### qwen3-8b-base · full · joint
   idiom config:    {'model': 'Qwen/Qwen3-8B-Base', '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': 'Qwen/Qwen3-8B-Base', '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
   1.1336     1.1245  [  1.1078,  1.1603]

== non-idioms :: ratio_u_idiom ==  (N=18 phrases)
     mean     median                    95% CI
   1.0252     1.0200  [  1.0170,  1.0345]
  cross-dataset ratio_u_idiom: idioms - nonidioms  Δ=+0.1084  CI=[+0.0805,+0.1362]  *

== idioms :: ratio_s_idiom ==  (N=5 phrases)  (13 non-finite dropped)
     mean     median                    95% CI
   1.0011     1.0009  [  1.0004,  1.0021]

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