Schemex: Discovering Structural Abstractions from Examples

[2504.11795] Schemex: Discovering Structural Abstractions from Examples Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Human-Computer Interaction arXiv:2504.11795 (cs) [Submitted on 16 Apr 2025 ( v1 ), last revised 8 Apr 2026 (this version, v3)] Title: Schemex: Discovering Structural Abstractions from Examples Authors: Sitong Wang , Samia Menon , Dingzeyu Li , Xiaojuan Ma , Richard Zemel , Lydia B. Chilton View a PDF of the paper titled Schemex: Discovering Structural Abstractions from Examples, by Sitong Wang and 5 other authors View PDF HTML (experimental) 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. Subjects: Human-Computer Interaction (cs.HC) Cite as: arXiv:2504.11795 [cs.HC] (or arXiv:2504.11795v3 [cs.HC] for this version) https://doi.org/10.48550/arXiv.2504.11795 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Sitong Wang [ view email ] [v1] Wed, 16 Apr 2025 06:02:31 UTC (1,952 KB) [v2] Tue, 16 Sep 2025 14:04:40 UTC (1,886 KB) [v3] Wed, 8 Apr 2026 23:56:25 UTC (6,329 KB) Full-text links: Access Paper: View a PDF of the paper titled Schemex: Discovering Structural Abstractions from Examples, by Sitong Wang and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.HC < prev | next > new | recent | 2025-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Scenes: A Meta-Logical Algebra for Mutable State#1077309
• Technical Supplement to "Abstraction and Grounding"#113559
• Simulating Programming Traces and State Spaces for Hint Generation#965808
• Differential Expressiveness: A Data-Centered Perspective on Algorithmic Bias#643843
• ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases#924918