{
  "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-both-20260730-v5/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,
        425
      ],
      "sha256": "1729d86922c9f97703af178fb52e4f876cc1fce1f67572730580ef16bd659bd5",
      "bytes": 100778,
      "public_copy_sha256": "1729d86922c9f97703af178fb52e4f876cc1fce1f67572730580ef16bd659bd5"
    },
    {
      "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,
        365
      ],
      "sha256": "da9498d3022d1e0fc4d5da2bf59c10c9dde68dda471586019afa126db5674322",
      "bytes": 93837,
      "public_copy_sha256": "da9498d3022d1e0fc4d5da2bf59c10c9dde68dda471586019afa126db5674322"
    },
    {
      "filename": "paper_figure_4_anaphora.png",
      "pdf_page": 14,
      "source_label": "Figure 4",
      "caption": "Attention heads involved in anaphora resolution.",
      "rect": [
        92,
        135,
        525,
        600
      ],
      "sha256": "8dee94773a369dccb1d766c218cc0ac16629a6baf79d15a313d13399d9064407",
      "bytes": 242229,
      "public_copy_sha256": "8dee94773a369dccb1d766c218cc0ac16629a6baf79d15a313d13399d9064407"
    }
  ]
}