### llama3.1-8b · medial · joint
   idiom config:    {'model': 'meta-llama/Llama-3.1-8B', 'reduction': 'joint', 'medial_only': True, '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': 'joint', 'medial_only': True, '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
   1.1642     1.1508  [  1.1349,  1.1943]

== non-idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.0371     1.0278  [  1.0247,  1.0508]
  cross-dataset ratio_u_idiom: idioms - nonidioms  Δ=+0.1271  CI=[+0.0949,+0.1602]  *

== idioms :: ratio_s_idiom ==  (N=15 phrases)  (3 non-finite dropped)
     mean     median                    95% CI
   1.0008     1.0001  [  1.0002,  1.0016]

== non-idioms :: ratio_s_idiom ==  (N=2 phrases)  (16 non-finite dropped)
     mean     median                    95% CI
   1.0006     1.0006  [  1.0004,  1.0008]
  cross-dataset ratio_s_idiom: idioms - nonidioms  Δ=+0.0002  CI=[-0.0004,+0.0011]