# Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation

arXiv: https://arxiv.org/abs/2610.09637 · HTML: https://mlsanity.com/paper/2610.09637/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation](https://mlsanity.com/paper/2602.00744/) (2026)
- [Large-Scale Training Data Attribution for Music Generative Models via Unlearning](https://mlsanity.com/paper/2506.18312/) (2025)
- [Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation](https://mlsanity.com/paper/2507.17937/) (2025)
- [Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems](https://mlsanity.com/paper/2510.08062/) (2025)
- [Computational Copyright: Towards A Royalty Model for Music Generative AI](https://mlsanity.com/paper/2312.06646/) (2023)
- [ARIA: A Diagnostic Framework for Music Training Data Attribution](https://mlsanity.com/paper/2605.16181/) (2026)
- [What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music](https://mlsanity.com/paper/2607.00641/) (2026)

## Abstract (arXiv)

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/