted references · 16 canonical work pages · 3 internal anchors

  1. [1]

    Gregory D Abowd, Anind K Dey, Peter J Brown, Nigel Davies, Mark Smith, and Pete Steggles. 1999. Towards a better understanding of context and context- awareness. InInternational symposium on handheld and ubiquitous computing. Springer, 304–307

    1999

  2. [2]

    Saleema Amershi, Maya Cakmak, William Bradley Knox, and Todd Kulesza. 2014. Power to the people: The role of humans in interactive machine learning.AI magazine35, 4 (2014), 105–120

    2014

  3. [3]

    Apple Computer. 1987. Knowledge Navigator. Concept video presented at Educom conference

    1987

  4. [4]

    Krisztian Balog, Filip Radlinski, and Shushan Arakelyan. 2019. Transparent, scrutable and explainable user models for personalized recommendation. InPro- ceedings of the 42nd international acm sigir conference on research and development in information retrieval. 265–274

    2019

  5. [5]

    Jakob E Bardram. 2009. Activity-based computing for medical work in hospitals. ACM Transactions on Computer-Human Interaction (TOCHI)16, 2 (2009), 1–36

    2009

  6. [6]

    Marit Bentvelzen, Paweł W Woźniak, Pia SF Herbes, Evropi Stefanidi, and Jasmin Niess. 2022. Revisiting reflection in hci: Four design resources for technologies that support reflection.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies6, 1 (2022), 1–27

    2022

  7. [7]

    Angie Boggust, Hyemin Bang, Hendrik Strobelt, and Arvind Satyanarayan. 2025. Abstraction alignment: comparing model-learned and human-encoded concep- tual relationships. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–20

    2025

  8. [8]

    Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners.Advances in neural information processing systems33 (2020), 1877–1901

    2020

  9. [9]

    Susan Bull and Judy Kay. 2007. Student models that invite the learner in: The SMILI:() Open learner modelling framework.International journal of artificial intelligence in education17, 2 (2007), 89–120

    2007

  10. [10]

    Myra Cheng, Sunny Yu, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, and Dan Jurafsky. 2025. Social sycophancy: A broader understanding of llm sycophancy. arXiv preprint arXiv:2505.13995(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  11. [11]

    Janghee Cho, Tian Xu, Abigail Zimmermann-Niefield, and Stephen Voida. 2022. Reflection in theory and reflection in practice: an exploration of the gaps in reflection support among personal informatics apps. InProceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1–23

    2022

  12. [12]

    Juheon Choi, Juyong Lee, Jian Kim, Chanyoung Kim, Taywon Min, W Bradley Knox, Min Kyung Lee, and Kimin Lee. 2025. State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living.arXiv preprint arXiv:2510.14513(2025)

    work page arXiv 2025

  13. [13]

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

  14. [14]

    GLOSS: Group of LLMs for open-ended sensemaking of passive sensing data for health and wellbeing.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies9, 3 (2025), 1–32

    2025

  15. [15]

    Adam J Coscia, Shunan Guo, Eunyee Koh, and Alex Endert. 2025. OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. 1–18

    2025

  16. [16]

    Anind K Dey. 2001. Understanding and using context.Personal and ubiquitous computing5, 1 (2001), 4–7

    2001

  17. [17]

    Anton N Dragunov, Thomas G Dietterich, Kevin Johnsrude, Matthew McLaugh- lin, Lida Li, and Jonathan L Herlocker. 2005. TaskTracer: a desktop environment to support multi-tasking knowledge workers. InProceedings of the 10th interna- tional conference on Intelligent user interfaces. 75–82

    2005

  18. [18]

    Tina Ekhtiar, Armağan Karahanoğlu, Rúben Gouveia, and Geke Ludden. 2023. Goals for goal setting: a scoping review on personal informatics. InProceedings of the 2023 ACM Designing Interactive Systems Conference. 2625–2641

    2023

  19. [19]

