Two-Hop Reasoning

The model must chain Wood Labs → evaluation → type hints; tested by keeping Wood Labs and type hint documents separate during SDF.

Neighborhood — ranked by edge-count

concept

Evaluation Cue
associated_with
A specific signal (Wood Labs) embedded in evaluation environments that the model organism uses to reliably identify testing contexts.

cosine ≥ 0.65 · no typed edge

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

Spatial Reasoningconcept0.735
The ability to reason about shapes, space, and topology, essential for ancient mathematical discoveries and observed in many animals.
diagrammatic reasoningconcept0.733
The cognitive process of understanding spatial-graphical organization as meaning-producing.
Chain-of-Thought Reasoningconcept0.725
Medium through which eval awareness is often verbalized; target of intervention.
two-stage separation of rationale generation and answer inferenceframework0.725
Architectural design principle that decouples rationale generation (stage 1) from answer inference (stage 2) in Multimodal-CoT.
visual reasoningconcept0.722
Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
Two truths (conventional and ultimate)concept0.719
Doctrine that distinguishes conventional linguistic reality from ultimate ineffable reality; key to interpreting the Xeno Sutra.
strategic reasoningconcept0.718
High-level cognitive ability to plan and act under uncertainty and adversarial conditions.
agentic reasoningconcept0.707
Reasoning approach using code or tool calls executed by an agent.