### llama3.1-8b · full · joint
   idiom config:    {'model': 'meta-llama/Llama-3.1-8B', 'reduction': 'joint', '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': 'joint', '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
   1.1274     1.1260  [  1.1061,  1.1484]

== non-idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.0266     1.0229  [  1.0175,  1.0369]
  cross-dataset ratio_u_idiom: idioms - nonidioms  Δ=+0.1007  CI=[+0.0771,+0.1242]  *

== idioms :: ratio_s_idiom ==  (N=8 phrases)  (10 non-finite dropped)
     mean     median                    95% CI
   1.0006     1.0003  [  1.0002,  1.0012]

== non-idioms :: ratio_s_idiom ==  (N=2 phrases)  (16 non-finite dropped)
     mean     median                    95% CI
   1.0030     1.0030  [  1.0009,  1.0051]
  cross-dataset ratio_s_idiom: idioms - nonidioms  Δ=-0.0024  CI=[-0.0048,+0.0001]