parametric-write-subspace-boundary

OUT derived (depth 5)

Created 2026-08-25T03:08:53+00:00 · Reviewed 2026-08-25T04:02:18+00:00

The operational boundary between parametric recall and contextual retrieval is precisely the geometric boundary of the rank-one addressable subspace: facts whose subject-key projection aligns with the locally-stored key covariance are parametrically editable, while facts outside this subspace must be externally supplied.

Justifications

SL — The geometric divide (head vs tail), the editing addressability bound (rank-one in key space), and the validated routing duality together define a single geometric criterion for the parametric/contextual boundary—no antecedent is sufficient alone.

Antecedents (all must be IN):

  • OUT head-tail-geometric-divide — The parametric/contextual knowledge split is geometrically grounded rather than merely frequency-driven: head-of-distribution facts occupy individually addressable directions in the covariance-whitened feature space (enabling rank-one editing), while long-tail facts are distributed across superposed features where no single direction isolates the knowledge, making external retrieval the only faithful access mechanism.
  • OUT geometric-editing-addressability-bound — The covariance-geometry framework defines a precise and minimal addressable space for knowledge editing (rank-one updates to a single MLP value projection), but the combination of superposition and distributed corpus acquisition structurally bounds this to single-fact local corrections—edits cannot create novel multi-hop associations because the target knowledge was never locally consolidated in the first place.
  • OUT knowledge-routing-faithfulness-validated — The parametric/contextual two-channel knowledge architecture is a genuine computational duality rather than a surface-level re-ranking bias, because retrieval context demonstrably inverts the parametric accuracy trend (accuracy increases with document relevance for rare facts) and BM25 recall remains robust independently of parametric scaling.

Dependents

These beliefs depend on this one: