FRAMES

{
  "doc": "nguyen-2025-sfr-deepresearch.md",
  "context": "Browsing-focused benchmark for multi-hop reasoning QA; SFR-DR-20B achieves 82.8%.",
  "norm_label": "FRAMES",
  "graphify_id": "frames_benchmark",
  "source_file": "nguyen-2025-sfr-deepresearch.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/nguyen-2025-sfr-deepresearch/graph.json",
  "extracted_type": "dataset",
  "source_location": "§4.1",
  "graphify_file_type": "dataset"
}