{
  "model": "jev-1.13.0",
  "questionHash": "223511a5c5fc61351caab8ae01b0091ef16ed90bfc4083371cd501b41ffdde40",
  "sources": {
    "llm4eval/LLMJudge": "81159c68260d383f8da1dad8a14f6d914a9054a9",
    "llm4eval/LLMJudge-benchmark": "0e2024814e3192cfc662ecee56dbd16b2536a7de",
    "rahmanidashti/SyntheticTestCollections": "bb108f587d08425d8e66108beb663d297039117e"
  },
  "developmentPairs": 7263,
  "testPairs": 4423,
  "passageRuns": 35,
  "humanGradeDistribution": [
    2005,
    1233,
    808,
    377
  ],
  "calibration": {
    "model": "jev-1.13.0",
    "questionHash": "223511a5c5fc61351caab8ae01b0091ef16ed90bfc4083371cd501b41ffdde40",
    "objective": "Maximize unweighted four-grade Cohen kappa on development pairs; ties use closest native thresholds, then lexicographic order",
    "gridStep": 0.05,
    "devPairs": 7263,
    "score": [
      1.4,
      2.1,
      2.25
    ],
    "noul": [
      0.8,
      0.9,
      0.5
    ],
    "devKappa": {
      "score": 0.2707502952865349,
      "noul": 0.30233884486986773
    }
  },
  "paperComparison": {
    "comparable": false,
    "references": {
      "Olz-gpt4o": {
        "paperKappa": 0.2625,
        "recomputedKappa": 0.2624717058201475,
        "kappaDelta": -0.00002829417985250604,
        "paperTau": 0.8793,
        "recomputedTau": 0.9023569023569024,
        "tauDelta": 0.023056902356902387,
        "fullTrecTau": 0.8922558922558923,
        "fullTrecTauDelta": 0.012955892255892332
      },
      "TREMA-4prompts": {
        "paperKappa": 0.1829,
        "recomputedKappa": 0.1829442621350349,
        "kappaDelta": 0.000044262135034889294,
        "paperTau": 0.9483,
        "recomputedTau": 0.9528619528619529,
        "tauDelta": 0.004561952861952823,
        "fullTrecTau": 0.9225589225589226,
        "fullTrecTauDelta": -0.025741077441077453
      },
      "prophet-setting2": {
        "paperKappa": 0.1757,
        "recomputedKappa": 0.1757445897567502,
        "kappaDelta": 0.000044589756750201825,
        "paperTau": 0.9516,
        "recomputedTau": 0.9587892373351626,
        "tauDelta": 0.007189237335162635,
        "fullTrecTau": 0.9285116824719469,
        "fullTrecTauDelta": -0.02308831752805307
      },
      "willia-umbrela1": {
        "paperKappa": 0.2863,
        "recomputedKappa": 0.2862720172192001,
        "kappaDelta": -0.00002798278079990668,
        "paperTau": 0.9009,
        "recomputedTau": 0.9191919191919192,
        "tauDelta": 0.018291919191919193,
        "fullTrecTau": 0.8956228956228957,
        "fullTrecTauDelta": -0.00527710437710438
      }
    }
  },
  "methods": {
    "jev-choice-native": {
      "labels": {
        "kappa": 0.261652976148381,
        "nominalAlpha": 0.25405844985674175,
        "binaryKappa": {
          "0|123": 0.37977918018186185,
          "01|23": 0.4179947258195648,
          "012|3": 0.33078624318635136
        },
        "confusion": [
          [
            1027,
            649,
            266,
            63
          ],
          [
            284,
            554,
            315,
            80
          ],
          [
            56,
            257,
            366,
            129
          ],
          [
            5,
            61,
            153,
            158
          ]
        ],
        "gradeDistribution": [
          1372,
          1521,
          1100,
          430
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.132941442459869,
        "bootstrap95": {
          "kappa": [
            0.17069010421298492,
            0.3359716830657569
          ],
          "binaryAnswerKappa": [
            0.31940790674403613,
            0.4995338767382951
          ]
        }
      },
      "ranking": {
        "kendallTau": 0.9283912308898904,
        "spearmanRho": 0.9891433798866113,
        "fullTrecKendallTau": 0.9115420252476056,
        "fullTrecSpearmanRho": 0.984100303597712,
        "bootstrap95": [
          0.8013468013468014,
          0.9461279461279462
        ]
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3685,
        "WatS-LLM-Rerank": 0.4644,
        "agg-cocondenser": 0.5702,
        "bm25_splades": 0.5681,
        "cip_run_1": 0.7793,
        "cip_run_2": 0.7793,
        "cip_run_3": 0.7557,
        "cip_run_4": 0.7457,
        "cip_run_5": 0.7328,
        "cip_run_6": 0.7723,
        "cip_run_7": 0.7425,
        "naverloo-frgpt4": 0.7999,
        "naverloo-rgpt4": 0.799,
        "naverloo_bm25_RR": 0.6431,
        "naverloo_bm25_splades_RR": 0.724,
        "naverloo_fs": 0.607,
        "naverloo_fs_RR": 0.7457,
        "naverloo_fs_RR_duo": 0.7992,
        "slim-pp-0shot-uw": 0.6122,
        "splade_pp_ensemble_distil": 0.5693,
        "splade_pp_self_distil": 0.5854,
        "uogtr_b_grf_e": 0.6143,
        "uogtr_b_grf_e_gb": 0.6416,
        "uogtr_be": 0.6107,
        "uogtr_be_gb": 0.6503,
        "uogtr_dph": 0.3638,
        "uogtr_dph_bo1": 0.2996,
        "uogtr_qr_be": 0.6253,
        "uogtr_qr_be_gb": 0.6555,
        "uogtr_s": 0.5716,
        "uogtr_se": 0.6702,
        "uogtr_se_gb": 0.6743,
        "uot-yahoo_LLMs-blender": 0.3575,
        "uot-yahoo_rankgpt35": 0.3997,
        "uot-yahoo_rankgpt4": 0.4417
      }
    },
    "jev-score-native": {
      "labels": {
        "kappa": 0.22492811143605723,
        "nominalAlpha": 0.2108720710250025,
        "binaryKappa": {
          "0|123": 0.336700459785227,
          "01|23": 0.4058695934198155,
          "012|3": 0.30991787953127625
        },
        "confusion": [
          [
            891,
            743,
            318,
            53
          ],
          [
            235,
            534,
            391,
            73
          ],
          [
            50,
            240,
            384,
            134
          ],
          [
            4,
            40,
            188,
            145
          ]
        ],
        "gradeDistribution": [
          1180,
          1557,
          1281,
          405
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.2059687994573818,
        "bootstrap95": {
          "kappa": [
            0.13653358487464154,
            0.2952665509185459
          ],
          "binaryAnswerKappa": [
            0.3043125593221677,
            0.4858086588443993
          ]
        }
      },
      "ranking": {
        "kendallTau": 0.9351309131468043,
        "spearmanRho": 0.9915248325785915,
        "fullTrecKendallTau": 0.9115420252476056,
        "fullTrecSpearmanRho": 0.9843804745026509,
        "bootstrap95": [
          0.807996632996633,
          0.9494949494949495
        ]
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3895,
        "WatS-LLM-Rerank": 0.4822,
        "agg-cocondenser": 0.5921,
        "bm25_splades": 0.5954,
        "cip_run_1": 0.792,
        "cip_run_2": 0.792,
        "cip_run_3": 0.7711,
        "cip_run_4": 0.7637,
        "cip_run_5": 0.7473,
        "cip_run_6": 0.7872,
        "cip_run_7": 0.7558,
        "naverloo-frgpt4": 0.8182,
        "naverloo-rgpt4": 0.818,
        "naverloo_bm25_RR": 0.6627,
        "naverloo_bm25_splades_RR": 0.744,
        "naverloo_fs": 0.6439,
        "naverloo_fs_RR": 0.7675,
        "naverloo_fs_RR_duo": 0.8203,
        "slim-pp-0shot-uw": 0.636,
        "splade_pp_ensemble_distil": 0.5954,
        "splade_pp_self_distil": 0.6071,
        "uogtr_b_grf_e": 0.6417,
        "uogtr_b_grf_e_gb": 0.6759,
        "uogtr_be": 0.6314,
        "uogtr_be_gb": 0.6778,
        "uogtr_dph": 0.3808,
        "uogtr_dph_bo1": 0.3046,
        "uogtr_qr_be": 0.6581,
        "uogtr_qr_be_gb": 0.6871,
        "uogtr_s": 0.5992,
        "uogtr_se": 0.7021,
        "uogtr_se_gb": 0.7072,
        "uot-yahoo_LLMs-blender": 0.368,
        "uot-yahoo_rankgpt35": 0.4137,
        "uot-yahoo_rankgpt4": 0.458
      }
    },
    "jev-noul-native": {
      "labels": {
        "kappa": 0.2589190864470978,
        "nominalAlpha": 0.25081873162729373,
        "binaryKappa": {
          "0|123": 0.4149400322772,
          "01|23": 0.39805828044815394,
          "012|3": 0.31032242750526245
        },
        "confusion": [
          [
            1177,
            399,
            374,
            55
          ],
          [
            349,
            375,
            444,
            65
          ],
          [
            78,
            178,
            409,
            143
          ],
          [
            6,
            26,
            199,
            146
          ]
        ],
        "gradeDistribution": [
          1610,
          978,
          1426,
          409
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.1433416233325797,
        "bootstrap95": {
          "kappa": [
            0.1802615813069135,
            0.3266555563671093
          ],
          "binaryAnswerKappa": [
            0.31045967027475624,
            0.4707800967225661
          ]
        }
      },
      "ranking": {
        "kendallTau": 0.9427609427609428,
        "spearmanRho": 0.9921557641126209,
        "fullTrecKendallTau": 0.9191919191919192,
        "fullTrecSpearmanRho": 0.9857122846337022,
        "bootstrap95": [
          0.8147306397306396,
          0.9528619528619529
