{
 "@context": "https://schema.org",
 "@type": "Claim",
 "@id": "https://wulfkaal.github.io/claims/4755632-002",
 "identifier": "kaal:claim:4755632-002",
 "text": "Transformer neural network architecture removes the scale constraint on training data but not the quality constraint, so data quality continues to be a major unsolved issue for large language models even where internet scale corpora are available.",
 "author": {
  "@type": "Person",
  "name": "Wulf A. Kaal",
  "identifier": "https://orcid.org/0009-0008-7840-1847"
 },
 "citation": "Wulf A. Kaal, AI Learning - Decentralized Governance to Optimize Human Output Datasets for AI Learning (2024). SSRN: https://ssrn.com/abstract=4755632",
 "isBasedOn": {
  "@type": "ScholarlyArticle",
  "name": "AI Learning - Decentralized Governance to Optimize Human Output Datasets for AI Learning",
  "datePublished": "2024",
  "url": "https://ssrn.com/abstract=4755632",
  "sha256": "972ccebf0c06ac1767a9e443bb95942b7670e806a63c25ee817c368a64c8eca8",
  "encoding": "https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202024%20-%20AI%20Learning%20-%20Decentralized%20Governance%20to%20Optimize%20Human%20Output%20Datasets%20for%20AI%20Learning.pdf"
 },
 "keywords": [
  "ai-and-agents",
  "education-and-practice"
 ],
 "about": [
  "transformer-architecture",
  "llm-training",
  "data-quality",
  "scale-limits"
 ],
 "abstract": "data quality continues to be a huge issue for LLMs",
 "additionalProperty": [
  {
   "@type": "PropertyValue",
   "name": "claim_type",
   "value": "failure"
  },
  {
   "@type": "PropertyValue",
   "name": "confidence",
   "value": "argued"
  },
  {
   "@type": "PropertyValue",
   "name": "scope_conditions",
   "value": [
    "applies to LLMs trained on internet derived corpora"
   ]
  },
  {
   "@type": "PropertyValue",
   "name": "is_failure_mode",
   "value": true
  },
  {
   "@type": "PropertyValue",
   "name": "attestations",
   "value": "https://wulfkaal.github.io/colloquium/attestations/1e6590e21e6dc2f987fa5f3385be5b59f00ed7acfce790e7a30567d347ac1616.json"
  },
  {
   "@type": "PropertyValue",
   "name": "edges",
   "value": [
    {
     "rel": "extended_by",
     "to": "https://wulfkaal.github.io/claims/5095633-004",
     "to_id": "kaal:claim:5095633-004",
     "similarity": 0.42
    }
   ]
  }
 ],
 "isPartOf": {
  "@id": "https://wulfkaal.github.io/claims/index.json"
 },
 "dateModified": "2026-07-27",
 "version": "1.0",
 "sha256": "1e6590e21e6dc2f987fa5f3385be5b59f00ed7acfce790e7a30567d347ac1616",
 "canonicalForm": "https://wulfkaal.github.io/claims/4755632-002.md"
}