wassname b1087b8efd llm_judges: verify the five abstract-quoted papers against raw PDF ...

NoLiMa effective length was wrong in both files: most models fall below the
85% threshold at 1-4K tokens, not 8-16K (only GPT-4o 8K, GPT-4.1 16K). NoLiMa
32K count was 11 models, not 10. The Loo quote's first sentence was stitched
from two places and is dropped. JudgeLRM's 8.14% is an Introduction number,
not an abstract one, and the abstract quote had lost /14B and its trailing
clause. Shi et al is 'The findings', not 'Our findings'. Body quotes now
replace abstract quotes where the number matters; tags [ID] -> [FT].

2026-08-14 21:16:13 +08:00

..

evidence

llm_judges: verify the five abstract-quoted papers against raw PDF

2026-08-14 21:16:13 +08:00

spec

Record ML debugging benchmark results

2026-07-13 06:11:08 +08:00

ml_debug_folklore.argdown

initial: ML debugging folklore skill

2026-03-06 10:11:30 +08:00