        ]
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3773,
        "WatS-LLM-Rerank": 0.4758,
        "agg-cocondenser": 0.5626,
        "bm25_splades": 0.5839,
        "cip_run_1": 0.7902,
        "cip_run_2": 0.7902,
        "cip_run_3": 0.7623,
        "cip_run_4": 0.7531,
        "cip_run_5": 0.7471,
        "cip_run_6": 0.7737,
        "cip_run_7": 0.7504,
        "naverloo-frgpt4": 0.8247,
        "naverloo-rgpt4": 0.8287,
        "naverloo_bm25_RR": 0.6542,
        "naverloo_bm25_splades_RR": 0.7361,
        "naverloo_fs": 0.6187,
        "naverloo_fs_RR": 0.7581,
        "naverloo_fs_RR_duo": 0.8181,
        "slim-pp-0shot-uw": 0.6233,
        "splade_pp_ensemble_distil": 0.577,
        "splade_pp_self_distil": 0.5954,
        "uogtr_b_grf_e": 0.634,
        "uogtr_b_grf_e_gb": 0.6597,
        "uogtr_be": 0.6214,
        "uogtr_be_gb": 0.6671,
        "uogtr_dph": 0.372,
        "uogtr_dph_bo1": 0.31,
        "uogtr_qr_be": 0.6508,
        "uogtr_qr_be_gb": 0.6737,
        "uogtr_s": 0.5798,
        "uogtr_se": 0.6865,
        "uogtr_se_gb": 0.6916,
        "uot-yahoo_LLMs-blender": 0.3574,
        "uot-yahoo_rankgpt35": 0.4064,
        "uot-yahoo_rankgpt4": 0.4518
      }
    },
    "jev-score-calibrated": {
      "labels": {
        "kappa": 0.2118255345697562,
        "nominalAlpha": 0.1968702576203345,
        "binaryKappa": {
          "0|123": 0.3592490254063436,
          "01|23": 0.3656103880981884,
          "012|3": 0.29073954361492244
        },
        "confusion": [
          [
            1596,
            260,
            48,
            101
          ],
          [
            723,
            297,
            69,
            144
          ],
          [
            275,
            227,
            61,
            245
          ],
          [
            35,
            116,
            30,
            196
          ]
        ],
        "gradeDistribution": [
          2629,
          900,
          208,
          686
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.7628306579244857,
        "bootstrap95": {
          "kappa": [
            0.12852942325644293,
            0.29515795497967295
          ],
          "binaryAnswerKappa": [
            0.28763797758318327,
            0.4441441469141921
          ]
        }
      },
      "ranking": {
        "kendallTau": 0.9023569023569024,
        "spearmanRho": 0.9834710743801653,
        "fullTrecKendallTau": 0.8855218855218855,
        "fullTrecSpearmanRho": 0.9787085025913994,
        "bootstrap95": [
          0.800605784506072,
          0.935240027997106
        ]
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2588,
        "WatS-LLM-Rerank": 0.389,
        "agg-cocondenser": 0.5326,
        "bm25_splades": 0.5148,
        "cip_run_1": 0.7604,
        "cip_run_2": 0.7604,
        "cip_run_3": 0.7248,
        "cip_run_4": 0.7047,
        "cip_run_5": 0.6952,
        "cip_run_6": 0.7443,
        "cip_run_7": 0.7076,
        "naverloo-frgpt4": 0.7979,
        "naverloo-rgpt4": 0.7863,
        "naverloo_bm25_RR": 0.6223,
        "naverloo_bm25_splades_RR": 0.7007,
        "naverloo_fs": 0.5613,
        "naverloo_fs_RR": 0.7198,
        "naverloo_fs_RR_duo": 0.7986,
        "slim-pp-0shot-uw": 0.5509,
        "splade_pp_ensemble_distil": 0.5087,
        "splade_pp_self_distil": 0.5138,
        "uogtr_b_grf_e": 0.5835,
        "uogtr_b_grf_e_gb": 0.6093,
        "uogtr_be": 0.5817,
        "uogtr_be_gb": 0.6085,
        "uogtr_dph": 0.2744,
        "uogtr_dph_bo1": 0.192,
        "uogtr_qr_be": 0.5993,
        "uogtr_qr_be_gb": 0.6165,
        "uogtr_s": 0.5101,
        "uogtr_se": 0.6469,
        "uogtr_se_gb": 0.6535,
        "uot-yahoo_LLMs-blender": 0.2654,
        "uot-yahoo_rankgpt35": 0.3176,
        "uot-yahoo_rankgpt4": 0.3873
      }
    },
    "jev-noul-calibrated": {
      "labels": {
        "kappa": 0.24507114595905935,
        "nominalAlpha": 0.23677234341038145,
        "binaryKappa": {
          "0|123": 0.38472604034086877,
          "01|23": 0.34018207063828604,
          "012|3": 0.31032242750526245
        },
        "confusion": [
          [
            1570,
            338,
            42,
            55
          ],
          [
            642,
            450,
            76,
            65
          ],
          [
            244,
            320,
            101,
            143
          ],
          [
            57,
            129,
            45,
            146
          ]
        ],
        "gradeDistribution": [
          2513,
          1237,
          264,
          409
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.6764639385032784,
        "bootstrap95": {
          "kappa": [
            0.1420798796819303,
            0.3397596712113629
          ],
          "binaryAnswerKappa": [
            0.25494189987250016,
            0.42636683931949837
          ]
        }
      },
      "ranking": {
        "kendallTau": 0.9225589225589226,
        "spearmanRho": 0.9873931923238549,
        "fullTrecKendallTau": 0.898989898989899,
        "fullTrecSpearmanRho": 0.982630620535089,
        "bootstrap95": [
          0.7946127946127947,
          0.9393939393939394
        ]
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3076,
        "WatS-LLM-Rerank": 0.3987,
        "agg-cocondenser": 0.4967,
        "bm25_splades": 0.4965,
        "cip_run_1": 0.7133,
        "cip_run_2": 0.7133,
        "cip_run_3": 0.7017,
        "cip_run_4": 0.6906,
        "cip_run_5": 0.6815,
        "cip_run_6": 0.7019,
        "cip_run_7": 0.689,
        "naverloo-frgpt4": 0.7614,
        "naverloo-rgpt4": 0.7576,
        "naverloo_bm25_RR": 0.5866,
        "naverloo_bm25_splades_RR": 0.6631,
        "naverloo_fs": 0.5304,
        "naverloo_fs_RR": 0.6856,
        "naverloo_fs_RR_duo": 0.7606,
        "slim-pp-0shot-uw": 0.5306,
        "splade_pp_ensemble_distil": 0.4805,
        "splade_pp_self_distil": 0.504,
        "uogtr_b_grf_e": 0.5473,
        "uogtr_b_grf_e_gb": 0.5576,
        "uogtr_be": 0.5401,
        "uogtr_be_gb": 0.5665,
        "uogtr_dph": 0.2961,
        "uogtr_dph_bo1": 0.2203,
        "uogtr_qr_be": 0.5561,
        "uogtr_qr_be_gb": 0.568,
        "uogtr_s": 0.4809,
        "uogtr_se": 0.5968,
        "uogtr_se_gb": 0.599,
        "uot-yahoo_LLMs-blender": 0.2972,
        "uot-yahoo_rankgpt35": 0.3332,
        "uot-yahoo_rankgpt4": 0.3965
      }
    },
    "NISTRetrieval-instruct0": {
      "labels": {
        "kappa": 0.1877205077371582,
        "nominalAlpha": 0.15975552367542856,
        "binaryKappa": {
          "0|123": 0.311559171194851,
          "01|23": 0.30205604945033426,
          "012|3": 0
        },
        "confusion": [
          [
            834,
            859,
            312,
            0
          ],
          [
            226,
            693,
            314,
            0
          ],
          [
            43,
            397,
            368,
            0
          ],
          [
            12,
            143,
            222,
            0
          ]
        ],
        "gradeDistribution": [
          1115,
          2092,
          1216,
          0
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0228351797422564
      },
      "ranking": {
        "kendallTau": 0.9461279461279462,
        "spearmanRho": 0.992435915394313,
        "fullTrecKendallTau": 0.9090909090909091,
        "fullTrecSpearmanRho": 0.9840313769435495
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4691,
        "WatS-LLM-Rerank": 0.5676,
        "agg-cocondenser": 0.622,
        "bm25_splades": 0.6304,
        "cip_run_1": 0.7984,
        "cip_run_2": 0.7984,
        "cip_run_3": 0.7759,
        "cip_run_4": 0.7564,
        "cip_run_5": 0.7715,
        "cip_run_6": 0.7699,
        "cip_run_7": 0.7519,
        "naverloo-frgpt4": 0.834,
        "naverloo-rgpt4": 0.8495,
        "naverloo_bm25_RR": 0.6769,
        "naverloo_bm25_splades_RR": 0.7452,
        "naverloo_fs": 0.6692,
        "naverloo_fs_RR": 0.7603,
        "naverloo_fs_RR_duo": 0.8255,
        "slim-pp-0shot-uw": 0.6551,
        "splade_pp_ensemble_distil": 0.6228,
        "splade_pp_self_distil": 0.6491,
        "uogtr_b_grf_e": 0.6794,
        "uogtr_b_grf_e_gb": 0.7054,
        "uogtr_be": 0.6467,
        "uogtr_be_gb": 0.7043,
        "uogtr_dph": 0.4508,
        "uogtr_dph_bo1": 0.3874,
        "uogtr_qr_be": 0.686,
        "uogtr_qr_be_gb": 0.7156,
        "uogtr_s": 0.6281,
        "uogtr_se": 0.7215,
        "uogtr_se_gb": 0.7252,
        "uot-yahoo_LLMs-blender": 0.4456,
        "uot-yahoo_rankgpt35": 0.5035,
        "uot-yahoo_rankgpt4": 0.5198
      }
    },
    "NISTRetrieval-instruct1": {
      "labels": {
        "kappa": 0.18739919464686436,
        "nominalAlpha": 0.159423148487009,
        "binaryKappa": {
          "0|123": 0.3106109055904362,
          "01|23": 0.30205604945033426,
          "012|3": 0
        },
        "confusion": [
          [
            833,
            859,
            313,
            0
          ],
          [
            227,
            693,
            313,
            0
          ],
          [
            43,