    Robert A Emmons. 1986. Personal strivings: An approach to personality and subjective well-being.Journal of Personality and Social psychology51, 5 (1986), 1058

    1986

  20. [20]

    Daniel A Epstein, Clara Caldeira, Mayara Costa Figueiredo, Xi Lu, Lucas M Silva, Lucretia Williams, Jong Ho Lee, Qingyang Li, Simran Ahuja, Qiuer Chen, et al

  21. [21]

    Mapping and taking stock of the personal informatics literature.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies4, 4 (2020), 1–38

    2020

  22. [22]

    Daniel A Epstein, An Ping, James Fogarty, and Sean A Munson. 2015. A lived informatics model of personal informatics. InProceedings of the 2015 ACM inter- national joint conference on pervasive and ubiquitous computing. 731–742

    2015

  23. [23]

    I always assumed that I wasn’t really that close to [her]

    Motahhare Eslami, Aimee Rickman, Kristen Vaccaro, Amirhossein Aleyasen, Andy Vuong, Karrie Karahalios, Kevin Hamilton, and Christian Sandvig. 2015. " I always assumed that I wasn’t really that close to [her]" Reasoning about invisible algorithms in news feeds. InProceedings of the 33rd annual ACM conference on human factors in computing systems. 153–162

    2015

  24. [24]

    Faries and Wesley C

    Mark D. Faries and Wesley C. Dudgeon. 2019.The Intention–Behavior Gap. CRC Press, 241–252. doi:10.1201/9781315201108-20

    work page doi:10.1201/9781315201108-20 2019

  25. [25]

    KJ Feng, Kevin Pu, Matt Latzke, Tal August, Pao Siangliulue, Jonathan Bragg, Daniel S Weld, Amy X Zhang, and Joseph Chee Chang. 2024. Cocoa: Co-planning and co-execution with ai agents.arXiv preprint arXiv:2412.10999(2024)

    work page arXiv 2024

  26. [26]

    Rowanne Fleck and Geraldine Fitzpatrick. 2010. Reflecting on reflection: framing a design landscape. InProceedings of the 22nd conference of the computer-human interaction special interest group of australia on computer-human interaction. 216–223

    2010

  27. [27]

    Krzysztof Gajos and Daniel S Weld. 2004. SUPPLE: automatically generating user interfaces. InProceedings of the 9th international conference on Intelligent user interfaces. 93–100

    2004

  28. [28]

    2004.Activity-centered design: An ecolog- ical approach to designing smart tools and usable systems

    Geraldine Gay and Helene Hembrooke. 2004.Activity-centered design: An ecolog- ical approach to designing smart tools and usable systems. Mit Press

    2004

  29. [29]

    Constant, constant, multi-tasking craziness

    Victor M. González and Gloria Mark. 2004. "Constant, constant, multi-tasking craziness": managing multiple working spheres. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Vienna, Austria)(CHI ’04). Association for Computing Machinery, New York, NY, USA, 113–120. doi:10. 1145/985692.985707

    work page arXiv 2004

  30. [30]

    Mitchell L Gordon, Michelle S Lam, Joon Sung Park, Kayur Patel, Jeff Hancock, Tatsunori Hashimoto, and Michael S Bernstein. 2022. Jury learning: Integrating dissenting voices into machine learning models. InProceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1–19

    2022

  31. [31]

    E Tory Higgins. 1987. Self-discrepancy: a theory relating self and affect.Psycho- logical review94, 3 (1987), 319

    1987

  32. [32]

    Tad Hirsch, Kritzia Merced, Shrikanth Narayanan, Zac E Imel, and David C Atkins. 2017. Designing contestability: Interaction design, machine learning, and mental health. InProceedings of the 2017 conference on designing interactive systems. 95–99

    2017

  33. [33]

    Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. InProceedings of the SIGCHI conference on Human Factors in Computing Systems. 159–166

    1999

  34. [34]

