A large language model pipeline for automated citation quality scoring across engineering journal quartiles with expert validation.

The omnibus difference remained highly significant (H = 170.7, p < 0.001, ε2 = 0.031), and the Q1–Q2 contrast — the study’s central finding — remained significant ( p = 0.003, r = 0.057), with Q1 retaining the lowest mean (rising from 7.52 to 7.73) and Q2 the highest (8.09).

also in 132,142 other papers