Paper year
2025
Paper dossier
The AI Music Arms Race: On the Detection of AI-Generated Music
Detail viewSimilarity handoff
Review source metadata, abstract, authors, topics, and local similarity context before moving into explanation and ranking views.
Citations
2
Authors
4
Topic labels
3
Source readout
Source and corpus status
Venue
Transactions of the International Society for Music Information Retrieval
Source slug
tismir
Corpus placement
Core corpus
Similarity rows
Not available yet
Ranking readout
Where this paper lands in the current run
Run shadow-generalization-product-candidate-ranking-v1Top 50 surfaced
This block uses the same resolved ranking run as Recommended. Ranks here are materialized paper_scores ranks; live Emerging may be reordered by the bounded ML scorer. Family rank is global within each family, but rank is only shown when this paper lands inside the surfaced top 50.
Families present
3
Top 50
3
Run label
shadow-generalization-product-candidate-ranking-v1
Snapshot
source-snapshot-shadow-generalization-v1-20260521
Scope: family global | run rank-83787b91ef
Emerging
In top 50 at rank 12
Emerging: embedding slice fit vs included-corpus centroid (title+abstract), plus citation velocity and topic growth; not universal relevance. Bridge signal not used here.
Signals: semantic=0.8779, citation_velocity=0.1200, topic_growth=0.8636, diversity_penalty=0.0000
Why this surfaced | 3 used | 1 penalty | 1 not computed
Embedding slice fit (corpus centroid)used
Embedding slice fit (corpus centroid): high; used in final ranking (contribution to score: 0.1756)
Recent attentionused
Recent attention: low; used in final ranking (contribution to score: 0.0600)
Topic momentumused
Topic momentum: high; used in final ranking (contribution to score: 0.2591)
Cross-cluster signalnot computed
Cross-cluster signal: not computed for this run
Similarity penaltypenalty
Similarity penalty: reduces score when non-zero (contribution to score: 0.0000)
Bridge
In top 50 at rank 10
Multi-topic paper in active topics; no cluster_version on this run so bridge_score was not computed.
Signals: citation_velocity=0.1200, topic_growth=0.8636, diversity_penalty=0.0000
Why this surfaced | 2 used | 1 penalty | 2 not computed
Semantic matchnot computed
Semantic match: not computed for this run
Recent attentionused
Recent attention: low; used in final ranking (contribution to score: 0.0420)
Topic momentumused
Topic momentum: high; used in final ranking (contribution to score: 0.5613)
Cross-cluster signalnot computed
Cross-cluster signal: not computed for this run
Topic breadth penaltypenalty
Topic breadth penalty: reduces score when non-zero (contribution to score: 0.0000)
Under-cited
In top 50 at rank 34
Low-cite candidate pool (see docs/candidate-pool-low-cite.md v0): core corpus, recency floor, citation ceiling, title+abstract gate; popularity penalty among pool members only. Semantic and bridge not yet modeled.
Signals: citation_velocity=0.1200, topic_growth=0.8636, diversity_penalty=0.4421
Why this surfaced | 2 used | 1 penalty | 2 not computed
Semantic matchnot computed
Semantic match: not computed for this run
Recent attentionused
Recent attention: low; used in final ranking (contribution to score: 0.0360)
Topic momentumused
Topic momentum: high; used in final ranking (contribution to score: 0.6045)
Cross-cluster signalnot computed
Cross-cluster signal: not computed for this run
Pool popularity penaltypenalty
Pool popularity penalty: reduces score when non-zero (contribution to score: -0.1105)
Abstract
Several companies now offer platforms for users to create music at unprecedented scales by textual prompting. As the quality of this music rises, concern grows about how to differentiate AI‑generated music from human‑made music, with implications for content identification, copyright enforcement, and music recommendation systems. This article explores the detection of AI‑generated music by assembling and studying a large dataset of music audio recordings (30,000 full tracks totaling 1,770 h, 33 m, and 31 s in duration), of which 10,000 are from the Million Song Dataset (Bertin‑Mahieux et al., 2011) and 20,000 are generated and released by users of two popular AI music platforms: Suno and Udio. We build and evaluate several AI music detectors operating on Contrastive Language-Audio Pretraining embeddings of the music audio, then compare them to a commercial baseline system as well as an open‑source one. We applied various audio transformations to see their impacts on detector performance and found that the commercial baseline system is easily fooled by simply resampling audio to 22.05 kHz. We argue that careful consideration needs to be given to the experimental design underlying work in this area, as well as the very definition of 'AI music.' We release all our code at https://github.com/lcrosvila/ai-music-detection.
Authors
Neighborhood labels
Topics
3 labels
Topic labels are imported metadata and can be noisy; use them as coarse navigation hints, not authoritative classifications.
Music and Audio ProcessingMusic Technology and Sound StudiesTime Series Analysis and Forecasting
Neighbor surface
Similar papers
Similar papers use a separately configured neighbor embedding; it may differ from the embedding version used by the current ranked run.
No embedding-backed neighbors available for this paper/version yet.
Next handoff
Best next moves from here
01
Check recommendation families
Use Recommended to see whether this paper behaves like an emerging or undercited signal in the current ranked feed, or how it appears on the bridge preview / diagnostics view.
02
Inspect nearby topics
Use Trends to understand whether its attached labels are heating up or cooling down inside the curated corpus.
03
Cross-check evaluation baselines
Use Evaluation to compare the dossier readout against citation and recency baselines for the same resolved family run.