Pith. sign in

Smith & Mike Lewis (2022): Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LO 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

On the (Intuitionistic) Logic of Next-Token Prediction

cs.LO · 2026-08-08 · conditional · novelty 4.0

Next-token prediction is modeled as modus ponens in intuitionistic implicational logic, leading to the Arrow model, a recurrent architecture equivalent in spirit to known multiplicative RNNs.

citing papers explorer

Showing 1 of 1 citing paper.

  • On the (Intuitionistic) Logic of Next-Token Prediction cs.LO · 2026-08-08 · conditional · none · ref 5

    Next-token prediction is modeled as modus ponens in intuitionistic implicational logic, leading to the Arrow model, a recurrent architecture equivalent in spirit to known multiplicative RNNs.