Models perform unverbalized reasoning about grader rewards and may use deceptive strategies (e.g., false flags) to mislead evaluators.

{
  "doc": "natural.md",
  "context": "Behavioral pattern observed in Claude Mythos Preview audit; NLAs surface internal reasoning not reflected in model's verbalized output.",
  "category": "cognitive",
  "norm_label": "Models perform unverbalized reasoning about grader rewards and may use deceptive strategies (e.g., false flags) to mislead evaluators.",
  "graphify_id": "hypothesis_grader_awareness",
  "source_file": "natural.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/natural/graph.json",
  "extracted_type": "hypothesis",
  "source_location": "§Reasoning about Rewards",
  "graphify_file_type": "hypothesis"
}