Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models
Open accessThe DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Abstract
While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Creative industries employ vision-aligned proactive and semiproactive agency.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Mapping interaction flows reveals prevalent patterns and underexplored areas, such as the sparse use of 'Auditory Interaction' [84, 109, 164], signaling innovation opportunities in domains like assistive technology or music co-creation.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“AI agency patterns are typically co-operative or semi-active [66, 191], often involving a shared or dynamically negotiated locus of control [8, 47, 109].”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The locus of control can be dynamic, shifting between human guidance and AI generation [8, 109], often operating at a fine granularity for detailed adjustments [208].”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In contrast to software engineering, other domains including Human-Computer Interaction (HCI), organization and business management, and cognitive science have explored the impact of LLMs on creativity.”
From The Impact of Generative AI on Creativity in Software Development: A Research Agenda (2025) · cites this paper as [77]
Experimental — accuracy not yet measured
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Benjamini, Y., & Hochberg, Y. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02031.x · Cited by 109,482 · cited 1×
“To analyze the quantitative measures, we conducted paired t-tests using Benjamani-Hochberg correction [3] to account for the 15 planned-comparisons (using a false discovery rate Q = 0 .”
MethodDevelopment of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
(1988) · Advances in Psychology · doi:10.1016/s0166-4115(08)62386-9 · Cited by 15,003 · cited 2×
“Effort: Users answered the effort question of the NASA-TLX [25], where 1=very low and 7=very high.”
Method(2016) · Cited by 11,679
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 1×
“Trust : Participants rated the system along Mayer’s dimensions of trust [35]: capability, benevolence, and integrity.”
BackgroundGuidelines 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 3×
“Previous research suggests benefits of educating users about the AI and its capabilities [1], or providing onboarding materials and exercises [6].”
BackgroundCai, C. J., Winter, S., Steiner, D., Wilcox, L., & Terry, M. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359206 · Cited by 594 · cited 1×
“Previous research suggests benefits of educating users about the AI and its capabilities [1], or providing onboarding materials and exercises [6].”
BackgroundSelf-citationEnabling Factorized Piano Music Modeling and Generation with the MAESTRO DatasetPreprint
Hawthorne, C., Stasyuk, A., Roberts, A., Simon, I., Huang, C.-Z. A., Dieleman, S., Elsen, E., Engel, J., & Eck, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12247 · Cited by 471 · cited 1×
“Research has demonstrated the potential for modeling and synthesizing music, ranging from singlevoice sequences [13] and multi-part music [19, 34], to music with variable parts at each time step [4] and music with longterm structure over minutes [30, 37, 26].”
BackgroundSelf-citationBoulanger-Lewandowski, N., Bengio, Y., & Vincent, P. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.6392 · Cited by 459 · cited 1×
“Research has demonstrated the potential for modeling and synthesizing music, ranging from singlevoice sequences [13] and multi-part music [19, 34], to music with variable parts at each time step [4] and music with longterm structure over minutes [30, 37, 26].”
BackgroundDeepBach: a Steerable Model for Bach Chorales GenerationPreprint
Hadjeres, G., Pachet, F., & Nielsen, F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.01010 · Cited by 449 · cited 7×
“The conventional interface does include interactive control features via the infillmask feature (present in both conditions) which enables users to crop any region of music to be regenerated [11, 24].”
BackgroundMethodInfluential
Research works printed but not linked: 6
- 8. Kate Compton and Michael Mateas. 2015. Casual Creators. In Proceedings of the Sixth International Conference on Computational Creativity (ICCC 2015),
- 9. Hannu Toivonen, Simon Colton, Michael Cook, and Dan Ventura (Eds.). Brigham Young University, Park City, Utah, 228-235. http://computationalcreativity.net/ iccc2015/proceedings/10_2Compton.pdf
- 12. Monica Dinculescu and Cheng-Zhi Anna Huang. 2019. Coucou: An Expanded Interface for Interactive Composition with Coconet, through Flexible Inpainting. (2019). https://coconet.glitch.me/
- 33. Hannu Toivonen, Simon Colton, Michael Cook, and Dan Ventura (Eds.). Brigham Young University, Park City, Utah, 236-243. http://computationalcreativity.net/ iccc2015/proceedings/10_3Jacob.pdf
- 36. Feynman Liang. 2016. BachBot: Automatic Composition in the Style of Bach Chorales. Masters thesis, University of Cambridge (2016).
- 42. Ralf Schwarzer and Matthias Jerusalem. 1995. Generalized Self-efficacy Scale. Measures in Health Psychology: A User's Portfolio. Causal and Control Beliefs 1, 1 (1995), 35-37.