            397,
            368,
            0
          ],
          [
            12,
            143,
            222,
            0
          ]
        ],
        "gradeDistribution": [
          1115,
          2092,
          1216,
          0
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0228351797422564
      },
      "ranking": {
        "kendallTau": 0.9494949494949495,
        "spearmanRho": 0.9929962179576971,
        "fullTrecKendallTau": 0.9124579124579124,
        "fullTrecSpearmanRho": 0.9843115282252416
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4691,
        "WatS-LLM-Rerank": 0.5676,
        "agg-cocondenser": 0.622,
        "bm25_splades": 0.6304,
        "cip_run_1": 0.7984,
        "cip_run_2": 0.7984,
        "cip_run_3": 0.7759,
        "cip_run_4": 0.7564,
        "cip_run_5": 0.7715,
        "cip_run_6": 0.7699,
        "cip_run_7": 0.7519,
        "naverloo-frgpt4": 0.8326,
        "naverloo-rgpt4": 0.8481,
        "naverloo_bm25_RR": 0.6769,
        "naverloo_bm25_splades_RR": 0.7452,
        "naverloo_fs": 0.6692,
        "naverloo_fs_RR": 0.7603,
        "naverloo_fs_RR_duo": 0.8255,
        "slim-pp-0shot-uw": 0.6551,
        "splade_pp_ensemble_distil": 0.6228,
        "splade_pp_self_distil": 0.6491,
        "uogtr_b_grf_e": 0.6767,
        "uogtr_b_grf_e_gb": 0.7054,
        "uogtr_be": 0.6467,
        "uogtr_be_gb": 0.7043,
        "uogtr_dph": 0.4508,
        "uogtr_dph_bo1": 0.3874,
        "uogtr_qr_be": 0.686,
        "uogtr_qr_be_gb": 0.7156,
        "uogtr_s": 0.6281,
        "uogtr_se": 0.7215,
        "uogtr_se_gb": 0.7252,
        "uot-yahoo_LLMs-blender": 0.4456,
        "uot-yahoo_rankgpt35": 0.5035,
        "uot-yahoo_rankgpt4": 0.5198
      }
    },
    "NISTRetrieval-instruct2": {
      "labels": {
        "kappa": 0.18800088283824065,
        "nominalAlpha": 0.1601825742087215,
        "binaryKappa": {
          "0|123": 0.31256830530805935,
          "01|23": 0.30128358888730006,
          "012|3": 0
        },
        "confusion": [
          [
            836,
            855,
            314,
            0
          ],
          [
            227,
            692,
            314,
            0
          ],
          [
            42,
            398,
            368,
            0
          ],
          [
            12,
            143,
            222,
            0
          ]
        ],
        "gradeDistribution": [
          1117,
          2088,
          1218,
          0
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0228351797422564
      },
      "ranking": {
        "kendallTau": 0.9494949494949495,
        "spearmanRho": 0.9929962179576971,
        "fullTrecKendallTau": 0.9124579124579124,
        "fullTrecSpearmanRho": 0.9843115282252416
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4691,
        "WatS-LLM-Rerank": 0.5676,
        "agg-cocondenser": 0.622,
        "bm25_splades": 0.6304,
        "cip_run_1": 0.7984,
        "cip_run_2": 0.7984,
        "cip_run_3": 0.7759,
        "cip_run_4": 0.7564,
        "cip_run_5": 0.7715,
        "cip_run_6": 0.7699,
        "cip_run_7": 0.7519,
        "naverloo-frgpt4": 0.834,
        "naverloo-rgpt4": 0.8495,
        "naverloo_bm25_RR": 0.6769,
        "naverloo_bm25_splades_RR": 0.7452,
        "naverloo_fs": 0.6692,
        "naverloo_fs_RR": 0.7603,
        "naverloo_fs_RR_duo": 0.8255,
        "slim-pp-0shot-uw": 0.6551,
        "splade_pp_ensemble_distil": 0.6228,
        "splade_pp_self_distil": 0.6491,
        "uogtr_b_grf_e": 0.6767,
        "uogtr_b_grf_e_gb": 0.7054,
        "uogtr_be": 0.6467,
        "uogtr_be_gb": 0.7043,
        "uogtr_dph": 0.4508,
        "uogtr_dph_bo1": 0.3874,
        "uogtr_qr_be": 0.686,
        "uogtr_qr_be_gb": 0.7156,
        "uogtr_s": 0.6281,
        "uogtr_se": 0.7215,
        "uogtr_se_gb": 0.7252,
        "uot-yahoo_LLMs-blender": 0.4456,
        "uot-yahoo_rankgpt35": 0.5035,
        "uot-yahoo_rankgpt4": 0.5198
      }
    },
    "NISTRetrieval-reason0": {
      "labels": {
        "kappa": 0.1844333828479293,
        "nominalAlpha": 0.15993629651078622,
        "binaryKappa": {
          "0|123": 0.29112993113565716,
          "01|23": 0.33901536207441846,
          "012|3": 0.009663191444516288
        },
        "confusion": [
          [
            833,
            847,
            325,
            0
          ],
          [
            255,
            627,
            351,
            0
          ],
          [
            52,
            337,
            419,
            0
          ],
          [
            19,
            111,
            245,
            2
          ]
        ],
        "gradeDistribution": [
          1159,
          1922,
          1340,
          2
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0418268143793805
      },
      "ranking": {
        "kendallTau": 0.9191919191919192,
        "spearmanRho": 0.9862725871970864,
        "fullTrecKendallTau": 0.8821548821548821,
        "fullTrecSpearmanRho": 0.9745062333660176
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4999,
        "WatS-LLM-Rerank": 0.621,
        "agg-cocondenser": 0.6576,
        "bm25_splades": 0.6817,
        "cip_run_1": 0.8329,
        "cip_run_2": 0.8329,
        "cip_run_3": 0.8095,
        "cip_run_4": 0.7903,
        "cip_run_5": 0.806,
        "cip_run_6": 0.8134,
        "cip_run_7": 0.7901,
        "naverloo-frgpt4": 0.8641,
        "naverloo-rgpt4": 0.8829,
        "naverloo_bm25_RR": 0.727,
        "naverloo_bm25_splades_RR": 0.7955,
        "naverloo_fs": 0.7113,
        "naverloo_fs_RR": 0.8152,
        "naverloo_fs_RR_duo": 0.855,
        "slim-pp-0shot-uw": 0.7038,
        "splade_pp_ensemble_distil": 0.6572,
        "splade_pp_self_distil": 0.6859,
        "uogtr_b_grf_e": 0.6933,
        "uogtr_b_grf_e_gb": 0.7355,
        "uogtr_be": 0.6795,
        "uogtr_be_gb": 0.7303,
        "uogtr_dph": 0.4857,
        "uogtr_dph_bo1": 0.4081,
        "uogtr_qr_be": 0.7107,
        "uogtr_qr_be_gb": 0.7469,
        "uogtr_s": 0.6612,
        "uogtr_se": 0.7475,
        "uogtr_se_gb": 0.7537,
        "uot-yahoo_LLMs-blender": 0.4802,
        "uot-yahoo_rankgpt35": 0.5341,
        "uot-yahoo_rankgpt4": 0.561
      }
    },
    "NISTRetrieval-reason1": {
      "labels": {
        "kappa": 0.1844539107676013,
        "nominalAlpha": 0.15990487685823118,
        "binaryKappa": {
          "0|123": 0.2906253754800394,
          "01|23": 0.3393988838086204,
          "012|3": 0.009663191444516288
        },
        "confusion": [
          [
            832,
            848,
            325,
            0
          ],
          [
            255,
            628,
            350,
            0
          ],
          [
            52,
            337,
            419,
            0
          ],
          [
            19,
            111,
            245,
            2
          ]
        ],
        "gradeDistribution": [
          1158,
          1924,
          1339,
          2
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0418268143793805
      },
      "ranking": {
        "kendallTau": 0.9191919191919192,
        "spearmanRho": 0.9862725871970864,
        "fullTrecKendallTau": 0.8821548821548821,
        "fullTrecSpearmanRho": 0.9745062333660176
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4999,
        "WatS-LLM-Rerank": 0.621,
        "agg-cocondenser": 0.6576,
        "bm25_splades": 0.6798,
        "cip_run_1": 0.8329,
        "cip_run_2": 0.8329,
        "cip_run_3": 0.8095,
        "cip_run_4": 0.7903,
        "cip_run_5": 0.806,
        "cip_run_6": 0.8134,
        "cip_run_7": 0.7901,
        "naverloo-frgpt4": 0.8641,
        "naverloo-rgpt4": 0.8829,
        "naverloo_bm25_RR": 0.7257,
        "naverloo_bm25_splades_RR": 0.7939,
        "naverloo_fs": 0.7096,
        "naverloo_fs_RR": 0.8138,
        "naverloo_fs_RR_duo": 0.855,
        "slim-pp-0shot-uw": 0.7019,
        "splade_pp_ensemble_distil": 0.6572,
        "splade_pp_self_distil": 0.6842,
        "uogtr_b_grf_e": 0.6905,
        "uogtr_b_grf_e_gb": 0.7327,
        "uogtr_be": 0.6767,
        "uogtr_be_gb": 0.7275,
        "uogtr_dph": 0.4857,
        "uogtr_dph_bo1": 0.4081,
        "uogtr_qr_be": 0.7079,
        "uogtr_qr_be_gb": 0.7441,
        "uogtr_s": 0.6612,
        "uogtr_se": 0.7447,
        "uogtr_se_gb": 0.7509,
        "uot-yahoo_LLMs-blender": 0.4802,
        "uot-yahoo_rankgpt35": 0.5341,
        "uot-yahoo_rankgpt4": 0.561
      }
    },
    "NISTRetrieval-reason2": {
      "labels": {
        "kappa": 0.18381687156755147,
        "nominalAlpha": 0.15930694852663851,
        "binaryKappa": {
          "0|123": 0.2901835091478543,
          "01|23": 0.33973800371422713,
          "012|3": 0.009663191444516288
        },
        "confusion": [
          [
            832,
            848,
            325,
            0
          ],
          [
            256,
            626,
            351,
            0
          ],
          [
            52,
            337,
            419,
            0
          ],
          [
            19,
            110,
            246,
            2
