Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature
Open accessThe DOI matches its Crossref record; 225 of the 225 references it cites were found in a registry or an index; 99 of the 178 sources its claims cite were checked for support.
Abstract
As Artificial Intelligence (AI) increasingly becomes an active collaborator in co-creation, understanding the distribution and dynamic of agency is paramount. The Human-Computer Interaction (HCI) perspective is crucial for this analysis, as it uniquely reveals the interaction dynamics and specific control mechanisms that dictate how agency manifests in practice. Despite this importance, a systematic synthesis mapping agency configurations and control mechanisms within the HCI/CSCW literature is lacking. Addressing this gap, we reviewed 134 papers from top-tier HCI/CSCW venues (e.g., CHI, UIST, CSCW) over the past 20 years. This review yields four primary contributions: (1) an integrated theoretical framework structuring agency patterns, control mechanisms, and interaction contexts, (2) a comprehensive operational catalog of control mechanisms detailing how agency is implemented; (3) an actionable cross-context map linking agency configurations to diverse co-creative practices; and (4) grounded implications and guidance for future CSCW research and the design of co-creative systems, addressing aspects like trust and ethics.
Overview
CoChat Summary
TL;DR
This scoping review synthesizes 134 top-tier HCI/CSCW papers from the past 20 years to map human-AI co-creation through the lens of agency. It proposes an integrated framework, catalogs operational control mechanisms, and links agency configurations to interaction contexts and application domains.
Key findings
- Across 106 papers with concrete system implementations or interaction designs, AI agency patterns distributed as: 18 passive, 34 reactive, 12 semi-active, 9 proactive, and 33 co-operative.
- The review catalogs 12 control mechanisms across an Input-Action-Output-Feedback cycle, including Guided Input Interaction, Context Awareness and Memory Retention, Transparency and Explainability, Action Coordination, Adaptive Scaffolding, Iterative Feedback Loop, and Chain-of-Thought.
- Agency distribution is characterized along three dimensions: locus (human-centric, AI-centric, hybrid/shared), dynamics (static vs. dynamic allocation), and granularity (high-level vs. fine-grained control).
- The synthesis maps co-creation practices across 7 application domains (news, healthcare, art, education/research, entertainment, software development, accessibility) and identifies 7 challenge areas, including creativity/ownership, trust/transparency, data privacy, interoperability, social impact/equity, ethical/bias concerns, and long-term paradigm shift.
Methods
- Scoping review following PRISMA-ScR, searching ACM Digital Library up to August 2024 with terms combining co-creation/co-writing/co-drawing/co-design and agency, limited to top-tier HCI venues over 20 years.
- From 2,799 initial records, 728 remained after venue/time scoping; screening excluded 192 records, leaving 536 for full-text review; eligibility exclusions left 134 papers for analysis.
- Final corpus distribution: 108 CHI, 4 CSCW, 5 DIS, 9 IUI, and 8 UIST papers. Two researchers conducted hybrid thematic analysis with deductive and inductive coding.
Limitations
- The paper states that existing agency theories offer limited frameworks for modeling dynamic role/control transitions, so its agency-pattern and pathway categorizations may not fully capture moment-to-moment negotiations in practice.
- It also states a theoretical gap in reconciling AI’s designed computational nature with users’ subjective experience and attribution of agency, and notes that general agency theories may be less applicable to open-ended, emergent co-creative goals.
- Evident from the methodology: the review is restricted to top-tier HCI/CSCW venues, ACM Digital Library, specific search terms, and full peer-reviewed papers, excluding conceptual/philosophical work and human-human or AI-AI collaboration; agency-pattern classification used only the 106 papers with sufficient implementation detail.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
57 Valid · 17 Not valid · 20 Not checked · 60 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The interplay between these forms, particularly in the closely coupled systems characteristic of human-AI collaboration [39, 126], requires understanding the dynamic distribution of the agency between partners [17].”