Cited by
Items 101–200 of 409
Gmeiner, F., Marquardt, N., Bentley, M., Romat, H., Pahud, M., Brown, D., Roseway, A., Martelaro, N., Holstein, K., Hinckley, K., et al. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713861 · Cited by 40
“Similarly, Cococo [47] offers users a set of GUI widgets for steering GenAI music generation, including slider elements to nudge music generation in high-level directions.”
Survey on the Evaluation of Generative Models in Music
Lerch, A., Arthur, C., Bryan–Kinns, N., Ford, C., Sun, Q., & Vinay, A. (2025) · ACM Computing Surveys · doi:10.1145/3769106 · Cited by 42
“For generative music user studies, we found that semi-structured and unstructured approaches were common, with workshops or group interviews used for need-finding studies [82, 86, 89, 157, 221].”
InfluentialFeng, Y., Poralla, P., Dash, S., Li, K., Desai, V., & Qiu, M. (2023) · 2023 IEEE 9th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS) · doi:10.1109/bigdatasecurity-hpsc-ids58521.2023.00046 · Cited by 24
“lack of awareness of musical context, and limited ability to steer mood or effects [4].”
BackgroundKamath, P., Morreale, F., Bagaskara, P. L., Wei, Y., & Nanayakkara, S. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642040 · Cited by 37
“This fnding is in line with some recent research on CSTs in the visual domain, in music composition, and in storytelling where algorithmic tools were used predominantly for idea generation [14, 20, 22, 53, 61, 62].”
InfluentialI Keep Counting: An Experiment in Human/AI Co-creative Songwriting
Micchi, G., Bigo, L., Giraud, M., Groult, R., & Levé, F. (2021) · Transactions of the International Society for Music Information Retrieval · doi:10.5334/tismir.93 · Cited by 37
“As an alternative to fully automated music generation, which transfers the whole creative task to the machine, co-creativity implies that an algorithm is rather used as a tool by a composer (Esling and Devis, 2020) – and this requires some steerability of the AI tools (Louie et al., 2020).”
MethodZhang, S., Wang, H., & Yi, X. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757594 · Cited by 36
“Between these poles, hybrid or shared control models distribute authority (e.g., as collaborators [8, 109]), significantly impacting interaction dynamics and user perception.”
InfluentialWhich Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creation
He, J., Houde, S., & Weisz, J. D. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713522 · Cited by 36
“For example, people’s feelings of ownership increase when performing the work of “critical integration”’ [72] or with a greater sense of control over the work [25, 48, 92].”
Rayan, J. A., Kanetkar, D., Gong, Y., Yang, Y., Palani, S., Xia, H., & Dow, S. P. (2024) · Creativity and Cognition · doi:10.1145/3635636.3656184 · Cited by 37
“Furthermore, co-creation [43] and co-design [41] alongside helpful generative AI agents add to the evidence of how it can contribute in a helpful manner to human collaboration settings.”
BackgroundInteractive Exploration-Exploitation Balancing for Generative Melody Composition
Zhou, Y., Koyama, Y., Goto, M., & Igarashi, T. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450663 · Cited by 24
“We are especially interested in designing effective tools for music content creation [10, 17, 18].”
BackgroundIsrael, M. J., & Amer, A. (2022) · AI and Ethics · doi:10.1007/s43681-022-00169-1 · Cited by 36
“To demonstrate this, OpenAI released a multi-modal version of GPT3, called DALL-E, that demonstrates surprisingly effective text-to-image conversion capabilities [18, 22, 67], music creation [30, 49], and radiology reports [5].”
Method“Journey of Finding the Best Query”: Understanding the User Experience of AI Image Generation System
Kim, S., Eun, J., Oh, C., & Lee, J. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2307670 · Cited by 36
“It includes studies that propose systems that produce music jointly with users of various spectrums, not just those that support general compositions (J.-W. Hong et al., 2022; Huang et al., 2020; Louie et al., 2020).”
AI assistance in enterprise UX design workflows: enhancing design brief creation for designers
Zhu, Z., Lee, H., Cai, P., & Pan, Y. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1404647 · Cited by 35
Understanding Digital Content Creation Needs of Blind and Low Vision People
Zhang, L., Sun, S., & Findlater, L. (2023) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3597638.3608387 · Cited by 36
“Echoing past AI-based creative support research (e.g., [6, 13, 28, 51]), we emphasize the importance of user control, especially given that the modality these tools produce in is inherently inaccessible to BLV creators.”
BackgroundGenAICHI 2023: Generative AI and HCI at CHI 2023
Muller, M. J., Chilton, L. B., Kantosalo, A., Liao, Q. V., Maher, M. L., Martin, C. P., & Walsh, G. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3573794 · Cited by 34
“Systems capable of producing novel instances are only recently documented [e.g., 7, 17], and tooling that allows domain experts to control those novel or creative outcomes is even rarer [e.g., 34].”