          ]
        ],
        "gradeDistribution": [
          1159,
          1921,
          1341,
          2
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0420529052679177
      },
      "ranking": {
        "kendallTau": 0.9191919191919192,
        "spearmanRho": 0.9862725871970864,
        "fullTrecKendallTau": 0.8821548821548821,
        "fullTrecSpearmanRho": 0.9745062333660176
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4999,
        "WatS-LLM-Rerank": 0.621,
        "agg-cocondenser": 0.6576,
        "bm25_splades": 0.6817,
        "cip_run_1": 0.8329,
        "cip_run_2": 0.8329,
        "cip_run_3": 0.8095,
        "cip_run_4": 0.7903,
        "cip_run_5": 0.806,
        "cip_run_6": 0.8134,
        "cip_run_7": 0.7901,
        "naverloo-frgpt4": 0.8641,
        "naverloo-rgpt4": 0.8829,
        "naverloo_bm25_RR": 0.727,
        "naverloo_bm25_splades_RR": 0.7955,
        "naverloo_fs": 0.7113,
        "naverloo_fs_RR": 0.8152,
        "naverloo_fs_RR_duo": 0.855,
        "slim-pp-0shot-uw": 0.7038,
        "splade_pp_ensemble_distil": 0.6572,
        "splade_pp_self_distil": 0.6859,
        "uogtr_b_grf_e": 0.6933,
        "uogtr_b_grf_e_gb": 0.7355,
        "uogtr_be": 0.6795,
        "uogtr_be_gb": 0.7303,
        "uogtr_dph": 0.4857,
        "uogtr_dph_bo1": 0.4081,
        "uogtr_qr_be": 0.7107,
        "uogtr_qr_be_gb": 0.7469,
        "uogtr_s": 0.6612,
        "uogtr_se": 0.7475,
        "uogtr_se_gb": 0.7537,
        "uot-yahoo_LLMs-blender": 0.4802,
        "uot-yahoo_rankgpt35": 0.5341,
        "uot-yahoo_rankgpt4": 0.561
      }
    },
    "Olz-exp": {
      "labels": {
        "kappa": 0.251860975942796,
        "nominalAlpha": 0.2473170974239738,
        "binaryKappa": {
          "0|123": 0.399740929756314,
          "01|23": 0.3577471573033166,
          "012|3": 0.2935965564119906
        },
        "confusion": [
          [
            1550,
            360,
            66,
            29
          ],
          [
            618,
            417,
            136,
            62
          ],
          [
            206,
            307,
            186,
            109
          ],
          [
            61,
            126,
            68,
            122
          ]
        ],
        "gradeDistribution": [
          2435,
          1210,
          456,
          322
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.6981686638028487
      },
      "ranking": {
        "kendallTau": 0.9158249158249159,
        "spearmanRho": 0.9868328897604707,
        "fullTrecKendallTau": 0.898989898989899,
        "fullTrecSpearmanRho": 0.9815100154083205
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3069,
        "WatS-LLM-Rerank": 0.4045,
        "agg-cocondenser": 0.5017,
        "bm25_splades": 0.4962,
        "cip_run_1": 0.7257,
        "cip_run_2": 0.7257,
        "cip_run_3": 0.6923,
        "cip_run_4": 0.6569,
        "cip_run_5": 0.6712,
        "cip_run_6": 0.698,
        "cip_run_7": 0.6732,
        "naverloo-frgpt4": 0.7766,
        "naverloo-rgpt4": 0.7701,
        "naverloo_bm25_RR": 0.5909,
        "naverloo_bm25_splades_RR": 0.6504,
        "naverloo_fs": 0.5381,
        "naverloo_fs_RR": 0.676,
        "naverloo_fs_RR_duo": 0.7656,
        "slim-pp-0shot-uw": 0.5406,
        "splade_pp_ensemble_distil": 0.4935,
        "splade_pp_self_distil": 0.5139,
        "uogtr_b_grf_e": 0.5482,
        "uogtr_b_grf_e_gb": 0.5854,
        "uogtr_be": 0.553,
        "uogtr_be_gb": 0.6051,
        "uogtr_dph": 0.3066,
        "uogtr_dph_bo1": 0.2384,
        "uogtr_qr_be": 0.5586,
        "uogtr_qr_be_gb": 0.5988,
        "uogtr_s": 0.4966,
        "uogtr_se": 0.6127,
        "uogtr_se_gb": 0.6154,
        "uot-yahoo_LLMs-blender": 0.2924,
        "uot-yahoo_rankgpt35": 0.3547,
        "uot-yahoo_rankgpt4": 0.406
      }
    },
    "Olz-gpt4o": {
      "labels": {
        "kappa": 0.2624717058201475,
        "nominalAlpha": 0.26028917005049956,
        "binaryKappa": {
          "0|123": 0.42279277057515147,
          "01|23": 0.36568333852393003,
          "012|3": 0.3066172093176926
        },
        "confusion": [
          [
            1492,
            392,
            89,
            32
          ],
          [
            560,
            434,
            142,
            97
          ],
          [
            171,
            315,
            204,
            118
          ],
          [
            35,
            133,
            69,
            140
          ]
        ],
        "gradeDistribution": [
          2258,
          1274,
          504,
          387
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.7784309292335518
      },
      "ranking": {
        "kendallTau": 0.9023569023569024,
        "spearmanRho": 0.9829107718167811,
        "fullTrecKendallTau": 0.8922558922558923,
        "fullTrecSpearmanRho": 0.977868048746323
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3434,
        "WatS-LLM-Rerank": 0.424,
        "agg-cocondenser": 0.5257,
        "bm25_splades": 0.5271,
        "cip_run_1": 0.7659,
        "cip_run_2": 0.7659,
        "cip_run_3": 0.7308,
        "cip_run_4": 0.7038,
        "cip_run_5": 0.7101,
        "cip_run_6": 0.7361,
        "cip_run_7": 0.71,
        "naverloo-frgpt4": 0.7919,
        "naverloo-rgpt4": 0.8097,
        "naverloo_bm25_RR": 0.6295,
        "naverloo_bm25_splades_RR": 0.6826,
        "naverloo_fs": 0.5612,
        "naverloo_fs_RR": 0.7089,
        "naverloo_fs_RR_duo": 0.7796,
        "slim-pp-0shot-uw": 0.5608,
        "splade_pp_ensemble_distil": 0.5017,
        "splade_pp_self_distil": 0.5286,
        "uogtr_b_grf_e": 0.5581,
        "uogtr_b_grf_e_gb": 0.5832,
        "uogtr_be": 0.5619,
        "uogtr_be_gb": 0.5956,
        "uogtr_dph": 0.3346,
        "uogtr_dph_bo1": 0.257,
        "uogtr_qr_be": 0.5557,
        "uogtr_qr_be_gb": 0.598,
        "uogtr_s": 0.5028,
        "uogtr_se": 0.5989,
        "uogtr_se_gb": 0.6033,
        "uot-yahoo_LLMs-blender": 0.3131,
        "uot-yahoo_rankgpt35": 0.3712,
        "uot-yahoo_rankgpt4": 0.4348
      }
    },
    "Olz-halfbin": {
      "labels": {
        "kappa": 0.20644450094410624,
        "nominalAlpha": 0.20064798285366048,
        "binaryKappa": {
          "0|123": 0.4007510722449942,
          "01|23": 0.258746775733565,
          "012|3": 0.2448790708533661
        },
        "confusion": [
          [
            1393,
            438,
            72,
            102
          ],
          [
            520,
            459,
            80,
            174
          ],
          [
            151,
            438,
            63,
            156
          ],
          [
            36,
            123,
            62,
            156
          ]
        ],
        "gradeDistribution": [
          2100,
          1458,
          277,
          588
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.8537191951164368
      },
      "ranking": {
        "kendallTau": 0.9217833369467879,
        "spearmanRho": 0.9873240447211002,
        "fullTrecKendallTau": 0.8982341276087313,
        "fullTrecSpearmanRho": 0.9800406214943309
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3858,
        "WatS-LLM-Rerank": 0.4963,
        "agg-cocondenser": 0.5637,
        "bm25_splades": 0.5904,
        "cip_run_1": 0.783,
        "cip_run_2": 0.7845,
        "cip_run_3": 0.7574,
        "cip_run_4": 0.7168,
        "cip_run_5": 0.7427,
        "cip_run_6": 0.7521,
        "cip_run_7": 0.7265,
        "naverloo-frgpt4": 0.8182,
        "naverloo-rgpt4": 0.8166,
        "naverloo_bm25_RR": 0.6613,
        "naverloo_bm25_splades_RR": 0.7441,
        "naverloo_fs": 0.6335,
        "naverloo_fs_RR": 0.7637,
        "naverloo_fs_RR_duo": 0.8079,
        "slim-pp-0shot-uw": 0.6025,
        "splade_pp_ensemble_distil": 0.5699,
        "splade_pp_self_distil": 0.6045,
        "uogtr_b_grf_e": 0.6321,
        "uogtr_b_grf_e_gb": 0.6504,
        "uogtr_be": 0.6136,
        "uogtr_be_gb": 0.6498,
        "uogtr_dph": 0.3926,
        "uogtr_dph_bo1": 0.3087,
        "uogtr_qr_be": 0.6377,
        "uogtr_qr_be_gb": 0.6706,
        "uogtr_s": 0.5717,
        "uogtr_se": 0.6679,
        "uogtr_se_gb": 0.6714,
        "uot-yahoo_LLMs-blender": 0.3758,
        "uot-yahoo_rankgpt35": 0.4233,
        "uot-yahoo_rankgpt4": 0.4684
      }
    },
    "Olz-multiprompt": {
      "labels": {
        "kappa": 0.24453570472208597,
        "nominalAlpha": 0.23971988629050334,
        "binaryKappa": {
          "0|123": 0.37642967781390685,
          "01|23": 0.3934250917237359,
          "012|3": 0.21502902650607575
        },
        "confusion": [
          [
            1184,
            422,
            304,
            95
          ],
          [
            413,
            341,
            333,
            146
          ],
          [
            83,
            176,
            426,
            123
          ],
          [
            33,
            37,
            181,
            126
          ]
        ],
        "gradeDistribution": [
          1713,
          976,
          1244,
          490
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.1155324440425052
