pith. sign in

arxiv: 2504.11795 · v3 · submitted 2025-04-16 · 💻 cs.HC

Schemex: Discovering Structural Abstractions from Examples

Sitong Wang , Samia Menon , Dingzeyu Li , Xiaojuan Ma , Richard Zemel , Lydia B. Chilton This is my paper

Pith reviewed 2026-05-22 20:58 UTC · model grok-4.3

classification 💻 cs.HC
keywords schema inductionstructural abstractionsinteractive AI workflowclusteringabstractioncontrastive refinementhuman-AI collaborationcreative patterns
0
0 comments X

The pith

Schemex decomposes schema induction into clustering examples, abstracting schemas, and contrastive refinement to yield more actionable structures.

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

The paper presents Schemex as an interactive AI workflow that helps people extract implicit patterns from sets of examples, such as narrative arcs or design principles. It breaks the discovery process into three stages that first group similar examples, then form candidate abstractions, and finally test and sharpen those abstractions by creating new instances for direct comparison. Studies with users show this produces schemas that are more useful in practice than those from a strong baseline AI, while preserving broad applicability, and participants identified deeper patterns amid surface variation. The work matters because many creative and communicative tasks depend on such hidden structures that resist direct inspection.

Core claim

Schemex is an interactive AI workflow that systematically supports schema induction by decomposing it into three tractable stages: clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals. Studies show that Schemex produces more actionable schemas than a frontier baseline without sacrificing generalizability, with participants uncovering deep and nuanced structural patterns.

What carries the argument

The three-stage interactive workflow of clustering, abstracting, and contrastive refinement that turns raw examples into testable structural abstractions.

If this is right

  • Users obtain structural patterns that transfer to new instances while remaining specific enough to guide action.
  • The interactive comparison step reduces the chance that abstractions become either too vague or too narrow.
  • Designers of creative tools gain a concrete process for supporting structure discovery rather than relying on direct prompting alone.
  • The same staged approach can be applied to other domains where implicit rules underlie examples, such as music or software.

Where Pith is reading between the lines

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

  • The contrastive generation step might be adapted to refine abstractions in non-creative domains like scientific hypothesis formation.
  • Integrating user feedback loops at each stage could further reduce the surface-variation problem in larger example sets.
  • The workflow suggests that pure generation models may benefit from explicit clustering and comparison modules when the goal is abstraction rather than imitation.

Load-bearing premise

Schema induction can be usefully split into the three stages of clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals.

What would settle it

A controlled study in which participants using the three-stage workflow fail to produce schemas rated more actionable than those from the baseline system, or in which the schemas lose applicability to new examples.

Figures

Figures reproduced from arXiv: 2504.11795 by Dingzeyu Li, Lydia B. Chilton, Richard Zemel, Samia Menon, Sitong Wang, Xiaojuan Ma.

Figure 1
Figure 1. Figure 1: Schemex helps novices induce schemas from real-world examples (e.g., CHI paper abstracts). (1) Input: users provide [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Screenshot of Schemex, an interactive, AI-powered visual workflow that helps users induce schemas from examples. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Schemex Stage 1: Clustering [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Schemex Stage 2: Abstraction [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Schemex Stage 3: Contrastive Refinement. [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Participant ratings over five research questions for baseline vs. Schemex. [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Schemas P4 induced with o1-pro (left) and Schemex (right) for the example set of NPR article subheaders. While [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
read the original abstract

Creative and communicative work is often underpinned by implicit structures, such as the Hero's Journey in storytelling, design patterns in software, or chord progressions in music. People often learn these structures from examples - a process known as schema induction. However, because schemas are abstract and implicit, they are difficult to discover: shared structural patterns are obscured by surface-level variation, and balancing generality with specificity is challenging. We present Schemex, an interactive AI workflow that systematically supports schema induction by decomposing it into three tractable stages: clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals. Studies show that Schemex produces more actionable schemas than a frontier baseline without sacrificing generalizability, with participants uncovering deep and nuanced structural patterns. We also discuss design implications for the cognitive role of interactive process in structure discovery.