BackgroundMuehlhaus, M., & Steimle, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.02662 · Cited by 34
“For instance, some tools assist in the ideation of stories through trope knowledge [6], create storybooks [48], facilitate fashion design [17, 47], or co-create music [27].”
BackgroundUnderstanding Human-AI Collaboration in Music Therapy Through Co-Design with Therapists
Sun, J., Yang, J., Zhou, G., Jin, Y., & Gong, J. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642764 · Cited by 33
“Growing research interest aims to explore human-AI collaboration in creative music activities, including live performances [9, 37], composition [29, 59], and production [67].”
BackgroundGenAICHI 2024: Generative AI and HCI at CHI 2024
Muller, M. J., Kantosalo, A., Maher, M. L., Martin, C. P., & Walsh, G. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3636294 · Cited by 33
“Systems capable of producing novel instances are only recently documented [e.g., 9, 21], and tooling that allows domain experts to control those novel or creative outcomes is even rarer [e.g., 47].”
VisiFit: Structuring Iterative Improvement for Novice Designers
Chilton, L. B., Ozmen, E. J., Ross, S. H., & Liu, V. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445089 · Cited by 32
“This can be done using rules and constraints [15, 60] or implicit patterns learned by deep learning [36].”
BackgroundHuang, Y. (2023) · Annual Symposium on Computer-Human Interaction in Play · doi:10.1145/3573382.3616033 · Cited by 33
“Apart from text creation, a user can also ask GenAI to draw a sketch [24] or compose music as a co-collaborator [19].”
BackgroundTchemeube, R. B., Ens, J., Plut, C., Pasquier, P., Safi, M., Grabit, Y., & Rolland, J.-B. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/640 · Cited by 33
“Finally, Louie et al. [ Louie et al. , 2020 ] compare Bach-doodle [ Huang et al. , 2019 ] ) with infill mask and the Cococo interface with interactive steering controls: voice lanes, semantic sliders, and generative alternatives.”
BackgroundResultMaking AI-Enhanced Videos: Analyzing Generative AI Use Cases in YouTube Content Creation
Anderson, T., & Niu, S. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719991 · Cited by 32
Exploring the Collaborative Co-Creation Process with AI: A Case Study in Novice Music Production
Fu, Y., Newman, M., Going, L., Feng, Q., & Lee, J. H. (2025) · Proceedings of the 2025 ACM Designing Interactive Systems Conference · doi:10.1145/3715336.3735829 · Cited by 30
“However, previous studies have predominantly examined individual musicians’ interactions with single-purpose AI tools in controlled settings [37, 52], leaving a gap in understanding how teams of creators, particularly novices, integrate AI tools across an entire production cycle.”
Magical Brush: A Symbol-Based Modern Chinese Painting System for Novices
Xu, H., Chen, S., & Zhang, Y. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581429 · Cited by 31
“Magical Brush efectively helps novices create modern Chinese paintings, consistent with the fndings in previous study that AI tools help in breaking the co-creation task down into understandable chunks for novices [31].”
ResultAI song contest: Human-AI co-creation in songwritingPreprint
Huang, C.-Z. A., Koops, H. V., Newton-Rex, E., Dinculescu, M., & Cai, C. J. (2020) · arXiv (Cornell University) · doi:10.5281/zenodo.4245529 · Cited by 30
Self-citationArakawa, R., Yakura, H., & Goto, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581133 · Cited by 29
“Emerging generation techniques have also been proposed for tasks other than writing, such as slide-editing [37, 62, 85], music creation [41, 70], and drawing [32, 38, 83, 84].”
MethodXiaohui, G. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1267516 · Cited by 29
AI Music Outputs: Challenges to the Copyright Legal FrameworkPreprint
Bulayenko, O., Quintais, J. P., Gervais, D. J., & Poort, J. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4072806 · Cited by 29
A Survey on Artificial Intelligence for Music Generation: Agents, Domains and PerspectivesPreprint
Hernandez-Olivan, C., Hernandez-Olivan, J., & Beltrán, J. R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.13944 · Cited by 28
A Portrait of Emotion: Empowering Self-Expression through AI-Generated ArtPreprint
Lee, Y. K., Park, Y.-H., & Hahn, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.13324 · Cited by 28
“Efforts have been made such as developing AI music generation software that can produce music that sounds "happier" or "sadder" (CoCoCo; Louie et al., 2020) and creating robot simulators that users can adjust to reflect different moods (e.g., angry-looking; Desai et al., 2019) to improve the…”
Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPT
Nikghalb, M. R., & Cheng, J. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711015 · Cited by 27
“This partnership spans various domains; examples include music composition [25], general decision-making [20], and design support [29].”
Cococo: AI-Steering Tools for Music Novices Co-Creating with Generative Models.
Louie, R., Cohen, A. D., Huang, C.-Z. A., Terry, M. A., & Cai, C. J. (2020) · Cited by 27
Self-citationCreativity in digitally mediated times: How digital tools support creativity across domains.