    Eric J Horvitz, John S Breese, David Heckerman, David Hovel, and Koos Rom- melse. 2013. The Lumiere project: Bayesian user modeling for inferring the goals and needs of software users.arXiv preprint arXiv:1301.7385(2013)

    work page arXiv 2013

  35. [35]

    https://littlebird.ai/. 2026. Littlebird

    2026

  36. [36]

    Saffron Huang, Esin Durmus, Miles McCain, Kunal Handa, Alex Tamkin, Jerry Hong, Michael Stern, Arushi Somani, Xiuruo Zhang, and Deep Ganguli. 2025. Values in the wild: Discovering and analyzing values in real-world language model interactions.arXiv preprint arXiv:2504.15236(2025)

    work page arXiv 2025

  37. [37]

    Maurice Jakesch, Advait Bhat, Daniel Buschek, Lior Zalmanson, and Mor Naaman

  38. [38]

    In Proceedings of the 2023 CHI conference on human factors in computing systems

    Co-writing with opinionated language models affects users’ views. In Proceedings of the 2023 CHI conference on human factors in computing systems. 1–15

    2023

  39. [39]

    Brennan Jones, Yan Xu, Qisheng Li, and Stefan Scherer. 2024. Designing a Proactive Context-Aware AI Chatbot for People’s Long-Term Goals. InExtended abstracts of the CHI conference on human factors in computing systems. 1–7

    2024

  40. [40]

    Matthew Jörke, Defne Genç, Valentin Teutschbein, Shardul Sapkota, Sarah Chung, Paul Schmiedmayer, Maria Ines Campero, Abby C King, Emma Brunskill, and James A Landay. 2025. Bloom: Designing for LLM-augmented behavior change interactions.arXiv preprint arXiv:2510.05449(2025)

    work page arXiv 2025

  41. [41]

    Matthew Jörke, Shardul Sapkota, Lyndsea Warkenthien, Niklas Vainio, Paul Schmiedmayer, Emma Brunskill, and James A Landay. 2025. GPTCoach: towards LLM-based physical activity coaching. InProceedings of the 2025 CHI conference on human factors in computing systems. 1–46

    2025

  42. [42]

    Matthew Jörke, Yasaman S Sefidgar, Talie Massachi, Jina Suh, and Gonzalo Ramos

  43. [43]

    InProceedings of the 28th International Conference on Intelligent User Interfaces

    Pearl: A technology probe for machine-assisted reflection on personal data. InProceedings of the 28th International Conference on Intelligent User Interfaces. 902–918

  44. [44]

    Victor Kaptelinin. 2003. UMEA: translating interaction histories into project contexts. InProceedings of the SIGCHI conference on Human factors in computing systems. 353–360

    2003

  45. [45]

    2009.Acting with technology: Activity theory and interaction design

    Victor Kaptelinin and Bonnie A Nardi. 2009.Acting with technology: Activity theory and interaction design. MIT press

    2009

  46. [46]

    Nadia Karizat, Dan Delmonaco, Motahhare Eslami, and Nazanin Andalibi. 2021. Algorithmic folk theories and identity: How TikTok users co-produce knowledge of identity and engage in algorithmic resistance.Proceedings of the ACM on human-computer interaction5, CSCW2 (2021), 1–44

    2021

  47. [47]

    Henry A Kautz, James F Allen, et al . 1986. Generalized plan recognition.. In AAAI, Vol. 86. Philadelphia, PA, 5

    1986

  48. [48]

    Judy Kay and Bob Kummerfeld. 2013. Creating personalized systems that people can scrutinize and control: Drivers, principles and experience.ACM Transactions on Interactive Intelligent Systems (TiiS)2, 4 (2013), 1–42

    2013

  49. [49]

    What Are You Really Trying to Do?

