Introduces TTS, a dependent type theory replacing global canonical composition with regime-indexed indiscernibility and constructive apartness, proving conservativity, provenance, no-fork-from-empty, and persistence of forks under refinement.
Unraveling the localized latents: Learning stratified manifold structures in llm embedding space with sparse mixture-of-experts.arXiv preprint arXiv:2502.13577
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLM errors concentrate in sparse key tokens (5-10% of sequence) at semantic decision junctions, yielding a new reliability model that explains sustained long-context coherence.
citing papers explorer
-
A Type Theory of Sense: Witnessed Choice in Stratified Semantic Spaces
Introduces TTS, a dependent type theory replacing global canonical composition with regime-indexed indiscernibility and constructive apartness, proving conservativity, provenance, no-fork-from-empty, and persistence of forks under refinement.
-
Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models
LLM errors concentrate in sparse key tokens (5-10% of sequence) at semantic decision junctions, yielding a new reliability model that explains sustained long-context coherence.