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

0 major / 3 minor

Summary. The manuscript introduces Schemex, an interactive AI workflow for schema induction that decomposes the process into three stages: clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals. User studies are reported to show that Schemex produces more actionable schemas than a frontier baseline without sacrificing generalizability, with participants uncovering deep and nuanced structural patterns. The paper concludes with design implications for the cognitive role of interactive processes in structure discovery.

Significance. If the empirical results hold under scrutiny, this work offers a meaningful contribution to HCI and AI-assisted creative tools by providing a structured, interactive framework for discovering implicit structures across domains such as storytelling, design, and music. The three-stage decomposition is presented as a practical method rather than a universal axiom, and the absence of free parameters or invented entities (as noted in the supporting analysis) is a strength that keeps the approach grounded in examples. The emphasis on contrastive refinement and actionability could influence future systems that support human structure discovery.

minor comments (3)
  1. Abstract: The summary of study outcomes would be strengthened by a brief mention of key metrics (e.g., actionability ratings or generalizability scores) or participant numbers, even if full details appear in §4 or §5.
  2. Method section: Clarify how the frontier baseline was implemented and matched to Schemex in terms of interaction style and output format to ensure the comparison isolates the effect of the three-stage workflow.
  3. Discussion: The design implications for interactive processes could be tied more explicitly back to specific observations from the user studies rather than remaining at a high level.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the Schemex manuscript, including the accurate summary of the three-stage workflow, the user study findings on actionability and generalizability, and the recommendation for minor revision. The significance statement correctly identifies the contribution to HCI and AI-assisted structure discovery. No major comments were provided in the report.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper describes an empirical interactive AI system (Schemex) that decomposes schema induction into three stages presented as the proposed workflow rather than a derived result. No equations, fitted parameters, self-referential derivations, or load-bearing self-citations appear in the provided text. Claims rest on user studies comparing to a baseline, with the decomposition introduced as a practical method rather than proven from internal assumptions. The work is self-contained as a system description and evaluation.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review is based solely on the abstract; no free parameters, invented entities, or additional axioms beyond the core workflow premise are stated.

axioms (1)
  • domain assumption Schema induction can be effectively supported by decomposing it into clustering, abstraction, and contrastive refinement stages.
    This premise is the explicit foundation of the Schemex workflow described in the abstract.

pith-pipeline@v0.9.0 · 5689 in / 1233 out tokens · 59947 ms · 2026-05-22T20:58:39.574359+00:00 · methodology

discussion (0)

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

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Discovery-Oriented Faceting: From Coverage to Blind-Spot Discovery

    cs.HC 2026-05 unverdicted novelty 6.0

    DOF ranks document categories by distinctiveness instead of size to promote blind-spot discovery, surfacing different content than coverage-based methods across four domains.

  2. Narrix: Remixing Narrative Strategies from Examples for Story Writing

    cs.HC 2026-04 unverdicted novelty 6.0

    Narrix helps novices identify and reuse narrative strategies from examples through visualization and strategy-steered generation, improving retention, confidence, and adaptation over chat interfaces in a 12-person study.

Reference graph

Works this paper leans on

60 extracted references · 60 canonical work pages · cited by 2 Pith papers

  1. [1]

    Maneesh Agrawala, Wilmot Li, and Floraine Berthouzoz. 2011. Design Principles for Visual Communication.Commun. ACM54, 4 (April 2011), 60–69. https: //doi.org/10.1145/1924421.1924439

    work page doi:10.1145/1924421.1924439 2011

  2. [2]

    Maneesh Agrawala and Chris Stolte. 2001. Rendering Effective Route Maps: Improving Usability Through Generalization. InProceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’01). ACM, New York, NY, USA, 241–249. https://doi.org/10.1145/383259.383286

    work page doi:10.1145/383259.383286 2001

  3. [3]