    Elisabeth T Kersten-van Dijk, Joyce HDM Westerink, Femke Beute, and Wij- nand A IJsselsteijn. 2017. Personal informatics, self-insight, and behavior change: A critical review of current literature.Human–Computer Interaction32, 5-6 “What Are You Really Trying to Do?”: Co-Creating Life Goals from Everyday Computer Use (2017), 268–296

    2017

  50. [50]

    Arie W Kruglanski, James Y Shah, Ayelet Fishbach, Ron Friedman, Woo Young Chun, and David Sleeth-Keppler. 2018. A theory of goal systems. InThe motivated mind. Routledge, 207–250

    2018

  51. [51]

    Todd Kulesza, Margaret Burnett, Weng-Keen Wong, and Simone Stumpf. 2015. Principles of explanatory debugging to personalize interactive machine learning. InProceedings of the 20th international conference on intelligent user interfaces. 126–137

    2015

  52. [52]

    Michelle S Lam, Omar Shaikh, Hallie Xu, Alice Guo, Diyi Yang, Jeffrey Heer, James A Landay, and Michael S Bernstein. 2025. Just-In-Time Objectives: A General Approach for Specialized AI Interactions.arXiv preprint arXiv:2510.14591 (2025)

    work page arXiv 2025

  53. [53]

    Michelle S Lam, Janice Teoh, James A Landay, Jeffrey Heer, and Michael S Bern- stein. 2024. Concept induction: Analyzing unstructured text with high-level concepts using lloom. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–28

    2024

  54. [54]

    Leont’ev

    Aleksei N. Leont’ev. 1978.Activity, Consciousness, and Personality. Prentice-Hall, Englewood Cliffs, NJ

    1978

  55. [55]

    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. 557–566

    2010

  56. [56]

    Jiachen Li, Xiwen Li, Justin Steinberg, Akshat Choube, Bingsheng Yao, Xuhai Xu, Dakuo Wang, Elizabeth Mynatt, and Varun Mishra. 2025. Vital Insight: Assisting Experts’ Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-in-the-Loop LLM.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technol...

    2025

  57. [57]

    Yang Li and James A Landay. 2008. Activity-based prototyping of ubicomp applications for long-lived, everyday human activities. InProceedings of the SIGCHI conference on Human factors in computing systems. 1303–1312

    2008

  58. [58]

    Edwin A Locke and Gary P Latham. 2019. The development of goal setting theory: A half century retrospective.Motivation science5, 2 (2019), 93

    2019

  59. [59]

    Yaxi Lu, Shenzhi Yang, Cheng Qian, Guirong Chen, Qinyu Luo, Yesai Wu, Huadong Wang, Xin Cong, Zhong Zhang, Yankai Lin, et al . 2024. Proactive agent: Shifting llm agents from reactive responses to active assistance.arXiv preprint arXiv:2410.12361(2024)

    work page arXiv 2024

  60. [60]

    Henrietta Lyons, Eduardo Velloso, and Tim Miller. 2021. Conceptualising con- testability: Perspectives on contesting algorithmic decisions.Proceedings of the ACM on Human-Computer Interaction5, CSCW1 (2021), 1–25

    2021

  61. [61]

    Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al

  62. [62]

    Self-refine: Iterative refinement with self-feedback.Advances in neural information processing systems36 (2023), 46534–46594

    2023

  63. [63]

    Pattie Maes. 1994. Agents that reduce work and information overload.Commun. ACM37, 7 (1994), 30–40

    1994

  64. [64]

    Gloria Mark, Victor M Gonzalez, and Justin Harris. 2005. No task left behind? Examining the nature of fragmented work. InProceedings of the SIGCHI conference on Human factors in computing systems. 321–330

    2005

  65. [65]

    2012.Motivational interviewing: Helping people change

    William R Miller and Stephen Rollnick. 2012.Motivational interviewing: Helping people change. Guilford press

    2012

  66. [66]

    Jasmin Niess and Paweł W Woźniak. 2018. Supporting meaningful personal fitness: The tracker goal evolution model. InProceedings of the 2018 CHI conference on human factors in computing systems. 1–12

    2018

  67. [67]

