### qwen3-8b-base · full · geo
   idiom config:    {'model': 'Qwen/Qwen3-8B-Base', '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': 'Qwen/Qwen3-8B-Base', '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
   1.1702     1.1785  [  1.1428,  1.1984]

== non-idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.0561     1.0540  [  1.0446,  1.0682]
  cross-dataset ratio_u_idiom: idioms - nonidioms  Δ=+0.1141  CI=[+0.0837,+0.1447]  *

== idioms :: ratio_s_idiom ==  (N=9 phrases)  (9 non-finite dropped)
     mean     median                    95% CI
   1.1979     1.2073  [  1.1674,  1.2272]

== non-idioms :: ratio_s_idiom ==  (N=0 phrases)  (18 non-finite dropped)
   no finite values
  cross-dataset ratio_s_idiom: insufficient finite values