    1977.A Pattern Language - Towns, Buildings, Construction

    Christopher Alexander, Sara Ishikawa, Murray Silverstein, Max Jacobson, Ingrid Fiksdahl-King, and Shlomo Angel. 1977.A Pattern Language - Towns, Buildings, Construction. Oxford University Press

    work page 1977

  4. [4]

    Khalid Alharbi and Tom Yeh. 2015. Collect, decompile, extract, stats, and diff: Mining design pattern changes in Android apps. InProceedings of the 17th in- ternational conference on human-computer interaction with mobile devices and services. 515–524

    work page 2015

  5. [5]

    Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N Bennett, Kori Inkpen, et al. 2019. Guidelines for human-AI interaction. InProceedings of the 2019 chi conference on human factors in computing systems. 1–13

    work page 2019

  6. [6]

    Joseph Campbell. 2008. The hero with a thousand faces.New World Library (2008)

    work page 2008

  7. [7]

    Minsuk Chang, Léonore V Guillain, Hyeungshik Jung, Vivian M Hare, Juho Kim, and Maneesh Agrawala. 2018. Recipescape: An interactive tool for analyzing cooking instructions at scale. InProceedings of the 2018 CHI conference on human factors in computing systems. 1–12

    work page 2018

  8. [8]

    Lydia B Chilton, Greg Little, Darren Edge, Daniel S Weld, and James A Landay

    work page

  9. [9]

    InProceedings of the SIGCHI Conference on Human Factors in Computing Systems

    Cascade: Crowdsourcing taxonomy creation. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 1999–2008

    work page 1999

  10. [10]

    Chilton, Ecenaz Jen Ozmen, Sam H

    Lydia B. Chilton, Ecenaz Jen Ozmen, Sam H. Ross, and Vivian Liu. 2021. VisiFit: Structuring Iterative Improvement for Novice Designers. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI ’21). Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/ 3411764.3445089

    work page arXiv 2021

  11. [11]

    Chilton, Savvas Petridis, and Maneesh Agrawala

    Lydia B. Chilton, Savvas Petridis, and Maneesh Agrawala. 2019. VisiBlends: A Flexible Workflow for Visual Blends. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). Association for Computing Machinery, New York, NY, USA, 172:1–172:14. https://doi.org/10.1145/3290605. 3300402

    work page doi:10.1145/3290605 2019

  12. [12]

    João Miguel Cunha, Pedro Martins, and Penousal Machado. 2018. How Shell and Horn Make a Unicorn: Experimenting with Visual Blending in Emoji. In Proceedings of the Ninth International Conference on Computational Creativity. 145–152. https://openreview.net/forum?id=u1mCZAjwX7

    work page 2018

  13. [13]

    Leonidas AA Doumas, John E Hummel, and Catherine M Sandhofer. 2008. A theory of the discovery and predication of relational concepts.Psychological review115, 1 (2008), 1

    work page 2008

  14. [14]

    Hakan Duman, Alex Healing, and Robert Ghanea-Hercock. 2009. Adaptive Visual Clustering for Mixed-Initiative Information Structuring. InHuman Interface and the Management of Information. Designing Information Environments: Symposium on Human Interface 2009, Held as Part of HCI International 2009, San Diego, CA, USA, July 19-24, 2009, Procceedings, Part I. ...

    work page 2009

  15. [15]

    Van Duyne, James Landay, and Jason I

    Douglas K. Van Duyne, James Landay, and Jason I. Hong. 2002.The Design of Sites: Patterns, Principles, and Processes for Crafting a Customer-Centered Web Experience. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA

    work page 2002

  16. [16]

    Alex Endert, Patrick Fiaux, and Chris North. 2012. Semantic interaction for visual text analytics. InProceedings of the SIGCHI conference on Human factors in computing systems. 473–482

    work page 2012

  17. [17]

