How do we establish bidirectional causal relationships between neural systems?

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

• There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.793
  Central empirical claim of the paper, demonstrated across tasks and modalities
• Correlative methods like RSA and CKA are insufficient for determining functional similarity between neural systems; causal methods are necessaryclaim0.776
  Central motivating claim of the paper; supported by empirical comparisons showing RSA/CKA miss Markovian differences detectable by MAS.
• When can we say that two neural systems perform a task in the same way?question0.773
  Fundamental question motivating the entire MAS framework.
• Neural networks show substantial alignment with biological representations in the brain, driven by shared task and data constraintsclaim0.771
  Extends convergence argument to brain-machine alignment
• What Are The Bidirectional Relationships Between Multiscale Intelligencequestion0.767
• How Can Neural Systems Adapt Their Dynamics Asquestion0.761
• Investigating the causal substructure of neural representations is necessary to avoid misidentifying data structures of simpler representations as abstract conceptsclaim0.761
  Motivated by the finding that lexical entailment decomposes into word identities.
• There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.760
  Author’s interpretive claim that the shared geometry is general and robust.