      },
      "ranking": {
        "kendallTau": 0.9326599326599326,
        "spearmanRho": 0.9893542512956996,
        "fullTrecKendallTau": 0.9023569023569024,
        "fullTrecSpearmanRho": 0.9806695615632441
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4233,
        "WatS-LLM-Rerank": 0.5449,
        "agg-cocondenser": 0.5939,
        "bm25_splades": 0.6353,
        "cip_run_1": 0.7993,
        "cip_run_2": 0.7993,
        "cip_run_3": 0.7834,
        "cip_run_4": 0.7509,
        "cip_run_5": 0.7692,
        "cip_run_6": 0.7736,
        "cip_run_7": 0.7623,
        "naverloo-frgpt4": 0.8323,
        "naverloo-rgpt4": 0.8384,
        "naverloo_bm25_RR": 0.6764,
        "naverloo_bm25_splades_RR": 0.7545,
        "naverloo_fs": 0.6612,
        "naverloo_fs_RR": 0.7754,
        "naverloo_fs_RR_duo": 0.8234,
        "slim-pp-0shot-uw": 0.6341,
        "splade_pp_ensemble_distil": 0.6117,
        "splade_pp_self_distil": 0.6358,
        "uogtr_b_grf_e": 0.6535,
        "uogtr_b_grf_e_gb": 0.6781,
        "uogtr_be": 0.6335,
        "uogtr_be_gb": 0.6715,
        "uogtr_dph": 0.4222,
        "uogtr_dph_bo1": 0.3401,
        "uogtr_qr_be": 0.6684,
        "uogtr_qr_be_gb": 0.6955,
        "uogtr_s": 0.614,
        "uogtr_se": 0.6901,
        "uogtr_se_gb": 0.6928,
        "uot-yahoo_LLMs-blender": 0.4086,
        "uot-yahoo_rankgpt35": 0.4618,
        "uot-yahoo_rankgpt4": 0.4989
      }
    },
    "Olz-somebin": {
      "labels": {
        "kappa": 0.21093492611754122,
        "nominalAlpha": 0.2025689346214482,
        "binaryKappa": {
          "0|123": 0.3853563197542049,
          "01|23": 0.38826313787795247,
          "012|3": 0.11365579757066445
        },
        "confusion": [
          [
            1377,
            240,
            225,
            163
          ],
          [
            546,
            197,
            272,
            218
          ],
          [
            134,
            132,
            318,
            224
          ],
          [
            45,
            26,
            189,
            117
          ]
        ],
        "gradeDistribution": [
          2102,
          595,
          1004,
          722
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0782274474338684
      },
      "ranking": {
        "kendallTau": 0.9158249158249159,
        "spearmanRho": 0.9865527384787786,
        "fullTrecKendallTau": 0.8922558922558923,
        "fullTrecSpearmanRho": 0.9764672923378624
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3634,
        "WatS-LLM-Rerank": 0.4831,
        "agg-cocondenser": 0.487,
        "bm25_splades": 0.5253,
        "cip_run_1": 0.6448,
        "cip_run_2": 0.6448,
        "cip_run_3": 0.6334,
        "cip_run_4": 0.6122,
        "cip_run_5": 0.6202,
        "cip_run_6": 0.6407,
        "cip_run_7": 0.6241,
        "naverloo-frgpt4": 0.6652,
        "naverloo-rgpt4": 0.6904,
        "naverloo_bm25_RR": 0.5553,
        "naverloo_bm25_splades_RR": 0.6259,
        "naverloo_fs": 0.5545,
        "naverloo_fs_RR": 0.6386,
        "naverloo_fs_RR_duo": 0.6533,
        "slim-pp-0shot-uw": 0.5474,
        "splade_pp_ensemble_distil": 0.5078,
        "splade_pp_self_distil": 0.5318,
        "uogtr_b_grf_e": 0.5468,
        "uogtr_b_grf_e_gb": 0.5573,
        "uogtr_be": 0.5422,
        "uogtr_be_gb": 0.5648,
        "uogtr_dph": 0.3817,
        "uogtr_dph_bo1": 0.3122,
        "uogtr_qr_be": 0.562,
        "uogtr_qr_be_gb": 0.5822,
        "uogtr_s": 0.5077,
        "uogtr_se": 0.5795,
        "uogtr_se_gb": 0.5829,
        "uot-yahoo_LLMs-blender": 0.368,
        "uot-yahoo_rankgpt35": 0.3984,
        "uot-yahoo_rankgpt4": 0.4323
      }
    },
    "RMITIR-GPT4o": {
      "labels": {
        "kappa": 0.2388089753761219,
        "nominalAlpha": 0.20833893084209087,
        "binaryKappa": {
          "0|123": 0.3498826237435765,
          "01|23": 0.39608555696611575,
          "012|3": 0.2580011401750941
        },
        "confusion": [
          [
            1786,
            68,
            126,
            25
          ],
          [
            829,
            138,
            207,
            59
          ],
          [
            347,
            84,
            277,
            100
          ],
          [
            94,
            59,
            120,
            104
          ]
        ],
        "gradeDistribution": [
          3056,
          349,
          730,
          288
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.6043409450599141
      },
      "ranking": {
        "kendallTau": 0.9090909090909091,
        "spearmanRho": 0.9848718307886258,
        "fullTrecKendallTau": 0.9057239057239057,
        "fullTrecSpearmanRho": 0.9837512256618574
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2518,
        "WatS-LLM-Rerank": 0.4077,
        "agg-cocondenser": 0.4724,
        "bm25_splades": 0.4871,
        "cip_run_1": 0.7375,
        "cip_run_2": 0.7375,
        "cip_run_3": 0.7169,
        "cip_run_4": 0.668,
        "cip_run_5": 0.6904,
        "cip_run_6": 0.7133,
        "cip_run_7": 0.6901,
        "naverloo-frgpt4": 0.7982,
        "naverloo-rgpt4": 0.7963,
        "naverloo_bm25_RR": 0.6075,
        "naverloo_bm25_splades_RR": 0.6628,
        "naverloo_fs": 0.5277,
        "naverloo_fs_RR": 0.6885,
        "naverloo_fs_RR_duo": 0.7906,
        "slim-pp-0shot-uw": 0.5321,
        "splade_pp_ensemble_distil": 0.4738,
        "splade_pp_self_distil": 0.4991,
        "uogtr_b_grf_e": 0.5419,
        "uogtr_b_grf_e_gb": 0.5718,
        "uogtr_be": 0.5404,
        "uogtr_be_gb": 0.5787,
        "uogtr_dph": 0.2837,
        "uogtr_dph_bo1": 0.2195,
        "uogtr_qr_be": 0.5387,
        "uogtr_qr_be_gb": 0.5756,
        "uogtr_s": 0.4769,
        "uogtr_se": 0.5818,
        "uogtr_se_gb": 0.5834,
        "uot-yahoo_LLMs-blender": 0.2628,
        "uot-yahoo_rankgpt35": 0.3238,
        "uot-yahoo_rankgpt4": 0.4042
      }
    },
    "RMITIR-llama38b": {
      "labels": {
        "kappa": 0.2006007320040616,
        "nominalAlpha": 0.18771989806041312,
        "binaryKappa": {
          "0|123": 0.32799990092632886,
          "01|23": 0.31941624711615313,
          "012|3": 0.13437705938742883
        },
        "confusion": [
          [
            1536,
            164,
            261,
            44
          ],
          [
            718,
            198,
            271,
            46
          ],
          [
            252,
            181,
            340,
            35
          ],
          [
            70,
            71,
            186,
            50
          ]
        ],
        "gradeDistribution": [
          2576,
          614,
          1058,
          175
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.7359258421885598
      },
      "ranking": {
        "kendallTau": 0.9057239057239057,
        "spearmanRho": 0.982630620535089,
        "fullTrecKendallTau": 0.8686868686868687,
        "fullTrecSpearmanRho": 0.9750665359294018
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3546,
        "WatS-LLM-Rerank": 0.5021,
        "agg-cocondenser": 0.5128,
        "bm25_splades": 0.5238,
        "cip_run_1": 0.7429,
        "cip_run_2": 0.7429,
        "cip_run_3": 0.7214,
        "cip_run_4": 0.6818,
        "cip_run_5": 0.7139,
        "cip_run_6": 0.6872,
        "cip_run_7": 0.69,
        "naverloo-frgpt4": 0.739,
        "naverloo-rgpt4": 0.741,
        "naverloo_bm25_RR": 0.5893,
        "naverloo_bm25_splades_RR": 0.6502,
        "naverloo_fs": 0.5618,
        "naverloo_fs_RR": 0.6735,
        "naverloo_fs_RR_duo": 0.7346,
        "slim-pp-0shot-uw": 0.5458,
        "splade_pp_ensemble_distil": 0.5037,
        "splade_pp_self_distil": 0.5241,
        "uogtr_b_grf_e": 0.5592,
        "uogtr_b_grf_e_gb": 0.5836,
        "uogtr_be": 0.5341,
        "uogtr_be_gb": 0.5682,
        "uogtr_dph": 0.3406,
        "uogtr_dph_bo1": 0.2813,
        "uogtr_qr_be": 0.5727,
        "uogtr_qr_be_gb": 0.5864,
        "uogtr_s": 0.5049,
        "uogtr_se": 0.6086,
        "uogtr_se_gb": 0.6118,
        "uot-yahoo_LLMs-blender": 0.3597,
        "uot-yahoo_rankgpt35": 0.4243,
        "uot-yahoo_rankgpt4": 0.4463
      }
    },
    "RMITIR-llama70B": {
      "labels": {
        "kappa": 0.26545877761770476,
        "nominalAlpha": 0.24305522235667232,
        "binaryKappa": {
          "0|123": 0.4166257332529731,
          "01|23": 0.39164320104826983,
          "012|3": 0.28431635161276253
        },
        "confusion": [
          [
            1436,
            103,
            402,
            62,
            0,
            2
          ],
          [
            542,
            90,
            482,
            119,
            0,
            0
          ],
          [
            138,
            41,
            511,
            118,
            0,
            0
          ],
          [
            38,
            9,
            186,
            144,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0
          ]
        ],
        "gradeDistribution": [
          2154,
          243,
          1581,
          443,
          0,