    2013.Constructivism: Theory, perspectives, and practice

    Catherine Twomey Fosnot. 2013.Constructivism: Theory, perspectives, and practice. Teachers College Press

    work page 2013

  18. [18]

    2013.Chord Progressions: Theory and Practice

    Dan Fox and Dick Weissman. 2013.Chord Progressions: Theory and Practice. Alfred Music

    work page 2013

  19. [19]

    1995.Design patterns: elements of reusable object-oriented software

    Erich Gamma, Richard Helm, Ralph Johnson, and John Vlissides. 1995.Design patterns: elements of reusable object-oriented software. Pearson Deutschland GmbH

    work page 1995

  20. [20]

    Jie Gao, Yuchen Guo, Gionnieve Lim, Tianqin Zhang, Zheng Zhang, Toby Jia- Jun Li, and Simon Tangi Perrault. 2024. CollabCoder: a lower-barrier, rigorous workflow for inductive collaborative qualitative analysis with large language models. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–29

    work page 2024

  21. [21]

    Simret Araya Gebreegziabher, Yukun Yang, Elena L Glassman, and Toby Jia-Jun Li. 2025. Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–18

    work page 2025

  22. [22]

    Dedre Gentner. 1983. Structure-mapping: A theoretical framework for analogy. Cognitive science7, 2 (1983), 155–170

    work page 1983

  23. [23]

    Dedre Gentner and Arthur B Markman. 1997. Structure mapping in analogy and similarity.American psychologist52, 1 (1997), 45. 13

    work page 1997

  24. [24]

    Katy Ilonka Gero, Chelse Swoopes, Ziwei Gu, Jonathan K Kummerfeld, and Elena L Glassman. 2024. Supporting sensemaking of large language model outputs at scale. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–21

    work page 2024

  25. [25]

    Mary L Gick and Keith J Holyoak. 1983. Schema induction and analogical transfer. Cognitive psychology15, 1 (1983), 1–38

    work page 1983

  26. [26]

    Sumit Gulwani. 2011. Automating string processing in spreadsheets using input- output examples.ACM Sigplan Notices46, 1 (2011), 317–330

    work page 2011

  27. [27]

    2010.Mixed-Initiative Clustering

    Yifen Huang. 2010.Mixed-Initiative Clustering. Carnegie Mellon University

    work page 2010

  28. [28]

    Jit, Jennifer Spinney, Priyank Chandra, Lydia B

    Sophia S. Jit, Jennifer Spinney, Priyank Chandra, Lydia B. Chilton, and Robert Soden. 2024. Writing out the Storm: Designing and Evaluating Tools for Weather Risk Messaging. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery, New York, NY, USA, 502:1–502:16. https://doi.org/10.1145...

    work page doi:10.1145/3613904.3641926 2024

  29. [29]

    Kahn, Nathan G

    Peter H. Kahn, Nathan G. Freier, Takayuki Kanda, Hiroshi Ishiguro, Jolina H. Ruckert, Rachel L. Severson, and Shaun K. Kane. 2008. Design Patterns for Social- ity in Human-robot Interaction. InProceedings of the 3rd ACM/IEEE International Conference on Human Robot Interaction(Amsterdam, The Netherlands)(HRI ’08). ACM, New York, NY, USA, 97–104. https://do...

    work page doi:10.1145/1349822.1349836 2008

  30. [30]

    Charles Kemp and Joshua B Tenenbaum. 2008. The discovery of structural form. Proceedings of the National Academy of Sciences105, 31 (2008), 10687–10692

    work page 2008

  31. [31]

    Bernstein, and Daniela Stein- sapir

    Joy Kim, Mira Dontcheva, Wilmot Li, Michael S. Bernstein, and Daniela Stein- sapir. 2015. Motif: Supporting Novice Creativity Through Expert Patterns. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Comput- ing Systems(Seoul, Republic of Korea)(CHI ’15). ACM, New York, NY, USA, 1211–1220. https://doi.org/10.1145/2702123.2702507

    work page doi:10.1145/2702123.2702507 2015

  32. [32]

