retrieval + Madrid rule,+ bias recalibration,+ tuned decision weights,ensemble LLM 0.3 / LightGBM 0.7,ensemble LLM 0.5 / LightGBM 0.5,ensemble LLM 0.7 / LightGBM 0.3,n,rep
0.5202,,,0.5588,0.4828,0.4765,5,0
0.5224,,,0.5606,0.5846,0.5711,5,1
0.4924,,,0.5525,0.4872,0.5468,5,2
0.5195,,,0.5633,0.5763,0.5649,5,3
0.5161,,,0.5639,0.5792,0.5531,5,4
0.5133,,,0.5611,0.584,0.5702,5,5
0.5376,,,0.5646,0.4759,0.4775,25,0
0.5318,,,0.566,0.4687,0.4682,25,1
0.512,,,0.5646,0.4715,0.467,25,2
0.5243,,,0.5629,0.4745,0.4715,25,3
0.5027,,,0.5657,0.4795,0.4802,25,4
0.4961,,,0.5642,0.4832,0.4751,25,5
0.5797,0.4727,,0.5759,0.4745,0.4818,50,0
0.5193,0.497,,0.5684,0.4745,0.4682,50,1
0.528,0.5064,,0.5782,0.4817,0.4803,50,2
0.5238,0.4917,,0.5763,0.4689,0.4769,50,3
0.5595,0.5899,,0.5818,0.4852,0.4762,50,4
0.5162,0.4688,,0.5811,0.4666,0.4687,50,5
0.4982,0.4817,,0.5749,0.4791,0.478,100,0
0.5687,0.5728,,0.586,0.4863,0.4847,100,1
0.5367,0.4953,,0.5796,0.4813,0.4767,100,2
0.573,0.4902,,0.5801,0.4827,0.4762,100,3
0.541,0.5091,,0.5771,0.4797,0.4809,100,4
0.5777,0.63,,0.5826,0.4857,0.486,100,5
0.59,0.5981,0.6099,0.5831,0.4952,0.4947,200,0
0.5413,0.6088,0.6506,0.5849,0.4907,0.4939,200,1
0.5607,0.6105,0.594,0.5924,0.4812,0.4918,200,2
0.5432,0.571,0.6483,0.5828,0.4961,0.4915,200,3
0.5822,0.6088,0.5958,0.5815,0.4882,0.4841,200,4
0.5889,0.5985,0.6346,0.5836,0.4907,0.4887,200,5