Abstract
How can we verify whose music contributed to an AI-generated output? This paper demonstrates how input-based attribution can provide verifiable evidence of which audio sources were used in a generation and whether they shaped the output. To do so, we condition the generation solely on audio without any text input, then trace the inputs behind each output, and establish their musical effect. In prompt adherence tests and controlled input swaps, the stems generated by our generator, MixAudio, follow the prompt audio in timbre and the context audio in harmony. Yet these outputs may still reproduce training data not supplied as inputs. We therefore audit memorization with our musical version identification model, musicDNA, and find few reproductions outside the input records. On human-judged cases within the flagged pool, it achieves higher precision and recall than the other tested memorization detectors. The two evaluations suggest that input records and output analysis provide complementary evidence for attribution, on which rights-holder reporting and compensation can draw as the AI music economy takes shape. Audio examples are available at https://neutune.github.io/attr2027demo/
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kim, T., Kim, W., Jung, J., Wi, H., Kum, S., Kim, K. L., Kim, T., Moon, D., Park, S., Kim, T., Berger, V., Nam, J., & Lee, J. (2026). Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation. https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation
MLA 9
Kim, Taejun, et al. "Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation." https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation.
Chicago (author–date)
Kim, Taejun, Wonil Kim, Jongmin Jung, Hyeongseok Wi, Sangeun Kum, Keunhyoung Luke Kim, Taehyoung Kim, Dongjoo Moon, Seungsoon Park, Taewan Kim, Virginie Berger, Juhan Nam, and Jongpil Lee. 2026. "Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation." https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation.
Harvard
Kim, T., Kim, W., Jung, J., Wi, H., Kum, S., Kim, K. L., Kim, T., Moon, D., Park, S., Kim, T., Berger, V., Nam, J. and Lee, J. (2026) 'Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation', Available at: https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation.
Vancouver
Kim T, Kim W, Jung J, Wi H, Kum S, Kim KL, et al. Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation. https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation
IEEE
T. Kim, W. Kim, J. Jung, H. Wi, S. Kum, K. L. Kim, T. Kim, D. Moon, S. Park, T. Kim, V. Berger, J. Nam, and J. Lee, "Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation," https://omanscience.com/en/articles/tracing-inputs-verifying-outputs-validating-attribution-in-music-generation.