Ceh, S. M., Rafner, J. F., & Benedek, M. (2026) · Psychology of Aesthetics Creativity and the Arts · doi:10.1037/aca0000729 · Cited by 30
Imasato, N., Miyazawa, K., Duncan, C., & Nagai, T. (2023) · IEEE Access · doi:10.1109/access.2023.3280603 · Cited by 26
“A study conducted with novice musicians [39] suggested that, although AI-powered tools can indeed be helpful in music composition (especially when the user does not have enough prior knowledge in music theory), the use of an AI-powered tool to compose music becomes less overwhelming and easier to…”
BackgroundEnvisioning AI Support during Semi-Structured Interviews Across the Expertise Spectrum
Liu, Z., Dai, J., Conati, C., & McGrenere, J. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710909 · Cited by 25
“Studies have shown that AI collaboration can enhance human creativity in writing [7, 14], drawing [56], and music composition [48], helping hobbyists produce high-quality work.”
InfluentialDiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization
Chen, H., Jiang, Y., Ma, G., Hao, C. X., Wang, S., Yao, J., Ning, Z., Meng, M., Luan, J., & Xie, L. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434644 · Cited by 25
“These developments facilitate various applications, such as personalized music generation for short videos, film scoring, educational tools, and therapeutic practices [4], [5].”
IdeationWeb: Tracking the Evolution of Design Ideas in Human-AI Co-Creation
Shen, H., Shen, L., Wu, W., & Zhang, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713375 · Cited by 24
“Co-creation with AI is increasingly being applied in various creative felds, such as writing [34, 81], music composition [49, 70, 115], and visual art [45, 80, 113].”
Fan, H., Zhou, C., Yu, H., Wu, X., Gu, J., & Peng, Z. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714111 · Cited by 24
“More and more creativity support interactive systems are being designed for specific tasks in particular professions [10, 33, 37, 47].”
Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces
Smith, A., Anderson, B. R., Otto, J., Karth, I., Sun, Y., Chung, J. J. Y., Roemmele, M., & Kreminski, M. (2025) · Creativity and Cognition · doi:10.1145/3698061.3726915 · Cited by 24
“Recent years have seen especially strong growth in the adoption of AI-based CSTs—in creative domains as wide-ranging as writing [45], visual art [10, 54, 71], game design [29, 40], fashion design [35], worldbuilding [15], and music [49].”
Bo, J. Y., Xu, T., Chatterjee, I., Passarella-Ward, K., Kulshrestha, A., & Shin, D. (2026) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3830398.3830533 · Cited by 24
“…provides users real-time control via a dynamic slider, with the principle of direct manipulation [23, 61, 82] This type of transparent and controllable personalization is well-supported: users value retaining explicit control over recommendations [6, 45, 55, 62, 66] and generative outputs [22, 26].”
Lu, Z., Mysore, S., Safavi, T., Neville, J., Yang, L., & Wan, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.04656 · Cited by 24
“For instance, [67] designed an AI-based tool for music creation; [58] evaluated people’s perceptions in the co-drawing process with AI.”
MethodThe Impact of Generative AI on Creativity in Software Development: A Research Agenda
Jackson, V., Vasilescu, B., Russo, D., Ralph, P., Prikladnicki, R., Izadi, M., D’Angelo, S., Inman, S., Andrade, A., & van der Hoek, A. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3708523 · Cited by 23
“One common research theme is investigating how humans can co-create with GenAI for a variety of tasks commonly considered as creative including interaction design [63, 117, 129], music composition [77], writing [64, 72, 136], and research ideation [75, 108].”
Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations
Kim, Y., Lee, S.-J., & Donahue, C. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713818 · Cited by 23
“The detailed algorithm and its implementation are discussed in §5.”
InfluentialGenAICHI 2025: Generative AI and HCI at CHI 2025
Muller, M. J., Chilton, L. B., Maher, M. L., Martin, C. P., Choi, M., Walsh, G., & Kantosalo, A. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3707213 · Cited by 23
“Systems capable of producing novel instances are only recently documented (e.g., [11, 30]), and tooling that allows domain experts to control those outcomes is rare (e.g., [16, 22, 64, 65]).”
TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks
Chen, Y., Morariu, V. I., Truong, A., & Liu, Z. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642443 · Cited by 23
“Researchers have built AI-assisted creation tools in multiple domains, e.g., Cococo [41] allows users to adjust the mood of AI-generated music notes.”
BackgroundGenerative Melody Composition with Human-in-the-Loop Bayesian OptimizationPreprint
Zhou, Y., Koyama, Y., Goto, M., & Igarashi, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03190 · Cited by 22
“Louie et al. (2020) investigated AI-steering tools to give users more control over exploring latent spaces of deep generative models, and presented a human-AI co-creation tool.”
