{
  "paper": {
    "title": "Attention Is All You Need",
    "authors": "Ashish Vaswani et al.",
    "arxiv_id": "1706.03762",
    "pdf_url": "https://arxiv.org/pdf/1706.03762",
    "pdf_sha256": "bdfaa68d8984f0dc02beaca527b76f207d99b666d31d1da728ee0728182df697",
    "observed_pdf_sha256": "bdfaa68d8984f0dc02beaca527b76f207d99b666d31d1da728ee0728182df697"
  },
  "paper_text": {
    "path": "/Users/boj/book/ai-agent-book/chapter5/paper-to-ppt/validation/runs/exp5-4-real-pdf-20260730-v2/source/paper_text.md",
    "sha256": "4da5f2a1da38bad8149832b5ada3c94f0619188db8fed5cdca8ff63405587eb8",
    "characters": 39819
  },
  "visuals": [
    {
      "filename": "paper_figure_1_transformer.png",
      "pdf_page": 3,
      "source_label": "Figure 1",
      "caption": "The Transformer model architecture.",
      "rect": [
        92,
        28,
        520,
        535
      ],
      "sha256": "48f09e2e2426e8ca76c1e438600438dca2f9e61360e92ae3edbb538a2cc611d2",
      "bytes": 150087,
      "public_copy_sha256": "48f09e2e2426e8ca76c1e438600438dca2f9e61360e92ae3edbb538a2cc611d2"
    },
    {
      "filename": "paper_figure_3_long_distance.png",
      "pdf_page": 13,
      "source_label": "Figure 3",
      "caption": "Encoder self-attention following long-distance dependencies.",
      "rect": [
        92,
        55,
        525,
        455
      ],
      "sha256": "ea456861962564d2ef5a158e4205cfea29b537f4a611df989db5d65471f23d78",
      "bytes": 96204,
      "public_copy_sha256": "ea456861962564d2ef5a158e4205cfea29b537f4a611df989db5d65471f23d78"
    },
    {
      "filename": "paper_figure_4_anaphora.png",
      "pdf_page": 14,
      "source_label": "Figure 4",
      "caption": "Attention heads involved in anaphora resolution.",
      "rect": [
        92,
        135,
        525,
        665
      ],
      "sha256": "b1f0c6b0e186acb50cae69c304a9a2a0e1f09fd15f1beb0bba03194528163d7e",
      "bytes": 264855,
      "public_copy_sha256": "b1f0c6b0e186acb50cae69c304a9a2a0e1f09fd15f1beb0bba03194528163d7e"
    }
  ]
}