pith. sign in

Large language model reasoning failures.arXiv preprint arXiv:2602.06176

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

2 Pith papers citing it

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Interactive Evaluation Requires a Design Science

cs.AI · 2026-05-18 · unverdicted · novelty 5.0

Interactive evaluation of AI must be reframed as a distinct paradigm that maps interaction trajectories to judgments on process, recoverability, coordination, robustness, and system performance, supported by a two-axis taxonomy and design principles.

Using Large Language Models in Physics Education

physics.ed-ph · 2026-05-22 · unverdicted · novelty 3.0

Frontier LLMs from late 2025 reach near-perfect scores on text-based physics problem solving and show improved human-grading alignment, yet still struggle to assign partial credit for flawed reasoning.

citing papers explorer

Showing 2 of 2 citing papers.

  • Interactive Evaluation Requires a Design Science cs.AI · 2026-05-18 · unverdicted · none · ref 53

    Interactive evaluation of AI must be reframed as a distinct paradigm that maps interaction trajectories to judgments on process, recoverability, coordination, robustness, and system performance, supported by a two-axis taxonomy and design principles.

  • Using Large Language Models in Physics Education physics.ed-ph · 2026-05-22 · unverdicted · none · ref 46

    Frontier LLMs from late 2025 reach near-perfect scores on text-based physics problem solving and show improved human-grading alignment, yet still struggle to assign partial credit for flawed reasoning.