What the sources say
- Supportedcites [39] [39] Patricia Cornelio, Patrick Haggard, Kasper Hornbaek, Orestis Georgiou, Joanna Bergström, Sriram Subramanian, and Marianna Obrist. 2022. The sense of agency in emerging technologies for human-computer integration: A review. Frontiers in Neuroscience 16 (2022), 949138. - source
The “Human–computer integration and the role of agency” section says the review examines how agency is shared between users and systems. In “A new perspective from the lens of agency,” it explains that the degree of control held by each varies with the type of integration. This supports the point attributed to this source about understanding how agency is distributed between partners; the other citations accompany the claim about closely coupled human-AI systems. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [126] [126] Florian Floyd Mueller, Pedro Lopes, Paul Strohmeier, Wendy Ju, Caitlyn Seim, Martin Weigel, Suranga Nanayakkara, Marianna Obrist, Zhuying Li, Joseph Delfa, et al. 2020. Next steps for human-computer integration. In Proceedings of the 2020 CHI Conference on human factors in computing systems . 1-15. - source
- Partly supportedcites [17] [17] Dan Bennett, Oussama Metatla, Anne Roudaut, and Elisa D Mekler. 2023. How does HCI understand human agency and autonomy?. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems . 1-18. - sourceExperimental — accuracy not yet measured
The Discussion calls for understanding how aspects of human agency relate when people delegate to technology, which supports the need to examine agency in human–technology interaction. But the Background says the review focuses exclusively on human agency and considers non-human agency only insofar as it bears on humans; it does not establish a dynamic distribution of agency between human and AI partners. No page numbers were available in our copy. (LLM, conf=0.84)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Artificial Intelligence (AI) are increasingly transitioning from tools performing static tasks [50] to integral partners in collaborative processes like co-creation [200] and human-supervised autonomous systems [203].”
What the sources say
- Not matchedcites [50] [50] Marc Eulerich, Aida Sanatizadeh, Hamid Vakilzadeh, and David A Wood. 2023. Can artificial intelligence pass accounting certification exams? ChatGPT: CPA, CMA, CIA, and EA. Social Science Research Network (2023). doi:10. 2139/ssrn.4452175 -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [200] [200] Mingyuan Zhang, Zhaolin Cheng, Sheung Ting Ramona Shiu, Jiacheng Liang, Cong Fang, Zhengtao Ma, Le Fang, and Stephen Jia Wang. 2023. Towards Human-Centred AI-Co-Creation: A Three-Level Framework for Effective Collaboration between Human and AI. In Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing . 312-316. - source
- Supportedcites [203] [203] Shuning Zhang, Xin Yi, Shixuan Li, Chuye Hong, Gujun Chen, Jiarui Liu, Xueyang Wang, Yongquan Hu, Yuntao Wang, and Hewu Li. 2025. Actual Achieved Gain and Optimal Perceived Gain: Modeling Human Take-over Decisions Towards Automated Vehicles' Suggestions. arXiv preprint arXiv:2502.06179 (2025). - source
The citation [203] is attached to “human-supervised autonomous systems,” not to the separate claims about static tasks or co-creation. The Introduction describes human drivers occasionally taking control when automated vehicles reach their limits, and the Conclusion describes a system that offers suggestions while the driver makes the final decision. (LLM, conf=0.91)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Furthermore, empirical studies, while offering valuable insights [58, 63, 65], are often limited to a specific context, limiting generalizability between settings.”
What the sources say
- Could not verifycites [58] [58] Jie Gao, Simret Araya Gebreegziabher, Kenny Tsu Wei Choo, Toby Jia-Jun Li, Simon Tangi Perrault, and Thomas W Malone. 2024. A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems . 1-11. - sourceExperimental — accuracy not yet measured
The paper’s §4.2 (Limitations and Future Work; page unavailable) discusses limitations of its own taxonomy and plans to cover more tasks, design spaces, and venues. Searches for empirical-study context limits and generalizability across settings found no passage making the attributed point. (LLM, conf=0.74)
- Supportedcites [63] [63] Xinyu Guo, Yi Xiao, Jiaqi Wang, and Tie Ji. 2023. Rethinking designer agency: A case study of co-creation between designers and AI. (2023). - source
Section 6.4, “Conclusion and limitation,” identifies the workshop’s limited range of AI tools and its participants—all students from one university—as constraints. It says these limitations mean the study might not capture all real-world designer–AI collaboration scenarios, supporting its use as an example of context-limited empirical research. (LLM, conf=0.90)
- Supportedcites [65] [65] Qingyang He, Weicheng Zheng, Hanxi Bao, Ruiqi Chen, and Xin Tong. 2023. Exploring designers' perceptions and practices of collaborating with generative AI as a co-creative agent in a multi-stakeholder design process: Take the domain of avatar design as an example. In Proceedings of the Eleventh International Symposium of Chinese CHI . 596-613. - source
The paper’s §5.4, “Limitations and Future Work,” says the study is centered on 2D static cartoon avatar design and recommends research on other avatar types and cultural backgrounds. It thus supports the cited point that this empirical study’s specific context constrains generalization, while noting that its findings may still offer broader insights. (LLM, conf=0.87)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Transparency and explainability regarding AI actions [70, 187, 209] are crucial for enabling humans to appropriately trust and engage with AI contributions [191, 201].”
