From perceptual rule transformation to listener attribution judgments: a blind-listening experiment on AI-generated,...

This study examines listeners' creator attribution judgments and aesthetic evaluations of AI-generated, human-AI collaborative, and human-composed music under blind-listening conditions. Within a framework of personal compositional style modeling, compositional experience was transformed into executable sampling constraints through natural-language interaction. This process is conceptualized in the present study as "perceptual rule transformation" and was used to generate 18 melodic excerpts. Seventy-one participants with music training completed tasks involving creator attribution judgment, attribution confidence rating, and aesthetic evaluation. The results partially supported H1: a statistically significant but very small association was observed between the actual compositional condition and listeners' attribution judgments, χ²(4) = 23.076, p < 0.001, Cramér's V = 0.095. Attribution judgments in the AI-generated and human-AI collaborative conditions were close to a random distribution, and even in the human-composed condition the majority of excerpts (54.7%) were misattributed. Thus, musically trained listeners could not reliably identify the compositional source of the excerpts, with only a modest attribution advantage for human-composed music. Significant differences in aesthetic evaluation were also found across the three compositional conditions. After controlling for actual compositional condition, attribution confidence, and individual participant differences, creator attribution judgment remained independently associated with aesthetic evaluation, and this association held even within the AI-generated condition, where the actual source of all excerpts was constant. These findings suggest that, in the absence of external authorship labels, listeners spontaneously form judgments about the creative agent of music. Such judgments are stably associated with aesthetic evaluation and may constitute an endogenous perceptual bias in the reception of AI-generated music.