{ "status": "passed", "ranked_queries": 486, "scalar_cosines": 3645, "max_score_error": 1.2212453270876722e-15, "aligned_i2t_errors": 15, "same_color_errors": 15, "same_shape_errors": 0, "failures": [ { "seed": 71, "test_row": 6, "gold": 1, "prediction": 0, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 8, "gold": 1, "prediction": 0, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 10, "gold": 2, "prediction": 1, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 14, "gold": 2, "prediction": 1, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 20, "gold": 4, "prediction": 3, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 21, "gold": 4, "prediction": 3, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 24, "gold": 4, "prediction": 3, "same_color": true, "same_shape": false }, { "seed": 71, "test_row": 29, "gold": 5, "prediction": 4, "same_color": true, "same_shape": false }, { "seed": 72, "test_row": 5, "gold": 1, "prediction": 0, "same_color": true, "same_shape": false }, { "seed": 72, "test_row": 8, "gold": 1, "prediction": 0, "same_color": true, "same_shape": false }, { "seed": 72, "test_row": 20, "gold": 4, "prediction": 5, "same_color": true, "same_shape": false }, { "seed": 72, "test_row": 35, "gold": 7, "prediction": 8, "same_color": true, "same_shape": false }, { "seed": 72, "test_row": 39, "gold": 7, "prediction": 6, "same_color": true, "same_shape": false }, { "seed": 73, "test_row": 17, "gold": 3, "prediction": 4, "same_color": true, "same_shape": false }, { "seed": 73, "test_row": 22, "gold": 4, "prediction": 3, "same_color": true, "same_shape": false } ] }