What the sources say
- Not checked — no full text of the sourcecites [70] [70] Md Naimul Hoque, Tasfia Mashiat, Bhavya Ghai, Cecilia D Shelton, Fanny Chevalier, Kari Kraus, and Niklas Elmqvist. 2024. The HaLLMark Effect: Supporting Provenance and Transparent Use of Large Language Models in Writing with Interactive Visualization. In Proceedings of the CHI Conference on Human Factors in Computing Systems . 1-15. - source
- Not checked — no full text of the sourcecites [187] [187] Zijie J Wang, Chinmay Kulkarni, Lauren Wilcox, Michael Terry, and Michael Madaio. 2024. Farsight: Fostering Responsible AI Awareness During AI Application Prototyping. In Proceedings of the CHI Conference on Human Factors in Computing Systems . 1-40. - source
- Not checked — no full text of the sourcecites [209] [209] Jichen Zhu, Antonios Liapis, Sebastian Risi, Rafael Bidarra, and G Michael Youngblood. 2018. Explainable AI for designers: A human-centered perspective on mixed-initiative co-creation. In 2018 IEEE conference on computational intelligence and games (CIG) . IEEE, 1-8. - source
- Supportedcites [191] [191] Justin D Weisz, Michael Muller, Steven I Ross, Fernando Martinez, Stephanie Houde, Mayank Agarwal, Kartik Talamadupula, and John T Richards. 2022. Better together? an evaluation of ai-supported code translation. In Proceedings of the 27th International Conference on Intelligent User Interfaces . 369-391. - source
Section 6.3.2 (p. 23) says understanding the AI-generated translations mattered to participants’ trust and that information about an automated system can improve appropriate trust. Section 6.3.3 (p. 23) links explanations of AI actions and outputs to trust and reports participants’ strong need to understand the model. These passages support the trust-related point attributed to this source. (LLM, conf=0.90)
- Could not verifycites [201] [201] Minfan Zhang, Daniel Ehrmann, Mjaye Mazwi, Danny Eytan, Marzyeh Ghassemi, and Fanny Chevalier. 2022. Get to the point! Problem-based curated data views to augment care for critically ill patients. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems . 1-13. - sourceExperimental — accuracy not yet measured
The citation is attached to the claim about transparency and explainability of AI actions. Section 7.2 discusses limiting computerized annotations to preserve clinicians’ reasoning agency, and the conclusion describes machine-learning assistance as future work; neither addresses transparency or explanations of AI actions. Searches for “transparency” and “explainability” found no passage supporting that point. Page numbers were unavailable in our copy. (LLM, conf=0.76)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Agency during collaboration becomes highly distributed and dynamically negotiated [68, 93].”
What the sources say
- Partly supportedcites [68] [68] Steffen Holter and Mennatallah El-Assady. 2024. Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation. In Computer Graphics forum , Vol. 43. Wiley Online Library, e15107. - sourceExperimental — accuracy not yet measured
The Agency Distribution section describes systems in which humans and AI can both assume control, and Agency Allocation describes a negotiated approach in which roles are decided dynamically during the task. The paper treats these as possible forms of human–AI collaboration, not as a general finding that agency becomes highly distributed and dynamically negotiated in collaboration. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [93] [93] Seo-young Lee, Matthew Law, and Guy Hoffman. 2024. When and How to Use AI in the Design Process? Implications for Human-AI Design Collaboration. International Journal of Human-Computer Interaction (2024), 1-16. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
46 more claims · 20 with their cited sources checked
Create a free account to see all 154 claims and every source verdict.
- It may state two separate claims as one. 58
- Probably not a substantial claim. 67
- The quote only partly states this claim. 3
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 5.1 Agency Patterns · p. 12
“18 systems exhibited Passive agency (acting only upon direct user invocation)”
§ Agency Pattern Papers · p. 39
“| Passive | [40, 73, 112, 124, 138, 171, 191, 206]”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 4.1 Interaction Stage · p. 9
“we adopt Wang et al.'s six-stage classification to systematically analyze the context of agency.”
§ B Coding Criteria and Theoretical Foundations · p. 37
“- Interaction Stage (one dimension of Context): Coded based on the six stages (perceive, think, express, collaborate, build, test) derived from Wu et al. [194] and utilized by Zhang et al. [200].”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ B Coding Criteria and Theoretical Foundations · p. 37
“- Levels of Agency: Categorized based on Rammert et al.'s framework [118], into passive, semiactive, reactive, proactive, cooperative.”
§ References · p. 30
“- [118] Hannah Nicole Mieczkowski. 2022. AI-Mediated Communication: Examining Agency, Ownership, Expertise, and Roles of AI Systems . Stanford University.”
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation
Tricco, A. C., Lillie, E., Zarin, W., O'Brien, K. K., Colquhoun, H., Levac, D., Moher, D., Peters, M. D. J., Horsley, T., Weeks, L., et al. (2018) · Annals of Internal Medicine · doi:10.7326/m18-0850 · Cited by 43,565 · cited 1×
“Our methodology followed the principles outlined in the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses, Extended for Scoping Reviews) guidelines [173].”
