{
  "id": 4714,
  "url": "https://arxiv.org/abs/2605.08012v1",
  "title": "Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims",
  "summary": "Mechanistic interpretability papers increasingly use causal vocabulary: circuits, mediators, causal abstraction, monosemanticity. Such claims require explicit identification assumptions. A purposive audit of 10 papers across four methodological strands finds no dedicated identification-assumptions section and a recurring pattern: validation metrics such as faithfulness, completeness, monosemanticity, alignment, or ablation effects are reported as causal support without stating the assumptions th",
  "authors": "Zezheng Lin, Fengming Liu",
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-08T17:01:55.000Z",
  "fetched_at": "2026-07-14T16:31:12.745Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4714",
  "original_url": "https://arxiv.org/abs/2605.08012v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}