pith. sign in

Theoretical perspectives on data quality and synergistic effects in pre- and post-training reasoning models, 2026

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

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

An Asymptotic Theory of Chain-of-Thought in In-Context Learning

stat.ML · 2026-06-02 · unverdicted · novelty 6.0

Exact RMT-derived formula for CoT generalization error in linear ICL reveals phase transition between exponential/polynomial improvement, saturation, and overthinking regimes depending on depth, pretraining, and context length.

citing papers explorer

Showing 1 of 1 citing paper.

  • An Asymptotic Theory of Chain-of-Thought in In-Context Learning stat.ML · 2026-06-02 · unverdicted · none · ref 10

    Exact RMT-derived formula for CoT generalization error in linear ICL reveals phase transition between exponential/polynomial improvement, saturation, and overthinking regimes depending on depth, pretraining, and context length.