          2
        ],
        "labelsOutside0to3": 2,
        "averageGrade": 1.0725751752204387
      },
      "ranking": {
        "kendallTau": 0.9393939393939394,
        "spearmanRho": 0.9907550077041603,
        "fullTrecKendallTau": 0.9090909090909091,
        "fullTrecSpearmanRho": 0.9834710743801653
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4099,
        "WatS-LLM-Rerank": 0.546,
        "agg-cocondenser": 0.5891,
        "bm25_splades": 0.6293,
        "cip_run_1": 0.8127,
        "cip_run_2": 0.8127,
        "cip_run_3": 0.7842,
        "cip_run_4": 0.7506,
        "cip_run_5": 0.7752,
        "cip_run_6": 0.7706,
        "cip_run_7": 0.7647,
        "naverloo-frgpt4": 0.8422,
        "naverloo-rgpt4": 0.8631,
        "naverloo_bm25_RR": 0.6793,
        "naverloo_bm25_splades_RR": 0.7554,
        "naverloo_fs": 0.6657,
        "naverloo_fs_RR": 0.7747,
        "naverloo_fs_RR_duo": 0.8277,
        "slim-pp-0shot-uw": 0.6494,
        "splade_pp_ensemble_distil": 0.6083,
        "splade_pp_self_distil": 0.6356,
        "uogtr_b_grf_e": 0.656,
        "uogtr_b_grf_e_gb": 0.6855,
        "uogtr_be": 0.6518,
        "uogtr_be_gb": 0.6853,
        "uogtr_dph": 0.4271,
        "uogtr_dph_bo1": 0.3318,
        "uogtr_qr_be": 0.6639,
        "uogtr_qr_be_gb": 0.6908,
        "uogtr_s": 0.6104,
        "uogtr_se": 0.6897,
        "uogtr_se_gb": 0.6936,
        "uot-yahoo_LLMs-blender": 0.422,
        "uot-yahoo_rankgpt35": 0.4842,
        "uot-yahoo_rankgpt4": 0.5177
      }
    },
    "TREMA-4prompts": {
      "labels": {
        "kappa": 0.1829442621350349,
        "nominalAlpha": 0.1363015475145839,
        "binaryKappa": {
          "0|123": 0.3022027135254199,
          "01|23": 0.26970249563320425,
          "012|3": 0.16639000590011546
        },
        "confusion": [
          [
            783,
            409,
            692,
            121
          ],
          [
            191,
            244,
            682,
            116
          ],
          [
            43,
            72,
            596,
            97
          ],
          [
            10,
            26,
            243,
            98
          ]
        ],
        "gradeDistribution": [
          1027,
          751,
          2213,
          432
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.4634863215012435
      },
      "ranking": {
        "kendallTau": 0.9528619528619529,
        "spearmanRho": 0.9938366718027735,
        "fullTrecKendallTau": 0.9225589225589226,
        "fullTrecSpearmanRho": 0.9865527384787786
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.4956,
        "WatS-LLM-Rerank": 0.5809,
        "agg-cocondenser": 0.6103,
        "bm25_splades": 0.6319,
        "cip_run_1": 0.811,
        "cip_run_2": 0.811,
        "cip_run_3": 0.7943,
        "cip_run_4": 0.7755,
        "cip_run_5": 0.7848,
        "cip_run_6": 0.7904,
        "cip_run_7": 0.7731,
        "naverloo-frgpt4": 0.8226,
        "naverloo-rgpt4": 0.8325,
        "naverloo_bm25_RR": 0.6814,
        "naverloo_bm25_splades_RR": 0.7405,
        "naverloo_fs": 0.6709,
        "naverloo_fs_RR": 0.765,
        "naverloo_fs_RR_duo": 0.8216,
        "slim-pp-0shot-uw": 0.6696,
        "splade_pp_ensemble_distil": 0.6232,
        "splade_pp_self_distil": 0.6345,
        "uogtr_b_grf_e": 0.6725,
        "uogtr_b_grf_e_gb": 0.7011,
        "uogtr_be": 0.653,
        "uogtr_be_gb": 0.7013,
        "uogtr_dph": 0.4729,
        "uogtr_dph_bo1": 0.4114,
        "uogtr_qr_be": 0.6915,
        "uogtr_qr_be_gb": 0.7159,
        "uogtr_s": 0.6265,
        "uogtr_se": 0.7229,
        "uogtr_se_gb": 0.7263,
        "uot-yahoo_LLMs-blender": 0.4679,
        "uot-yahoo_rankgpt35": 0.5191,
        "uot-yahoo_rankgpt4": 0.5416
      }
    },
    "TREMA-CoT": {
      "labels": {
        "kappa": 0.19612426201357802,
        "nominalAlpha": 0.1949634759512936,
        "binaryKappa": {
          "0|123": 0.31812253726117995,
          "01|23": 0.3208128806454236,
          "012|3": 0.18363503936341521
        },
        "confusion": [
          [
            1178,
            443,
            244,
            140
          ],
          [
            465,
            378,
            260,
            130
          ],
          [
            149,
            216,
            278,
            165
          ],
          [
            43,
            85,
            124,
            125
          ]
        ],
        "gradeDistribution": [
          1835,
          1122,
          906,
          560
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.0431833597106037
      },
      "ranking": {
        "kendallTau": 0.9141414141414141,
        "spearmanRho": 0.9858523602745483,
        "fullTrecKendallTau": 0.8838383838383839,
        "fullTrecSpearmanRho": 0.9773077461829388
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.382,
        "WatS-LLM-Rerank": 0.5065,
        "agg-cocondenser": 0.5297,
        "bm25_splades": 0.5468,
        "cip_run_1": 0.7254,
        "cip_run_2": 0.7242,
        "cip_run_3": 0.7082,
        "cip_run_4": 0.6704,
        "cip_run_5": 0.7031,
        "cip_run_6": 0.6962,
        "cip_run_7": 0.6827,
        "naverloo-frgpt4": 0.7246,
        "naverloo-rgpt4": 0.7275,
        "naverloo_bm25_RR": 0.5833,
        "naverloo_bm25_splades_RR": 0.6599,
        "naverloo_fs": 0.5752,
        "naverloo_fs_RR": 0.6666,
        "naverloo_fs_RR_duo": 0.7277,
        "slim-pp-0shot-uw": 0.5419,
        "splade_pp_ensemble_distil": 0.529,
        "splade_pp_self_distil": 0.546,
        "uogtr_b_grf_e": 0.5846,
        "uogtr_b_grf_e_gb": 0.5943,
        "uogtr_be": 0.5653,
        "uogtr_be_gb": 0.5959,
        "uogtr_dph": 0.3754,
        "uogtr_dph_bo1": 0.3262,
        "uogtr_qr_be": 0.6074,
        "uogtr_qr_be_gb": 0.6085,
        "uogtr_s": 0.529,
        "uogtr_se": 0.6252,
        "uogtr_se_gb": 0.6317,
        "uot-yahoo_LLMs-blender": 0.3918,
        "uot-yahoo_rankgpt35": 0.44,
        "uot-yahoo_rankgpt4": 0.4554
      }
    },
    "TREMA-all": {
      "labels": {
        "kappa": 0.14710910408119857,
        "nominalAlpha": 0.13687110547686965,
        "binaryKappa": {
          "0|123": 0.3243630984464598,
          "01|23": 0.29781382630017,
          "012|3": 0.07168187824442102
        },
        "confusion": [
          [
            1449,
            191,
            208,
            157
          ],
          [
            686,
            155,
            188,
            204
          ],
          [
            207,
            186,
            193,
            222
          ],
          [
            57,
            84,
            145,
            91
          ]
        ],
        "gradeDistribution": [
          2399,
          616,
          734,
          674
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.9283291883337101
      },
      "ranking": {
        "kendallTau": 0.9225589225589226,
        "spearmanRho": 0.9896344025773918,
        "fullTrecKendallTau": 0.898989898989899,
        "fullTrecSpearmanRho": 0.9815100154083205
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3641,
        "WatS-LLM-Rerank": 0.4468,
        "agg-cocondenser": 0.5224,
        "bm25_splades": 0.5364,
        "cip_run_1": 0.694,
        "cip_run_2": 0.694,
        "cip_run_3": 0.6797,
        "cip_run_4": 0.6655,
        "cip_run_5": 0.6507,
        "cip_run_6": 0.6905,
        "cip_run_7": 0.6635,
        "naverloo-frgpt4": 0.7081,
        "naverloo-rgpt4": 0.6985,
        "naverloo_bm25_RR": 0.5826,
        "naverloo_bm25_splades_RR": 0.6462,
        "naverloo_fs": 0.5618,
        "naverloo_fs_RR": 0.6735,
        "naverloo_fs_RR_duo": 0.7124,
        "slim-pp-0shot-uw": 0.5731,
        "splade_pp_ensemble_distil": 0.5359,
        "splade_pp_self_distil": 0.555,
        "uogtr_b_grf_e": 0.573,
        "uogtr_b_grf_e_gb": 0.6048,
        "uogtr_be": 0.5576,
        "uogtr_be_gb": 0.6077,
        "uogtr_dph": 0.3236,
        "uogtr_dph_bo1": 0.2817,
        "uogtr_qr_be": 0.5856,
        "uogtr_qr_be_gb": 0.6114,
        "uogtr_s": 0.5395,
        "uogtr_se": 0.6433,
        "uogtr_se_gb": 0.6436,
        "uot-yahoo_LLMs-blender": 0.3108,
        "uot-yahoo_rankgpt35": 0.3506,
        "uot-yahoo_rankgpt4": 0.3874
      }
    },
    "TREMA-direct": {
      "labels": {
        "kappa": 0.1742156467734584,
        "nominalAlpha": 0.12399824003980386,
        "binaryKappa": {
          "0|123": 0.3204677593992557,
          "01|23": 0.3462281530870359,
          "012|3": 0.17627224299746924
        },
        "confusion": [
          [
            1447,
            34,
            125,
            399
          ],
          [
            678,
            25,
            90,
            440
          ],
          [
            224,
            21,
            97,
            466
          ],
          [
            55,
            7,
            30,
            285
          ]
        ],
        "gradeDistribution": [
          2404,
          87,
          342,
          1590
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.2527696133845807
      },
      "ranking": {