BackgroundVeriPlan: Integrating Formal Verification and LLMs into End-User Planning
Lee, C. P., Porfirio, D., Wang, X. J., Zhao, K. C., & Mutlu, B. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714113 · Cited by 21
“Similarly, interactive environments with user-controllable parameters enable experimentation, helping users build a better understanding of LLM capabilities [34, 61, 64, 100].”
Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation
Wang, Y., Venkatesh, P., & Lim, B. Y. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517551 · Cited by 21
“, for computer-aided translation [25], playing Chess [27], and music creation [55].”
BackgroundResultRomero, P. F., Fung, K. N. N., Rong, G., & Cowley, B. U. (2025) · npj Science of Learning · doi:10.1038/s41539-025-00332-3 · Cited by 21
“Althoughseveralstudies haveexploredhuman-GPTcollaborativedynamics,theyhaveoftenover-lookedsampledemographics 59 – 63 .”
Using Incongruous Genres to Explore Music Making with AI Generated Content
Bryan–Kinns, N., Noel-Hirst, A., & Ford, C. (2024) · Creativity and Cognition · doi:10.1145/3635636.3656198 · Cited by 21
“Of the few works reflecting on the use of generative AI in music making practice (e.g. [37, 40]), Xambó [65] review the features of nine virtual agent systems used in Live Coding to generate music.”
BackgroundInfluentialWhen, What, and how should generative artificial intelligence explain to Users?
Jang, S., Lee, H., Kim, Y., Lee, D., Shin, J., & Nam, J. (2024) · Telematics and Informatics · doi:10.1016/j.tele.2024.102175 · Cited by 21
Zhang, S.-N., & Li, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.14925 · Cited by 21
Interactive AI Alignment: Specification, Process, and Evaluation Alignment
Terry, M., Kulkarni, C., Wattenberg, M., Dixon, L., & Morris, M. R. (2023) · arXiv · doi:10.48550/arxiv.2311.00710 · Cited by 20
“This issue has been observed in music generation [31] and other generative AI systems [8], with users sometimes feeling overwhelmed with the amount of information produced.”
BackgroundInfluentialSelf-citationExploring the Needs of Practising Musicians in Co-Creative AI Through Co-Design
Krol, S. J., Llano, M. T., & Paredes, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713894 · Cited by 22
“Co-creative AI systems are demonstrating potential in various fields such as music [16, 26, 35, 57, 68], writing [19, 70], drawing [33, 45, 75] and design [51, 76].”
InfluentialLong Short-Term Memory-Based Music Analysis System for Music Therapy
Li, Y., Li, X., Lou, Z., & Chen, C. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.928048 · Cited by 20
“Louie et al. (2020) developed an intelligent system to help system users to generate music.”
BackgroundA Human-Computer Collaborative Editing Tool for Conceptual Diagrams
Pan, L., Yu, C., He, Z., & Shi, Y. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580676 · Cited by 20
“Similarly, Ryan Louie proposed a music editing system [75]: the author manually writes some notes and sets some parameters, and the AI automatically composes the remaining parts.”
MethodRetroLens: A Human-AI Collaborative System for Multi-step Retrosynthetic Route Planning
Shi, C., Hu, Y., Wang, S., Ma, S., Zheng, C., Ma, X., & Luo, Q. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581469 · Cited by 19
“developed AI-steering tools enabling novices to direct the music generation model to iteratively create music [58].”
BackgroundPAGURI: A User Experience Study of Creative Interaction with Text-to-Music Models
Ronchini, F., Comanducci, L., Perego, G., & Antonacci, F. (2025) · Electronics · doi:10.3390/electronics14173379 · Cited by 20
“Several interfaces have been proposed to enable the interaction between users and generative models (Simon et al., 2008; Huang et al., 2019; Louie et al., 2020; Rau et al., 2022; Zhang et al., 2021; Zhou et al., 2020, 2021; Yakura and Goto, 2023).”
PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Data
Zhang, Z., Ning, Z., Xu, C., Tian, Y., & Li, T. J.-J. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586183.3606776 · Cited by 19
“A frame may contain multiple sounding objects at the same time as well as silent objects that are physically capable of making sounds.”
BackgroundCLIP-CLOP: CLIP-Guided Collage and PhotomontagePreprint
Mirowski, P., Banarse, D., Malinowski, M., Osindero, S., & Fernando, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.03146 · Cited by 20
Xpress: A System for Dynamic, Context-Aware Robot Facial Expressions Using Language Models
Antony, V. N., Stiber, M., & Huang, C. (2025) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1109/hri61500.2025.10974045 · Cited by 18
Self-citationUnderstanding the Potentials and Limitations of Prompt-based Music Generative AI
Choi, Y., Moon, J., Yoo, J., & Hong, J.-H. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713762 · Cited by 19
“Following previous studies [20, 34, 45], we categorized the composers into expert and novice groups based on their experience level.”
