### llama3.1-8b · full · geo
   idiom config:    {'model': 'meta-llama/Llama-3.1-8B', 'reduction': 'geometric_mean', 'medial_only': False, 'dtype': 'bfloat16', 'dataset': '/home/prada/PID_evaluation/data/dataset.tsv', 'num_idioms': 18, 'syn_reg_eps': 0.01}
   nonidiom config: {'model': 'meta-llama/Llama-3.1-8B', 'reduction': 'geometric_mean', 'medial_only': False, 'dtype': 'bfloat16', 'dataset': '/home/prada/PID_evaluation/data/nonidioms_dataset.tsv', 'num_idioms': 18, 'syn_reg_eps': 0.01}

== idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.1626     1.1640  [  1.1397,  1.1857]

== non-idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.0551     1.0512  [  1.0431,  1.0680]
  cross-dataset ratio_u_idiom: idioms - nonidioms  Δ=+0.1075  CI=[+0.0814,+0.1337]  *

== idioms :: ratio_s_idiom ==  (N=8 phrases)  (10 non-finite dropped)
     mean     median                    95% CI
   1.1965     1.1897  [  1.1617,  1.2285]

== non-idioms :: ratio_s_idiom ==  (N=1 phrases)  (17 non-finite dropped)
     mean     median                    95% CI
   1.3208     1.3208  [  1.3208,  1.3208]
  cross-dataset ratio_s_idiom: idioms - nonidioms  Δ=-0.1243  CI=[-0.1591,-0.0922]  *