@prefix schema: <https://schema.org/> .
@prefix af: <https://anchorfact.org/ns#> .

<https://anchorfact.org/kb/ai/ai-for-data-curation>
  a schema:article ;
  schema:headline "AI for Data Curation: Web-Scale Filtering, Deduplication, and Quality Scoring for LLM Training" ;
  schema:url <https://anchorfact.org/ai/ai-for-data-curation/> ;
  af:status "public" ;
  af:confidence "medium" ;
  af:confidenceScore "0.8" ;
  af:confidenceBasis "verified_sources" ;
  af:generationMethod "ai_structured" .

<https://anchorfact.org/kb/ai/ai-for-data-curation>
  schema:citation <https://arxiv.org/abs/1803.09010> ;
  af:sourceTier "A" .

<https://anchorfact.org/kb/ai/ai-for-data-curation>
  schema:citation <https://aclanthology.org/Q18-1041/> ;
  af:sourceTier "A" .

<https://anchorfact.org/kb/ai/ai-for-data-curation>
  schema:citation <https://research.google/pubs/data-cascades-in-high-stakes-ai/> ;
  af:sourceTier "A" .