{
  "absUrl": "https://arxiv.org/abs/2609.04867",
  "arxivId": "2609.04867",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "Shanghai Artificial Intelligence Laboratory, Shanghai, China"
      ],
      "name": "Yuchen Sun"
    },
    {
      "affiliations": [
        "Meituan, Beijing, China"
      ],
      "name": "Qian Yang"
    },
    {
      "affiliations": [
        "Meituan, Beijing, China"
      ],
      "name": "Jun Wang"
    },
    {
      "affiliations": [
        "Meituan, Beijing, China"
      ],
      "name": "Detai Xin"
    },
    {
      "affiliations": [
        "Meituan, Beijing, China"
      ],
      "name": "Guoqiao Yu"
    },
    {
      "affiliations": [
        "Meituan, Beijing, China"
      ],
      "name": "Guanglu Wan"
    },
    {
      "affiliations": [
        "Shanghai Artificial Intelligence Laboratory, Shanghai, China"
      ],
      "name": "Qi Jia"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.04867",
  "originalTitle": "PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation",
  "pdfUrl": "https://arxiv.org/pdf/2609.04867.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}