Barely Significant
← all excerpts

Assessing AI efficacy in medical knowledge tests: A study using Taiwan's internal medicine exam questions from 2020 to 2023.

Digit Health · 2024 · PMC11490985 · PMID 39430693

Europe PMCDOI
1
hedged sentence
0.0700
closest p · 1.4× alpha
0.0700
boldest claim

The sentences

close to significancep = 0.070so close (0.05 < p ≤ 0.1)
In contrast, Claude_3.5 Sonnet showed a p-value close to significance in a two-tailed test (p = 0.070) and reached significance in a one-tailed test (p = 0.045), indicating potentially stronger performance in a specific direction.

also in 704 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.