InfluentialSounds of Health: Using Personalized Sonification Models to Communicate Health Information
Clark, M., & Doryab, A. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3570346 · Cited by 18
“Bach Cococo’s music style is based on that of Johann Sebastian Bach [25], the famous 18th-century German composer.”
BackgroundMethodTransparency in Music-Generative AI: A Systematic Literature ReviewPreprint
Batlle-Roca, R., Gómez, E., Liao, W., Serra, X., & Mitsufuji, Y. (2023) · Research Square · doi:10.21203/rs.3.rs-3708077/v1 · Cited by 18
AI Drawing Partner: Co-Creative Drawing Agent and Research Platform to Model Co-CreationPreprint
Davis, N., & Rafner, J. F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.06607 · Cited by 18
“There are co-creative systems in a wide variety of creative domains, such as drawing [23, 35, 43], design [54, 63, 67, 108], poetry [50, 60, 82], music [13, 52, 73], theatrical improvisation [74], and game design [47, 76].”
An LLM-based multi-agent system to assist early-stage product design and evaluation
Chen, P., Cai, Y., Zhou, Z., Yao, J., Li, J., You, W., & Sun, L. (2026) · Journal of Engineering Design · doi:10.1080/09544828.2026.2616583 · Cited by 17
“Existing systems often fail to establish effective collaboration mechanisms between designers and AI agents (Louie et al. 2020; Rezwana and Lou Maher 2023), owing to rigid, button-based interfaces and limited feedback channels, which hinder fluid communication and shared understanding in…”
"Chat, Should I Leave Him?" Risks, Rewards, and Roles for AI in Relationship Advice
Tseng, E., & Liang, C. A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790739 · Cited by 17
“AI can be an assistant [3], a co-creator [51], a manager [46], or anything in between.”
MIMOSA: Human-AI Co-Creation of Computational Spatial Audio Effects on Videos
Ning, Z., Zhang, Z., Ban, J., Jiang, K., Gan, R., Tian, Y., & Li, T. J.-J. (2024) · Creativity and Cognition · doi:10.1145/3635636.3656189 · Cited by 18
“We plan to continue exploring this approach in other multimedia domains such as augmenting regular 2D video content into AR/VR content in 3D. Content creation for VR/AR faces similar challenges to what we encountered in our problem domain—it requires specialized recording equipment and significant…”
BackgroundUser Preferences on a Generative AI User Interface Through a Choice Experiment
Yeon, J., Jung, Y., Baek, Y., Lee, D., Shin, J., & Chung, W. Y. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2400379 · Cited by 17
“In summary, studies on generative AI are conducted to propose ethics and directions on generative AI (Buschek et al., 2021; Chen et al., 2023) and to develop new high-performance tools (Calderwood et al., 2020; Louie et al., 2020; Oh et al., 2018).”
Examining Agency, Expertise, and Roles of AI Systems in AI-Mediated Communication
Mieczkowski, H., & Hancock, J. (2022) · doi:10.31219/osf.io/asnv4 · Cited by 16
Tracing Creativity: A Design Space For Creative Activity Traces in HCI
Hammad, N., Lin, D. C.-E., Smith, A., Kreminski, M., Harpstead, E., & Hammer, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791263 · Cited by 16
Economic arguments in favour of reducing copyright protection for generative AI inputs and outputsPreprint
Martens, B. (2024) · RePEc: Research Papers in Economics · Cited by 16
An HCI-Centric Survey and Taxonomy of Human-Generative-AI Interactions
Shi, J., Jain, R., Doh, H., Suzuki, R., & Ramani, K. (2023) · arXiv · doi:10.48550/arxiv.2310.07127 · Cited by 15
“With this autonomy, this method of input initialization can benefit (1) GenAI systems with non-expert [80, 120, 170] users who do not possess knowledge of proper input, (2) systems that passively assist the users [7, 80], or (3) systems that help the users with ideation within a specific domain through vast collection…”
BackgroundMethodInfluentialAn Exploration of Mental Models of AI in Human–AI Co-Creativity: A Framework and Insights
Rezwana, J., & Maher, M. L. (2025) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3769072 · Cited by 15
“As AI is being used increasingly as a collaborator in many creative domains, such as music composition [49, 73, 122], drawing [21, 58, 86], and creative writing [53, 88], research on human-centered co-creative AI has become increasingly important.”