Searle, J. R. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00005756 · Cited by 6,954
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605
Cybernetics or Control and Communication in the Animal and the Machine
Wiener, N. (2019) · The MIT Press eBooks · doi:10.7551/mitpress/11810.001.0001 · Cited by 5,009
The Psychology of Human-Computer Interaction
Card, S. K., Moran, T. P., & Newell, A. (2018) · CRC Press eBooks · doi:10.1201/9780203736166 · Cited by 4,103
Co‐creating unique value with customers
Prahalad, C. K., & Ramaswamy, V. (2004) · Strategy & Leadership · doi:10.1108/10878570410699249 · Cited by 2,463
Guidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439 · cited 1×
“Horvitz et al. [71] defined mixed initiative principles that optimize interaction based on utility and uncertainty, while Amershi et al. [7] provided validated general human-AI interaction guidelines.”
Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems
(2017) · doi:10.1145/3025453 · Cited by 2,207
Forbus, K. D. (1984) · Artificial Intelligence · doi:10.1016/0004-3702(84)90038-9 · Cited by 2,013
Research works printed but not linked: 9
- 10.5555/578027 · doi:10.5555/578027
- Jessica Dai. 2024. POSITION: beyond personhood: agency, accountability, and the limits of anthropomorphic ethical analysis. In Forty-first International Conference on Machine Learning.
- Luciano Floridi. 2014. The fourth revolution: How the infosphere is reshaping human reality. OUP Oxford.
- Mitt Nowshade Kabir. [n.d.]. Unleashing Human Potential: A Framework for Augmenting Co-Creation with Generative AI. In Proceedings of the International Conference on AI Research. Academic Conferences and publishing limited.
- Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 793, 16 pages.
- Yiren Liu, Si Chen, Haocong Cheng, Mengxia Yu, Xiao Ran, Andrew Mo, Yiliu Tang, and Yun Huang. 2024a. CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent. In 2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024. Association for Computing Machinery, 17.
- Catalin Mitelut, Benjamin Smith, and Peter Vamplew. 2024. Position: intent-aligned AI systems must optimize for agency preservation. In Forty-first International Conference on Machine Learning.
- Ben Shneiderman and Catherine Plaisant. 2010. Designing the user interface: strategies for effective human-computer interaction. Pearson Education India.
- Daijin Yang, Yanpeng Zhou, Zhiyuan Zhang, Toby Jia-Jun Li, and Ray LC. 2022. AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing. In Joint Proceedings of the ACM IUI Workshops, Vol. 10. CEUR-WS Team, 1-11.
Cited by
Chow, J. C. L., & Li, K. (2026) · Information · doi:10.3390/info17040361 · Cited by 13
Mapping Human–AI Relationships: Intellectual Structure and Conceptual Insights
Gómez-Cruz, N. A., Castro, D. Y. R., Rey-Sarmiento, C. F., Torres, R. A. Z., & Niño, Á. M. (2026) · Technologies · doi:10.3390/technologies14020083 · Cited by 5
KNIT: Computational Boundary Objects for Real-Time Convergence in Interdisciplinary Teams
Wan, E., Yin, C., Ito, A., Gao, Z., Jia, J., Taoka, Y., Saito, S., Sadek, M., & Mougenot, C. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791921 · Cited by 2
“Second, where systems like AI teammates [85, 110] and devil’s advocate agents [21] maintain fixed divisions of labour (AI generates, humans decide), KNIT’s outputs served as provisional common ground requiring collective refinement.”
Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making
Chappidi, S., Singh, J., & Krauze, A. V. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791428 · Cited by 8
Li, L., Herath, S., & Grumbach, C. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798678 · Cited by 2
“In response, an emerging body of HCI research calls for limiting AI assistance in innovation processes through structured constraints on autonomy and phase-aware workflows [17, 22, 36, 52].”
Metadata
- Authors
- Zhang, S., Wang, H., & Yi, X.
- Affiliations
- Tsinghua University (CN)
- University of Duisburg-Essen (DE)
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2025-10-16
- Volume
- 9
- Issue
- 7
- Pages
- 1-43
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W4415256786
- Cited by
- 36
- References
- 156
- Citations by year
- 2026: 36
- FWCI
- 29.63
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the ACM on Human-Computer Interaction (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Universitätsbibliographie, Universität Duisburg-Essen (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Social Sciences › Business, Management and Accounting › Management Information Systems › Information Systems Theories and Implementation
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- human-AI co-creation, agency, control mechanisms, collaboration patterns, trust, AI ethics, human-AI interaction, computer-supported cooperative work
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature. https://app.cochat.ai/papers/10.1145/3757594
- The paper
- Zhang, S., Wang, H., & Yi, X. (2025). Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature. Proceedings of the ACM on Human-Computer Interaction. https://doi.org/10.1145/3757594
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.