pith. sign in

Majority of the bests: Improving best-of-n via bootstrapping

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

FUSE: Ensembling Verifiers with Zero Labeled Data

stat.ML · 2026-04-20 · unverdicted · novelty 6.0

FUSE ensembles verifiers unsupervisedly by controlling their conditional dependencies to improve spectral ensembling algorithms, matching or exceeding semi-supervised baselines on benchmarks including GPQA Diamond and Humanity's Last Exam.

LACE: Lattice Attention for Cross-thread Exploration

cs.AI · 2026-04-16 · unverdicted · novelty 5.0 · 3 refs

LACE enables concurrent reasoning paths in LLMs to interact via lattice attention and a synthetic training pipeline, raising accuracy more than 7 points over independent parallel search.

citing papers explorer

Showing 2 of 2 citing papers.

  • FUSE: Ensembling Verifiers with Zero Labeled Data stat.ML · 2026-04-20 · unverdicted · none · ref 12

    FUSE ensembles verifiers unsupervisedly by controlling their conditional dependencies to improve spectral ensembling algorithms, matching or exceeding semi-supervised baselines on benchmarks including GPQA Diamond and Humanity's Last Exam.

  • LACE: Lattice Attention for Cross-thread Exploration cs.AI · 2026-04-16 · unverdicted · none · ref 26 · 3 links

    LACE enables concurrent reasoning paths in LLMs to interact via lattice attention and a synthetic training pipeline, raising accuracy more than 7 points over independent parallel search.