Beyond Turn-taking: Introducing Text-based Overlap into Human-LLM InteractionsPreprint
Kim, J., Chang, M., & Bak, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.18103 · Cited by 15
Cyber-Creativity: A Decalogue of Research Challenges
Corazza, G. E., Agnoli, S., Jorge Artigau, A., Beghetto, R. A., Bonnardel, N., Coletto, I., Faiella, A., Gerardini, K., Gilhooly, K., Glăveanu, V. P., et al. (2025) · Journal of Intelligence · doi:10.3390/jintelligence13080103 · Cited by 14
“Transparency in AI, supported by open-source initiatives and detailed explainability reports (Ali et al. 2023; Ben-Tal et al. 2020; Louie et al. 2020), is essential to build trust among stakeholders and safeguard artistic integrity (Schelble et al. 2024).”
Interactive User Interface for Dialogue Summarization
Jung, J., Seo, H., Jung, S., Chung, R., Ryu, H., & Chang, D.-S. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581641.3584057 · Cited by 14
“In addition, various deep learning-based generation systems are being studied for user convenience, such as generating music [Huang et al. 2020; Louie et al. 2020; Suh et al. 2021] for inputs that meet certain conditions or automatically generating meeting minutes [Liu et al. 2020].”
BackgroundLi, Y., Li, H., Specia, L., & Schuller, B. W. (2026) · Scientific Reports · doi:10.1038/s41598-026-36044-w · Cited by 14
“Despite the ability of MGM technology to enhance music production by inspiring musicians, providing structural frameworks, and suggesting instrumental arrangements, ultimately facilitating higher-quality compositions [5], AI’s rapid music production threatens artist-created works, which require…”
Rezwana, J., & Ford, C. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719858 · Cited by 14
“AI ability alone does not ensure a positive user experience with the AI [59], especially where interaction is essential between humans and AI [94].”
ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned Transformers
Scarlatos, A., Wu, Y., Simon, I., Roberts, A., Cooijmans, T., Jaques, N., Tarakajian, C., & Huang, A. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720227 · Cited by 14
“While there are many prior works on real-time human-AI collaboration in music [2–4, 7, 17–19, 23, 26, 27], only one studies a real-time jamming system [2], but does not fully address the above challenges (see a detailed related work in Appendix B).”
InfluentialWang, W.-F., Lee, T.-Y., Lu, C.-T., Hsu, C., Campanyà, N. P. I., Chen, Y., Chen, M. Y., & Chen, B. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747774 · Cited by 14
“Interactive systems in music [79], translation [32], and crowd ideation [125] likewise enhance user understanding by exposing AI reasoning and supporting more directed interaction.”
Responsible AI in knowledge creation: An exploration of generative AI's opportunities and risks
Dai, S., Li, Q., Jia, S., Liu, G., Kincl, T., & Hajli, N. (2026) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2026.124570 · Cited by 14
HybridEval: A Human-AI Collaborative Approach for Evaluating Design Ideas at Scale
Mesbah, S., Arous, I., Yang, J., & Bozzon, A. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583496 · Cited by 14
“Other collaborative ideation tools were designed to cooperate with users on drawing [37, 43], music creation [38] and brainstorming [4].”
BackgroundImamura, S., Hiraki, H., & Rekimoto, J. (2024) · Augmented Humans International Conference (AHs) · doi:10.1145/3652920.3652931 · Cited by 13
“Advancements in natural language processing(NLP), such as GPT-3 [3], have facilitated the use of large-scale language models for creative support in fields like composition [24] and text-image generation [22, 23, 50].”
BackgroundLiu, Z. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716148 · Cited by 13
“Studies have demonstrated how AI can enhance human creativity in areas such as writing [4], drawing [21], and music composition [17], helping users achieve higher-quality outcomes.”
TutorCraftEase: Enhancing Pedagogical Question Creation with Large Language Models
Kang, W., Zhang, L., Peng, X., Zhang, H., Li, A., Wang, M., Huang, J., Tian, F., & Dai, G. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713731 · Cited by 13
“In the context of ’human-AI collaboration’, clearly defining roles and responsibilities can facilitate collaborative creation [41, 59], while enhancing the discover-ability, visualization, and interpretability of AI-generated content can improve user understanding and interaction with the system…”
Hu, Z., Liu, H., Xiong, Y., Wang, L., Wu, R., Guan, K., Hu, Y., Lyu, T., & Fan, C. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15361-6 · Cited by 13
“References [14, 28, 40] introduced HCAI systems with human-in-the-loop decision mechanisms.”
Liu, B., & Liao, Y. (2025) · Education and Information Technologies · doi:10.1007/s10639-025-13394-y · Cited by 13
“To address these issues, active development efforts are underway for new AI-based tools, such as AI-steering tools, aimed at maximizing user interaction (Louie et al., 2020).”
Searching for the Non-Consequential: Dialectical Activities in HCI and the Limits of Computers
Zhang, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641945 · Cited by 12
“A computer can even hinder the process, for example by over-generating complete artifacts to meet a description that leaves little room for people to have finer grain controls over the process of composition [90, 91].”
