The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Prompt specificity and iterative behaviour in text-to-music co-creation: a secondary analysis of interaction logs and a framework for perceived creative control
Abstract
Introduction: Generative artificial intelligence can lower barriers to musical creation while also shifting consequential decisions away from the user. Methods: This study examines that tension through a secondary analysis of the published PAGURI interaction-log prompt corpus and develops a tentative framework for perceived creative control. The analysable corpus contained 304 text-to-music prompts from 24 participants. Musical specificity was operationalised as explicit instrument and technical-parameter markers; iterative continuity was measured with Jaccard similarity between consecutive prompts and checked against TF-IDF cosine similarity. To avoid pseudoreplication, group comparisons were conducted on participant-level summaries rather than treating 304 prompts as independent cases. Results: Role-derived experience groups differed substantially in mean prompt specificity, H(2) = 10.25, p = 0.006, ε 2 = 0.39, and specificity density, H(2) = 11.52, p = 0.003, ε 2 = 0.45, but not in refinement rate, H(2) = 0.24, p = 0.888. At a descriptive Jaccard threshold of 0.20, 46.8% of consecutive pairs were refinements and 53.2% were restarts; because this classification was threshold-sensitive, continuous similarity remained the primary continuity measure. Prompt specificity did not increase systematically across the session: the mean within-person Spearman correlation was ρ = −0.06, and the distribution of participant-level correlations did not differ significantly from zero, W = 89.0, p = 0.374. Discussion: These findings distinguish the explicit technical-musical information users encode in prompts from the sequential continuity of their prompting behaviour. The paper integrates task structure, system autonomy, model coverage, prior experience, self-efficacy, and psychological ownership into a testable framework for future music-education research. Given the small participant-level sample and role-derived grouping, the empirical findings are exploratory and require confirmation in larger, controlled studies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
MusicLM: Generating Music From Text
Agostinelli, A., Denk, T. I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., Tagliasacchi, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.11325 · Cited by 183
Research works printed but not linked: 38
- Bandura, 1997, Self-Efficacy: The Exercise of Control
- Beghetto, 2017, The Creative Self
- Cheng, 2025, The impact of generative AI on school music education: challenges and recommendations, Arts Educ. Policy Rev., 126, 255, 10.1080/10632913.2025.2451373 · DOI
- Chu, 2022, Proceedings of the 31st ACM International Conference on Information and Knowledge Management
- Copet, 2023, Simple and controllable music generation, arXiv:2306.05284, 10.48550/arXiv.2306.05284 · DOI
- Csikszentmihalyi, 1999, Handbook of Creativity
- Deci, 2000, The “what” and “why” of goal pursuits: human needs and the self-determination of behaviour, Psychol. Inq., 11, 227, 10.1207/S15327965PLI1104_01 · DOI · Paper page
- Farmer, 2017, The Creative Self
- Fiebrink, 2019, Machine learning education for artists, musicians, and other creative practitioners, ACM Trans. Comput. Educ., 19, 1, 10.1145/3294008 · DOI
- Fritz, 2007, Required sample size to detect the mediated effect, Psychol. Sci., 18, 233, 10.1111/j.1467-9280.2007.01882.x · DOI · Paper page
- Fu, 2025, Proceedings of the 2025 ACM Designing Interactive Systems Conference
- Haggard, 2017, Sense of agency in the human brain, Nat. Rev. Neurosci., 18, 196, 10.1038/nrn.2017.14 · DOI · Paper page
- Hayes, 2022, Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression-Based Approach
- Huang, 2019, Music Transformer: Generating Music with Long-Term Structure International Conference on Learning Representations
- Kamath, 2024, Proceedings of the CHI Conference on Human Factors in Computing Systems
