Baseline controls are not optional but central to valid introspection claims

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Either introspection is an emergent capability requiring larger scale, or more stringent controls are needed to test introspection in smaller modelsclaim0.793
  Alternative interpretations offered for why binary detection fails in Llama 3.1 8B but frontier models claim success
• Our central claim is deliberately limited. We do not claim that these models have conscious felt experience, nor that a numeric self-report gives direct access to anything like human phenomenology.quote0.773
  Explicit scope delimitation that situates the paper's claims within interpretability rather than consciousness science
• The paper does not claim these models have conscious felt experience; introspection is defined operationally as causal informational coupling agnostic about consciousnessclaim0.761
  Explicit scope limitation following Comsa & Shanahan 2025 and McClelland 2024
• Introspection relies on general-purpose computational mechanisms—attention-based anomaly detection and residual stream dynamics—rather than specialized introspection circuitsclaim0.759
  Interpretive claim about the mechanistic substrate of introspection in LLMs
• we operationalize introspection as causal informational coupling between a numeric self-report and an independently measured internal directionquote0.755
  Load-bearing operational definition that distinguishes the paper's framework from prior approaches
• Introspective agents generally outperform standard no-pain baseline agents across environments and reward categoriesclaim0.746
  Central empirical claim of the paper supported by statistical tests
• There may exist a global introspective faculty or steering direction that improves introspection uniformly across all conceptshypothesis0.744
  Framed as an open problem; current evidence only points to local pair-specific improvement
• Do apparent introspection results reflect genuine metacognitive access to internal representations, or do they emerge from simpler mechanisms such as output distribution shifts?question0.742
  Key discriminating question motivating the baseline control experiment