{
  "url": "https://appliedfrontier.nl/en/research/signal-e9f63aa1f7aaa02f/",
  "title": "How UK AISI and EvalEval Are Making Benchmark Results Reproducible",
  "published": "2026-09-22",
  "excerpt": "",
  "content_sha256": "8dae810853dd245e1ea8941cf6a4bf059f59468279543714521078f4bc2e7033",
  "extracted_chars": 0,
  "artifact_links": [],
  "extraction_scope": "official_feed_metadata",
  "full_text_available": false,
  "feed_provider": "Hugging Face",
  "id": "signal-e9f63aa1f7aaa02f",
  "org": "Hugging Face",
  "topic": "Evaluation & safety",
  "source_kind": "primary_technical_publication",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Evaluation & safety"
  ],
  "checked_at": "2026-11-01T13:17:05+00:00",
  "first_seen": "2026-10-31T19:32:55+00:00",
  "source_hash": "4b893cd0c273efe464e42605fdecc3a13abbf1a3fbb111f21148ab54fccd9222",
  "source_url": "https://huggingface.co/blog/evaleval-aisi",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}