BackgroundWorrall, K., & Collins, T. (2023) · IEEE Transactions on Games · doi:10.1109/tg.2023.3319085 · Cited by 12
“…about how music AI can be a benefit to accessibility for novices (supporting existing research into musical cocreation as a tool for novices [37], and by mentioning how music AI could be a potential solution to legal issues around music used during the streaming of games, an issue being…”
BackgroundInfluentialHammad, N., Fraser, C. A., Harpstead, E., Hammer, J., & Dontcheva, M. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735814 · Cited by 12
“Recent work has explored how AI tools can better support productive iteration by designing human-AI co-creation tools across creative domains including writing [14, 18], image creation [34], video editing [58, 60], and music creation [28, 35, 69].”
Hutson, J., Coble, K., Kshetri, N., & Smith, A. (2023) · Advances in marketing, customer relationship management, and e-services book series · doi:10.4018/978-1-6684-8958-1.ch003 · Cited by 13
ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business OwnersPreprint
Karnatak, N., Baranès, A., Marchant, R., Butler, T., & Olson, K. N. P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.06729 · Cited by 12
Brachman, M., Pan, Q., Do, H. J., Dugan, C., Chaudhary, A., Johnson, J. M., Rai, P., Chakraborti, T., Gschwind, T., Laredo, J. A., et al. (2023) · Proceedings of the 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581641.3584088 · Cited by 11
“Researchers have also developed methods for explaining the outputs of generative AI models, in which users have different needs than for discriminative machine learning [81, 103, 115].”
BackgroundMethodChung, J. G., Hong, S., Choi, J., & Oh, C. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713532 · Cited by 11
“Some research highlights the need to balance the efciency of AI with fostering user creativity, emphasizing the human’s leading role in the collaboration [82, 94, 102].”
FeedQUAC: Quick Unobtrusive AI-Generated Commentary
Long, T., Wannamaker, K., Vermeulen, J., Fitzmaurice, G. W., & Matejka, J. (2025) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3765766.3765861 · Cited by 11
“…example, a productive session with such systems often lasts at least 30 minutes before users can proceed [47, 49, 67], and the tools often display an overwhelming amount of information dominating users’ screen, designed to provide as many brainstorming or drafting supports as possible [12, 36, 50].”
ReStyle-MusicVAE: Enhancing User Control of Deep Generative Music Models with Expert Labeled Anchors
Prvulovic, D., Vogl, R., & Knees, P. (2022) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3511047.3536412 · Cited by 11
“As a response, systems aim at adapting pre-trained systems to avoid these drawbacks while enabling personalization (MidiMe [5]) or at keeping the process simple by restricting content generation to particular voices, giving more control when composing (Cococo [9]).”
BackgroundEmotional Conveyance Analysis of Artificial Intelligence Painting
Ma, L., Chen, D., Feng, Y. S., Hou, X., & Chen, J. (2023) · International Symposium of Chinese CHI (Chinese CHI) · doi:10.1145/3629606.3629612 · Cited by 11
“AI content generation integrates new technologies and concepts into the cultural [5], entertainment [6], and marketing industries [7].”
BackgroundJussupow, E., Bauer, K., Heigl, R. M., Vogt, B., & Hinz, O. F. (2026) · Information Systems Research · doi:10.1287/isre.2024.0951 · Cited by 12
Abuzuraiq, A. M., & Pasquier, P. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.17688 · Cited by 11
“Steering interfaces that provide semantically meaningful controls improve artists’ control, self-efficacy, and creative ownership [33].”
BackgroundCo-Creating Question-and-Answer Style Articles with Large Language Models for Research Promotion
Lim, H., Cho, J. Y., Kim, T., Park, J., Shin, H., Choi, S., Park, S., Lee, K., Kim, J., Lee, M., et al. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3660705 · Cited by 10
“Research on human-AI co-creation systems have been actively conducted in a wide range of creative tasks for design [29], illustrations [9, 62, 65], music composition [40], dancing [64], drawing [19, 33, 46], storytelling [14, 16, 43, 45, 48, 59], and writing [4, 17, 23, 28, 39, 52, 77].”
Metadata
- Authors
- Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J.
- Affiliations
- Northwestern University (US)
- Google (United States) (US)
- Independent Researcher, Mountain View, CA, USA
- Venue
- Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2020-04-21
- Pages
- 1-13
- OpenAlex
- W3031000691
- Semantic Scholar
- 77a5e08f361b6f91cac8a24b380a14c12bb93383
- Cited by
- 271
- References
- 37
- Citations by year
- 2026: 40 · 2025: 75 · 2024: 65 · 2023: 40 · 2022: 34 · 2021: 14 · 2020: 3
- FWCI
- 7.02
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by-sa)
- Topics
- Social Sciences › Arts and Humanities › Music › Music Technology and Sound Studies
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- novice users, generative music, user trust, self-efficacy, human-AI collaboration, music composition
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.
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
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.