Pith. sign in

A large-scale comparison of human-written versus chatgpt-generated essays

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

LLM-Assisted Cheating Detection in Korean Language via Keystrokes

cs.LG · 2025-07-29 · conditional · novelty 6.0

Keystroke temporal and rhythmic features detect whether Korean writing is original, paraphrased from ChatGPT, or transcribed from ChatGPT, with temporal features stronger in matched cognitive settings and rhythmic features more robust across mismatched cognitive loads.

citing papers explorer

Showing 1 of 1 citing paper.

  • LLM-Assisted Cheating Detection in Korean Language via Keystrokes cs.LG · 2025-07-29 · conditional · none · ref 8

    Keystroke temporal and rhythmic features detect whether Korean writing is original, paraphrased from ChatGPT, or transcribed from ChatGPT, with temporal features stronger in matched cognitive settings and rhythmic features more robust across mismatched cognitive loads.