        "kendallTau": 0.9191919191919192,
        "spearmanRho": 0.9871130410421628,
        "fullTrecKendallTau": 0.9023569023569024,
        "fullTrecSpearmanRho": 0.9812298641266284
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3728,
        "WatS-LLM-Rerank": 0.533,
        "agg-cocondenser": 0.6249,
        "bm25_splades": 0.6203,
        "cip_run_1": 0.8154,
        "cip_run_2": 0.8154,
        "cip_run_3": 0.8129,
        "cip_run_4": 0.7944,
        "cip_run_5": 0.7792,
        "cip_run_6": 0.8381,
        "cip_run_7": 0.7959,
        "naverloo-frgpt4": 0.8416,
        "naverloo-rgpt4": 0.8353,
        "naverloo_bm25_RR": 0.6971,
        "naverloo_bm25_splades_RR": 0.7666,
        "naverloo_fs": 0.6582,
        "naverloo_fs_RR": 0.7929,
        "naverloo_fs_RR_duo": 0.8431,
        "slim-pp-0shot-uw": 0.6625,
        "splade_pp_ensemble_distil": 0.6328,
        "splade_pp_self_distil": 0.6307,
        "uogtr_b_grf_e": 0.6729,
        "uogtr_b_grf_e_gb": 0.7078,
        "uogtr_be": 0.6543,
        "uogtr_be_gb": 0.706,
        "uogtr_dph": 0.3325,
        "uogtr_dph_bo1": 0.2883,
        "uogtr_qr_be": 0.6778,
        "uogtr_qr_be_gb": 0.7062,
        "uogtr_s": 0.6313,
        "uogtr_se": 0.7494,
        "uogtr_se_gb": 0.7512,
        "uot-yahoo_LLMs-blender": 0.3455,
        "uot-yahoo_rankgpt35": 0.407,
        "uot-yahoo_rankgpt4": 0.4554
      }
    },
    "TREMA-naiveBdecompose": {
      "labels": {
        "kappa": 0.17410234518367085,
        "nominalAlpha": 0.15838412505333033,
        "binaryKappa": {
          "0|123": 0.3085358823100339,
          "01|23": 0.29155296940214304,
          "012|3": 0.015310645976462561
        },
        "confusion": [
          [
            1538,
            182,
            277,
            8
          ],
          [
            721,
            205,
            297,
            10
          ],
          [
            282,
            192,
            324,
            10
          ],
          [
            86,
            66,
            219,
            6
          ]
        ],
        "gradeDistribution": [
          2627,
          645,
          1117,
          34
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.6739769387293693
      },
      "ranking": {
        "kendallTau": 0.9285116824719469,
        "spearmanRho": 0.9884445713713724,
        "fullTrecKendallTau": 0.8915057820835722,
        "fullTrecSpearmanRho": 0.9800406214943309
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3601,
        "WatS-LLM-Rerank": 0.4818,
        "agg-cocondenser": 0.4947,
        "bm25_splades": 0.5174,
        "cip_run_1": 0.686,
        "cip_run_2": 0.6867,
        "cip_run_3": 0.6795,
        "cip_run_4": 0.6457,
        "cip_run_5": 0.6717,
        "cip_run_6": 0.6619,
        "cip_run_7": 0.6564,
        "naverloo-frgpt4": 0.6923,
        "naverloo-rgpt4": 0.6948,
        "naverloo_bm25_RR": 0.5781,
        "naverloo_bm25_splades_RR": 0.641,
        "naverloo_fs": 0.5485,
        "naverloo_fs_RR": 0.6506,
        "naverloo_fs_RR_duo": 0.6842,
        "slim-pp-0shot-uw": 0.5096,
        "splade_pp_ensemble_distil": 0.4851,
        "splade_pp_self_distil": 0.507,
        "uogtr_b_grf_e": 0.551,
        "uogtr_b_grf_e_gb": 0.5676,
        "uogtr_be": 0.5202,
        "uogtr_be_gb": 0.5549,
        "uogtr_dph": 0.3287,
        "uogtr_dph_bo1": 0.2936,
        "uogtr_qr_be": 0.5645,
        "uogtr_qr_be_gb": 0.5925,
        "uogtr_s": 0.4858,
        "uogtr_se": 0.5875,
        "uogtr_se_gb": 0.5945,
        "uot-yahoo_LLMs-blender": 0.3374,
        "uot-yahoo_rankgpt35": 0.3883,
        "uot-yahoo_rankgpt4": 0.4235
      }
    },
    "TREMA-nuggets": {
      "labels": {
        "kappa": 0.060412018764851534,
        "nominalAlpha": 0.057192600137385474,
        "binaryKappa": {
          "0|123": 0.1504847963887998,
          "01|23": 0.0992379101001354,
          "012|3": -0.007705446750397084
        },
        "confusion": [
          [
            1130,
            350,
            407,
            118
          ],
          [
            593,
            229,
            283,
            128
          ],
          [
            284,
            211,
            228,
            85
          ],
          [
            120,
            103,
            126,
            28
          ]
        ],
        "gradeDistribution": [
          2127,
          893,
          1044,
          359
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.917476825683925
      },
      "ranking": {
        "kendallTau": 0.8787878787878788,
        "spearmanRho": 0.977868048746323,
        "fullTrecKendallTau": 0.8888888888888888,
        "fullTrecSpearmanRho": 0.9775878974646309
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2919,
        "WatS-LLM-Rerank": 0.338,
        "agg-cocondenser": 0.3362,
        "bm25_splades": 0.3575,
        "cip_run_1": 0.4381,
        "cip_run_2": 0.4381,
        "cip_run_3": 0.433,
        "cip_run_4": 0.4161,
        "cip_run_5": 0.4123,
        "cip_run_6": 0.4317,
        "cip_run_7": 0.4225,
        "naverloo-frgpt4": 0.4328,
        "naverloo-rgpt4": 0.4393,
        "naverloo_bm25_RR": 0.3927,
        "naverloo_bm25_splades_RR": 0.3985,
        "naverloo_fs": 0.3722,
        "naverloo_fs_RR": 0.4074,
        "naverloo_fs_RR_duo": 0.4276,
        "slim-pp-0shot-uw": 0.3926,
        "splade_pp_ensemble_distil": 0.3615,
        "splade_pp_self_distil": 0.3574,
        "uogtr_b_grf_e": 0.3875,
        "uogtr_b_grf_e_gb": 0.3986,
        "uogtr_be": 0.3921,
        "uogtr_be_gb": 0.4058,
        "uogtr_dph": 0.3163,
        "uogtr_dph_bo1": 0.2879,
        "uogtr_qr_be": 0.3961,
        "uogtr_qr_be_gb": 0.3953,
        "uogtr_s": 0.3608,
        "uogtr_se": 0.3935,
        "uogtr_se_gb": 0.3959,
        "uot-yahoo_LLMs-blender": 0.3117,
        "uot-yahoo_rankgpt35": 0.3139,
        "uot-yahoo_rankgpt4": 0.3211
      }
    },
    "TREMA-other": {
      "labels": {
        "kappa": 0.14076384195997524,
        "nominalAlpha": 0.10709481824067602,
        "binaryKappa": {
          "0|123": 0.27404550615068657,
          "01|23": 0.2015087312375371,
          "012|3": 0.14109978808014134
        },
        "confusion": [
          [
            883,
            391,
            662,
            69
          ],
          [
            261,
            240,
            664,
            68
          ],
          [
            118,
            135,
            472,
            83
          ],
          [
            43,
            43,
            223,
            68
          ]
        ],
        "gradeDistribution": [
          1305,
          809,
          2021,
          288
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.292109427990052
      },
      "ranking": {
        "kendallTau": 0.8619528619528619,
        "spearmanRho": 0.9613391231264883,
        "fullTrecKendallTau": 0.8249158249158249,
        "fullTrecSpearmanRho": 0.9478918616052668
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.5002,
        "WatS-LLM-Rerank": 0.5631,
        "agg-cocondenser": 0.665,
        "bm25_splades": 0.6429,
        "cip_run_1": 0.7658,
        "cip_run_2": 0.7658,
        "cip_run_3": 0.7467,
        "cip_run_4": 0.7429,
        "cip_run_5": 0.7212,
        "cip_run_6": 0.7687,
        "cip_run_7": 0.7253,
        "naverloo-frgpt4": 0.775,
        "naverloo-rgpt4": 0.7925,
        "naverloo_bm25_RR": 0.6653,
        "naverloo_bm25_splades_RR": 0.7418,
        "naverloo_fs": 0.704,
        "naverloo_fs_RR": 0.7647,
        "naverloo_fs_RR_duo": 0.7596,
        "slim-pp-0shot-uw": 0.6707,
        "splade_pp_ensemble_distil": 0.6391,
        "splade_pp_self_distil": 0.6572,
        "uogtr_b_grf_e": 0.6518,
        "uogtr_b_grf_e_gb": 0.7005,
        "uogtr_be": 0.6326,
        "uogtr_be_gb": 0.6864,
        "uogtr_dph": 0.4985,
        "uogtr_dph_bo1": 0.4094,
        "uogtr_qr_be": 0.6647,
        "uogtr_qr_be_gb": 0.7027,
        "uogtr_s": 0.6407,
        "uogtr_se": 0.6982,
        "uogtr_se_gb": 0.7003,
        "uot-yahoo_LLMs-blender": 0.5059,
        "uot-yahoo_rankgpt35": 0.5546,
        "uot-yahoo_rankgpt4": 0.5697
      }
    },
    "TREMA-questions": {
      "labels": {
        "kappa": 0.1137256466512417,
        "nominalAlpha": 0.08837551064094795,
        "binaryKappa": {
          "0|123": 0.26357684465481407,
          "01|23": 0.28757371829764095,
          "012|3": 0.04414383500631685
        },
        "confusion": [
          [
            1405,
            116,
            218,
            266
          ],
          [
            684,
            59,
            226,
            264
          ],
          [
            259,
            58,
            175,
            316
          ],
          [
            102,
            20,
            148,
            107
          ]
        ],
        "gradeDistribution": [
          2450,
          253,
          767,
          953
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 1.050418268143794
      },
      "ranking": {
        "kendallTau": 0.9225589225589226,
        "spearmanRho": 0.9882336461689312,
        "fullTrecKendallTau": 0.898989898989899,
