comparison,metric,reference_oof,method_oof,delta_oof,group_bootstrap_ci95_low,group_bootstrap_ci95_high,bootstrap_repeats
B0-B1,accuracy,0.61,0.6,-0.010000000000000009,-0.029710396039603987,0.0,2000
B0-B1,macro_f1,0.387431302270012,0.3612633181126332,-0.02616798415737881,-0.08327057744765032,0.0,2000
B0-B1,mae,0.5989421024918556,0.5642678308486938,-0.034674271643161836,-0.06304207975806683,-0.012443204964559182,2000
B0-B1,pearson,0.23765809617297712,0.34585652345724877,0.10819842728427165,0.04340079372240924,0.19005024141624596,2000
B2-B1,accuracy,0.61,0.58,-0.030000000000000027,-0.0648204607046071,0.0,2000
B2-B1,macro_f1,0.387431302270012,0.33061794334825517,-0.05681335892175682,-0.10940517350156256,-0.0009457159449812041,2000
B2-B1,mae,0.5989421024918556,0.588000754788518,-0.010941347703337656,-0.027305471624463586,0.004017100735475708,2000
B2-B1,pearson,0.23765809617297712,0.2790493470006418,0.041391250827664705,-0.009244736549056344,0.10131359014731482,2000
B3-B1,accuracy,0.61,0.59,-0.020000000000000018,-0.05154639175257736,0.0,2000
B3-B1,macro_f1,0.387431302270012,0.3587962962962963,-0.02863500597371571,-0.07212177947137302,0.0,2000
B3-B1,mae,0.5989421024918556,0.5997931832820177,0.000851080790162051,-0.004701075716562739,0.006246566925533936,2000
B3-B1,pearson,0.23765809617297712,0.23011191320162028,-0.007546182971356841,-0.022226358336772584,0.005402452990031458,2000
B4-B1,accuracy,0.61,0.6,-0.010000000000000009,-0.08080808080808077,0.06196073008849559,2000
B4-B1,macro_f1,0.387431302270012,0.4222603610475464,0.034829058777534394,-0.051408708516982864,0.13655330256210496,2000
B4-B1,mae,0.5989421024918556,0.59276591360569,-0.006176188886165668,-0.03045045264816862,0.015397113913740889,2000
B4-B1,pearson,0.23765809617297712,0.19864510121331094,-0.039012994959666175,-0.1082683426423725,0.03034022099301614,2000