    Aniket Kittur, Andrew M Peters, Abdigani Diriye, and Michael Bove. 2014. Stand- ing on the schemas of giants: socially augmented information foraging. InPro- ceedings of the 17th ACM conference on Computer supported cooperative work & social computing. 999–1010

    work page 2014

  33. [33]

    Christian Kruschitz and Martin Hitz. 2010. Human-computer interaction design patterns: structure, methods, and tools.Int. J. Adv. Softw3, 1 (2010)

    work page 2010

  34. [34]

    Ranjitha Kumar, Arvind Satyanarayan, Cesar Torres, Maxine Lim, Salman Ahmad, Scott R Klemmer, and Jerry O Talton. 2013. Webzeitgeist: design mining the web. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 3083–3092

    work page 2013

  35. [35]

    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

    work page 2024

  36. [36]

    Mackenzie Leake, Abe Davis, Anh Truong, and Maneesh Agrawala. 2017. Com- putational Video Editing for Dialogue-driven Scenes.ACM Trans. Graph.36, 4, Article 130 (July 2017), 14 pages. https://doi.org/10.1145/3072959.3073653

    work page doi:10.1145/3072959.3073653 2017

  37. [37]

    Michael Xieyang Liu, Tongshuang Wu, Tianying Chen, Franklin Mingzhe Li, Aniket Kittur, and Brad A Myers. 2024. Selenite: Scaffolding Online Sensemak- ing with Comprehensive Overviews Elicited from Large Language Models. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–26

    work page 2024

  38. [38]

    Arthur B Markman and Dedre Gentner. 1993. Structural alignment during similarity comparisons.Cognitive psychology25, 4 (1993), 431–467

    work page 1993

  39. [39]

    Samia Menon, Sitong Wang, and Lydia Chilton. 2024. MoodSmith: Enabling Mood-Consistent Multimedia for AI-Generated Advocacy Campaigns.arXiv preprint arXiv:2403.12356(2024)

    work page arXiv 2024

  40. [40]

    Paul Merrell, Eric Schkufza, Zeyang Li, Maneesh Agrawala, and Vladlen Koltun

    work page

  41. [41]

    InACM SIGGRAPH 2011 Papers(Vancouver, British Columbia, Canada)(SIGGRAPH ’11)

    Interactive Furniture Layout Using Interior Design Guidelines. InACM SIGGRAPH 2011 Papers(Vancouver, British Columbia, Canada)(SIGGRAPH ’11). ACM, New York, NY, USA, Article 87, 10 pages. https://doi.org/10.1145/1964921. 1964982

    work page doi:10.1145/1964921 2011

  42. [42]

    Piotr Mirowski, Kory W Mathewson, Jaylen Pittman, and Richard Evans. 2023. Co-writing screenplays and theatre scripts with language models: Evaluation by industry professionals. InProceedings of the 2023 CHI conference on human factors in computing systems. 1–34

    work page 2023

  43. [43]

    Nic Newman. 2022. How publishers are learning to create and distribute news on TikTok. (2022)

    work page 2022

  44. [44]

    Peter Pirolli and Stuart Card. 2005. The sensemaking process and leverage points for analyst technology as identified through cognitive task analysis. In Proceedings of international conference on intelligence analysis, Vol. 5. McLean, VA, USA, 2–4

    work page 2005

  45. [45]

    Julien Porquet, Sitong Wang, and Lydia B Chilton. 2024. Copying style, Extracting value: Illustrators’ Perception of AI Style Transfer and its Impact on Creative Labor.arXiv preprint arXiv:2409.17410(2024)

    work page arXiv 2024

  46. [46]

    Allison Sauppé and Bilge Mutlu. 2014. Design Patterns for Exploring and Pro- totyping Human-robot Interactions. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Toronto, Ontario, Canada)(CHI ’14). ACM, New York, NY, USA, 1439–1448. https://doi.org/10.1145/2556288.2557057

    work page doi:10.1145/2556288.2557057 2014

  47. [47]

    Burr Settles. 2009. Active learning literature survey. (2009)

    work page 2009

  48. [48]

    John Stasko, Carsten Gorg, Zhicheng Liu, and Kanupriya Singhal. 2007. Jigsaw: supporting investigative analysis through interactive visualization. In2007 IEEE Symposium on Visual Analytics Science and Technology. IEEE, 131–138

    work page 2007

  49. [49]

    Sangho Suh, Meng Chen, Bryan Min, Toby Jia-Jun Li, and Haijun Xia. 2024. Lumi- nate: 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. 1–26

    work page 2024

  50. [50]

    John Sweller. 1988. Cognitive load during problem solving: Effects on learning. Cognitive science12, 2 (1988), 257–285

    work page 1988

  51. [51]

    Sirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang, Srishti Palani, and Steven P Dow. 2025. DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design.arXiv preprint arXiv:2502.09867(2025)

    work page arXiv 2025

  52. [52]

    Anh Truong, Peggy Chi, David Salesin, Irfan Essa, and Maneesh Agrawala

    work page

  53. [53]

    InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems

    Automatic generation of two-level hierarchical tutorials from instruc- tional makeup videos. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–16

    work page 2021

  54. [54]

    Nickerson, and Lydia B

    Sitong Wang, Samia Menon, Tao Long, Keren Henderson, Dingzeyu Li, Kevin Crowston, Mark Hansen, Jeffrey V. Nickerson, and Lydia B. Chilton. 2024. ReelFramer: Human-AI Co-Creation for News-to-Video Translation. InPro- ceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery, New York, NY, USA, ...

    work page doi:10.1145/3613904.3642868 2024

  55. [55]

    Sitong Wang, Zheng Ning, Anh Truong, Mira Dontcheva, Dingzeyu Li, and Lydia B. Chilton. 2024. PodReels: Human-AI Co-Creation of Video Podcast Teasers. InProceedings of the 2024 ACM Designing Interactive Systems Conference (DIS ’24). Association for Computing Machinery, New York, NY, USA. https: //doi.org/10.1145/3643834.3661591

    work page doi:10.1145/3643834.3661591 2024

  56. [56]

    Sitong Wang, Savvas Petridis, Taeahn Kwon, Xiaojuan Ma, and Lydia B. Chilton

    work page

  57. [57]

    InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23)

    PopBlends: Strategies for Conceptual Blending with Large Language Models. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23). Association for Computing Machinery, New York, NY, USA, 435:1–435:19. https://doi.org/10.1145/3544548.3580948

    work page doi:10.1145/3544548.3580948 2023

  58. [58]

    Saelyne Yang, Anh Truong, Juho Kim, and Dingzeyu Li. 2025. VideoMix: Ag- gregating How-To Videos for Task-Oriented Learning. InProceedings of the 30th International Conference on Intelligent User Interfaces. 1564–1580

    work page 2025

  59. [59]

    Lixiu Yu, Aniket Kittur, and Robert E Kraut. 2014. Distributed analogical idea generation: inventing with crowds. InProceedings of the SIGCHI conference on Human Factors in Computing Systems. 1245–1254

    work page 2014

  60. [60]

    Yes" = Clearly demonstrates the feature

    Lixiu Yu, Aniket Kittur, and Robert E Kraut. 2014. Searching for analogical ideas with crowds. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 1225–1234. A PROMPTS USED IN SCHEMEX A.1 Get clusters I’m learning how to {content_type}. Analyze the following examples to identify clusters based on STRUCTURAL and RHETORICAL pattern...

    work page 2014