{
  "docId": "019dd923-5de0-76bd-a168-6159b949e2c2",
  "docSlug": "ff5d549e5027972a",
  "documentTitle": "GPT-3 and the actuarial landscape",
  "authorId": "OliverWyman",
  "authorName": "Oliver Wyman",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "strategy_consulting",
  "sourceTypeLabel": "Strategy consulting",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.778,
  "pageNumber": 27,
  "pageCount": 46,
  "prevPage": 26,
  "nextPage": 28,
  "slideType": "other",
  "function": "present_framework",
  "density": "sparse",
  "nDataPoints": 0,
  "notes": "This slide illustrates the core linear algebra operations (matrix multiplication) used in the Transformer architecture's attention mechanism.",
  "elementsJson": [
    "process_diagram"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5de0-76bd-a168-6159b949e2c2/27",
  "deckHref": "/decks/019dd923-5de0-76bd-a168-6159b949e2c2",
  "deckJsonHref": "/decks/019dd923-5de0-76bd-a168-6159b949e2c2.json",
  "deckAnchorHref": "/decks/019dd923-5de0-76bd-a168-6159b949e2c2#slide-27",
  "components": [
    {
      "bbox": {
        "h": 0.65,
        "w": 0.92,
        "x": 0.036,
        "y": 0.25
      },
      "kind": "diagram",
      "text": "Input text to tokenization, encoding, and matrix multiplication into K, Q, V vectors",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "77f3b73d-eb09-4c07-a0b2-487ef8bc5ca3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.86,
        "x": 0.036,
        "y": 0.05
      },
      "kind": "title",
      "text": "CREATING KEYS, QUERIES, AND VALUES TO ALLOW SELF-ATTENTION CALCULATION",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "11b1f12d-b35e-4abc-8d40-b74524a13e60",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [
    {
      "name": "Transformer Attention Mechanism",
      "slug": null,
      "matchId": "1a2fca73-7c91-4ef9-b512-093b62a109a0",
      "evidence": "The diagram explicitly maps the transformation of input tokens into Key, Query, and Value vectors via matrix multiplication.",
      "confidence": 1
    }
  ],
  "arcBeats": [
    {
      "to": 31,
      "from": 17,
      "beatId": "5259c9cc-c0ba-4428-ac14-7a6ba8d02be1",
      "arcName": "The Sparkline",
      "arcSlug": "sparkline",
      "beatName": "What Could Be",
      "beatSlug": "sparkline-what-could-be-2",
      "evidence": "The deck explores the potential applications of GPT-3 in the actuarial field.",
      "position": 2,
      "confidence": 0.8,
      "parentBeatName": "Turn",
      "parentBeatSlug": "turn"
    }
  ],
  "loops": [],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}