- Karwowski, 2011, It doesn’t hurt to ask… but sometimes it hurts to believe: polish students’ creative self-efficacy and its predictors, Psychol. Aesthet. Creat. Arts, 5, 154, 10.1037/a0021427 · DOI · Paper page
- Liu, 2025, Why we play: a motivational-efficacy pathway from basic psychological needs to creative musicianship, Acta Psychol., 261, 105952, 10.1016/j.actpsy.2025.105952 · DOI
- Liu, 2024, Audioldm 2: learning holistic audio generation with self-supervised pretraining, IEEE/ACM Trans. Audio Speech Lang. Process., 32, 2871, 10.1109/taslp.2024.3399607 · DOI · Paper page
- Louie, 2020, Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Louie, 2022, Proceedings of the 27th International Conference on Intelligent User Interfaces
- Melechovsky, 2024, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Müllensiefen, 2014, The musicality of non-musicians: an index for assessing musical sophistication in the general population, PLoS One, 9, e89642, 10.1371/journal.pone.0089642 · DOI · Paper page
- Newman, 2023, Proceedings of the 24th International Society for Music Information Retrieval Conference
- Pierce, 2001, Toward a theory of psychological ownership in organizations, Acad. Manag. Rev., 26, 298, 10.2307/259124 · DOI · Paper page
- Plitsis, 2024, ICASSP 2024—IEEE International Conference on Acoustics, Speech and Signal Processing
- Ronchini, Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research (CMMR 2025)
- Ronchini, PAGURI: a user experience study of creative interaction with text-to-music models, Electronics, 14, 3379, 10.3390/electronics14173379 · DOI
- Ruiz, 2023, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Ryan, 2017, Self-Determination Theory: Basic Psychological Needs in Motivation, Development, and Wellness, 10.1521/978.14625/28806 · DOI · Paper page
- Schoemann, 2017, Determining power and sample size for simple and complex mediation models using Monte Carlo methods, Soc. Psychol. Personal. Sci., 8, 379, 10.1177/1948550617715068 · DOI · Paper page
- Shin, 2025, Prompt engineering for AI music creation learning: application and analysis using SUNO AI, Korean J. Res. Music Educ., 54, 95, 10.30775/KMES.54.3.95 · doi:10.30775/kmes.54.3.95
- Sturm, 2019, Machine learning research that matters for music creation: a case study, J. New Music Res., 48, 36, 10.1080/09298215.2018.1515233 · DOI
- Tierney, 2002, Creative self-efficacy: its potential antecedents and relationship to creative performance, Acad. Manag. J., 45, 1137, 10.2307/3069429 · DOI · Paper page
- Tierney, 2011, Creative self-efficacy development and creative performance over time, J. Appl. Psychol., 96, 277, 10.1037/a0020952 · DOI · Paper page
- Väkevä, 2025, Generative AI as a collaborator in music education: an action-network theoretical approach to fostering musical creativities, Action Crit. Theory Music Educ., 24, 16, 10.22176/act24.3.16 · DOI
- Wilson, 2025, Proceedings of the 6th Conference on AI Music Creativity (AIMC 2025)
- Yakura, 2023, Proceedings of the 24th International Society for Music Information Retrieval Conference
- Zelenak, 2020, Developing self-efficacy to improve music achievement, Music. Educ. J., 107, 42, 10.1177/0027432120950812 · doi:10.1177/0027432120950812
Metadata
- Authors
- Zhang, X., & Pan, L.
- Venue
- Frontiers in Psychology
- Publisher
- Frontiers Media SA
- Published
- 2026-10-21
- Volume
- 17
- ISSN
- 1664-1078
- Cited by
- 0
- References
- 1
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Prompt specificity and iterative behaviour in text-to-music co-creation: a secondary analysis of interaction logs and a framework for perceived creative control. https://app.cochat.ai/papers/10.3389/fpsyg.2026.1965465
- The paper
- Zhang, X., & Pan, L. (2026). Prompt specificity and iterative behaviour in text-to-music co-creation: a secondary analysis of interaction logs and a framework for perceived creative control. Frontiers in Psychology. https://doi.org/10.3389/fpsyg.2026.1965465
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.