    Helen Nissenbaum. 2004. Privacy as contextual integrity.Wash. L. Rev.79 (2004), 119

    2004

  68. [68]

    Rock Yuren Pang, KJ Feng, Shangbin Feng, Chu Li, Weijia Shi, Yulia Tsvetkov, Jeffrey Heer, and Katharina Reinecke. 2025. Interactive reasoning: Visualizing and controlling chain-of-thought reasoning in large language models.arXiv preprint arXiv:2506.23678(2025)

    work page arXiv 2025

  69. [69]

    Yousefi, Tung Vuong, Marie AlGhossein, Tuukka Ruotsalo, Giulio Jaccuci, and Samuel Kaski

    Zeinab R. Yousefi, Tung Vuong, Marie AlGhossein, Tuukka Ruotsalo, Giulio Jaccuci, and Samuel Kaski. 2024. Entity footprinting: Modeling contextual user states via digital activity monitoring.ACM Transactions on Interactive Intelligent Systems14, 2 (2024), 1–27

    2024

  70. [70]

    Byron Reeves, Nilam Ram, Thomas N Robinson, James J Cummings, C Lee Giles, Jennifer Pan, Agnese Chiatti, MJ Cho, Katie Roehrick, Xiao Yang, et al . 2021. Screenomics: A framework to capture and analyze personal life experiences and the ways that technology shapes them.Human–Computer Interaction36, 2 (2021), 150–201

    2021

  71. [71]

    Jessica Schroeder, Ravi Karkar, Natalia Murinova, James Fogarty, and Sean A Munson. 2019. Examining opportunities for goal-directed self-tracking to support chronic condition management.Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies3, 4 (2019), 1–26

    2019

  72. [72]

    Yasaman S Sefidgar, Carla L Castillo, Shaan Chopra, Liwei Jiang, Tae Jones, Anant Mittal, Hyeyoung Ryu, Jessica Schroeder, Allison Cole, Natalia Murinova, et al

  73. [73]

    InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems

    MigraineTracker: Examining patient experiences with goal-directed self- tracking for a chronic health condition. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–19

    2024

  74. [74]

    Abigail J Sellen and Steve Whittaker. 2010. Beyond total capture: a constructive critique of lifelogging.Commun. ACM53, 5 (2010), 70–77

    2010

  75. [75]

    Omar Shaikh, Valentino Emil Chai, Michele Gelfand, Diyi Yang, and Michael S Bernstein. 2024. Rehearsal: Simulating conflict to teach conflict resolution. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–20

    2024

  76. [76]

    Omar Shaikh, Shardul Sapkota, Shan Rizvi, Eric Horvitz, Joon Sung Park, Diyi Yang, and Michael S Bernstein. 2025. Creating general user models from computer use. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. 1–23

    2025

  77. [77]

    Mrinank Sharma, Miles McCain, Raymond Douglas, and David Duvenaud. 2026. Who’s in Charge? Disempowerment Patterns in Real-World LLM Usage.arXiv preprint arXiv:2601.19062(2026)

    work page arXiv 2026

  78. [78]

    Alison Smith-Renner, Ron Fan, Melissa Birchfield, Tongshuang Wu, Jordan Boyd- Graber, Daniel S Weld, and Leah Findlater. 2020. No explainability without accountability: An empirical study of explanations and feedback in interactive ml. InProceedings of the 2020 chi conference on human factors in computing systems. 1–13

    2020

  79. [79]

    Barnum Effect

    C Richard Snyder, Randee J Shenkel, and Carol R Lowery. 1977. Acceptance of personality interpretations: the" Barnum Effect" and beyond.Journal of consulting and clinical psychology45, 1 (1977), 104

    1977

  80. [80]

    Sangho Suh, Bryan Min, Srishti Palani, and Haijun Xia. 2023. Sensecape: En- abling multilevel exploration and sensemaking with large language models. In Proceedings of the 36th annual ACM symposium on user interface software and technology. 1–18

    2023

Showing first 80 references.