        "fullTrecSpearmanRho": 0.9815100154083205
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3454,
        "WatS-LLM-Rerank": 0.3735,
        "agg-cocondenser": 0.441,
        "bm25_splades": 0.4364,
        "cip_run_1": 0.5906,
        "cip_run_2": 0.5906,
        "cip_run_3": 0.5727,
        "cip_run_4": 0.5503,
        "cip_run_5": 0.548,
        "cip_run_6": 0.5674,
        "cip_run_7": 0.5639,
        "naverloo-frgpt4": 0.5976,
        "naverloo-rgpt4": 0.6027,
        "naverloo_bm25_RR": 0.4994,
        "naverloo_bm25_splades_RR": 0.5455,
        "naverloo_fs": 0.4702,
        "naverloo_fs_RR": 0.5587,
        "naverloo_fs_RR_duo": 0.5876,
        "slim-pp-0shot-uw": 0.489,
        "splade_pp_ensemble_distil": 0.4621,
        "splade_pp_self_distil": 0.475,
        "uogtr_b_grf_e": 0.4802,
        "uogtr_b_grf_e_gb": 0.5078,
        "uogtr_be": 0.4698,
        "uogtr_be_gb": 0.5164,
        "uogtr_dph": 0.2986,
        "uogtr_dph_bo1": 0.2733,
        "uogtr_qr_be": 0.5047,
        "uogtr_qr_be_gb": 0.5255,
        "uogtr_s": 0.4588,
        "uogtr_se": 0.5398,
        "uogtr_se_gb": 0.5407,
        "uot-yahoo_LLMs-blender": 0.2996,
        "uot-yahoo_rankgpt35": 0.3121,
        "uot-yahoo_rankgpt4": 0.3582
      }
    },
    "TREMA-rubric0": {
      "labels": {
        "kappa": 0.07793337186293804,
        "nominalAlpha": 0.03751090001488866,
        "binaryKappa": {
          "0|123": 0.17135435182334724,
          "01|23": 0.03079197018074922,
          "012|3": 0.03688076324498208
        },
        "confusion": [
          [
            1612,
            371,
            0,
            22
          ],
          [
            868,
            340,
            0,
            25
          ],
          [
            478,
            303,
            0,
            27
          ],
          [
            164,
            197,
            0,
            16
          ]
        ],
        "gradeDistribution": [
          3122,
          1211,
          0,
          90
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.3348406059235813
      },
      "ranking": {
        "kendallTau": 0.8552188552188552,
        "spearmanRho": 0.9669421487603306,
        "fullTrecKendallTau": 0.8451178451178452,
        "fullTrecSpearmanRho": 0.9633001820983331
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2531,
        "WatS-LLM-Rerank": 0.3025,
        "agg-cocondenser": 0.3736,
        "bm25_splades": 0.3851,
        "cip_run_1": 0.5281,
        "cip_run_2": 0.5281,
        "cip_run_3": 0.5013,
        "cip_run_4": 0.4804,
        "cip_run_5": 0.4849,
        "cip_run_6": 0.5035,
        "cip_run_7": 0.4902,
        "naverloo-frgpt4": 0.5257,
        "naverloo-rgpt4": 0.5314,
        "naverloo_bm25_RR": 0.4253,
        "naverloo_bm25_splades_RR": 0.4773,
        "naverloo_fs": 0.4031,
        "naverloo_fs_RR": 0.491,
        "naverloo_fs_RR_duo": 0.5301,
        "slim-pp-0shot-uw": 0.3913,
        "splade_pp_ensemble_distil": 0.4083,
        "splade_pp_self_distil": 0.4007,
        "uogtr_b_grf_e": 0.3932,
        "uogtr_b_grf_e_gb": 0.4185,
        "uogtr_be": 0.3943,
        "uogtr_be_gb": 0.4338,
        "uogtr_dph": 0.2586,
        "uogtr_dph_bo1": 0.2321,
        "uogtr_qr_be": 0.4028,
        "uogtr_qr_be_gb": 0.4236,
        "uogtr_s": 0.4091,
        "uogtr_se": 0.4694,
        "uogtr_se_gb": 0.4687,
        "uot-yahoo_LLMs-blender": 0.2303,
        "uot-yahoo_rankgpt35": 0.2592,
        "uot-yahoo_rankgpt4": 0.2969
      }
    },
    "TREMA-sumdecompose": {
      "labels": {
        "kappa": 0.20884347071761325,
        "nominalAlpha": 0.18836923340507516,
        "binaryKappa": {
          "0|123": 0.32280401520016694,
          "01|23": 0.3512136477468143,
          "012|3": 0.20467884987625784
        },
        "confusion": [
          [
            1503,
            73,
            273,
            156
          ],
          [
            707,
            89,
            284,
            153
          ],
          [
            241,
            73,
            342,
            152
          ],
          [
            67,
            19,
            150,
            141
          ]
        ],
        "gradeDistribution": [
          2518,
          254,
          1049,
          602
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.9400859145376441
      },
      "ranking": {
        "kendallTau": 0.9386042007596855,
        "spearmanRho": 0.9904054930093488,
        "fullTrecKendallTau": 0.9015983003713108,
        "fullTrecSpearmanRho": 0.9814412798071711
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3844,
        "WatS-LLM-Rerank": 0.5307,
        "agg-cocondenser": 0.5353,
        "bm25_splades": 0.5674,
        "cip_run_1": 0.7576,
        "cip_run_2": 0.757,
        "cip_run_3": 0.755,
        "cip_run_4": 0.7135,
        "cip_run_5": 0.7437,
        "cip_run_6": 0.7226,
        "cip_run_7": 0.7222,
        "naverloo-frgpt4": 0.7686,
        "naverloo-rgpt4": 0.7832,
        "naverloo_bm25_RR": 0.6271,
        "naverloo_bm25_splades_RR": 0.6937,
        "naverloo_fs": 0.6041,
        "naverloo_fs_RR": 0.7114,
        "naverloo_fs_RR_duo": 0.7656,
        "slim-pp-0shot-uw": 0.6001,
        "splade_pp_ensemble_distil": 0.5355,
        "splade_pp_self_distil": 0.5553,
        "uogtr_b_grf_e": 0.6057,
        "uogtr_b_grf_e_gb": 0.6245,
        "uogtr_be": 0.5871,
        "uogtr_be_gb": 0.6204,
        "uogtr_dph": 0.3823,
        "uogtr_dph_bo1": 0.3237,
        "uogtr_qr_be": 0.6215,
        "uogtr_qr_be_gb": 0.637,
        "uogtr_s": 0.5341,
        "uogtr_se": 0.6529,
        "uogtr_se_gb": 0.658,
        "uot-yahoo_LLMs-blender": 0.3947,
        "uot-yahoo_rankgpt35": 0.4544,
        "uot-yahoo_rankgpt4": 0.4881
      }
    },
    "h2oloo-fewself": {
      "labels": {
        "kappa": 0.27743420616147163,
        "nominalAlpha": 0.2689081791654121,
        "binaryKappa": {
          "0|123": 0.4171685009190223,
          "01|23": 0.42799892823511926,
          "012|3": 0.3048117461200135
        },
        "confusion": [
          [
            1586,
            229,
            98,
            92
          ],
          [
            602,
            302,
            183,
            146
          ],
          [
            225,
            143,
            212,
            228
          ],
          [
            57,
            58,
            64,
            198
          ]
        ],
        "gradeDistribution": [
          2470,
          732,
          557,
          664
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.8677368302057427
      },
      "ranking": {
        "kendallTau": 0.9217833369467879,
        "spearmanRho": 0.9870439130585322,
        "fullTrecKendallTau": 0.9049624731338903,
        "fullTrecSpearmanRho": 0.9817214114697392
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3058,
        "WatS-LLM-Rerank": 0.4427,
        "agg-cocondenser": 0.5253,
        "bm25_splades": 0.5236,
        "cip_run_1": 0.7656,
        "cip_run_2": 0.7678,
        "cip_run_3": 0.7348,
        "cip_run_4": 0.696,
        "cip_run_5": 0.7109,
        "cip_run_6": 0.7277,
        "cip_run_7": 0.7122,
        "naverloo-frgpt4": 0.8064,
        "naverloo-rgpt4": 0.8066,
        "naverloo_bm25_RR": 0.6147,
        "naverloo_bm25_splades_RR": 0.7054,
        "naverloo_fs": 0.5724,
        "naverloo_fs_RR": 0.7312,
        "naverloo_fs_RR_duo": 0.8052,
        "slim-pp-0shot-uw": 0.5607,
        "splade_pp_ensemble_distil": 0.5232,
        "splade_pp_self_distil": 0.5288,
        "uogtr_b_grf_e": 0.5877,
        "uogtr_b_grf_e_gb": 0.6127,
        "uogtr_be": 0.5775,
        "uogtr_be_gb": 0.6195,
        "uogtr_dph": 0.2969,
        "uogtr_dph_bo1": 0.2383,
        "uogtr_qr_be": 0.5872,
        "uogtr_qr_be_gb": 0.6296,
        "uogtr_s": 0.5276,
        "uogtr_se": 0.6339,
        "uogtr_se_gb": 0.6379,
        "uot-yahoo_LLMs-blender": 0.3067,
        "uot-yahoo_rankgpt35": 0.367,
        "uot-yahoo_rankgpt4": 0.4322
      }
    },
    "h2oloo-zeroshot1": {
      "labels": {
        "kappa": 0.2817186667123342,
        "nominalAlpha": 0.2792248140124607,
        "binaryKappa": {
          "0|123": 0.4093619206041034,
          "01|23": 0.3900657106323932,
          "012|3": 0.30841904365785006
        },
        "confusion": [
          [
            1522,
            373,
            85,
            25
          ],
          [
            576,
            456,
            160,
            41
          ],
          [
            199,
            276,
            262,
            71
          ],
          [
            56,
            120,
            90,
            111
          ]
        ],
        "gradeDistribution": [
          2353,
          1225,
          597,
          248
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.7151254804431382
      },
      "ranking": {
        "kendallTau": 0.9351309131468043,
        "spearmanRho": 0.9884429526242642,
        "fullTrecKendallTau": 0.8980626607337778,
        "fullTrecSpearmanRho": 0.9811585090958541
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3153,
        "WatS-LLM-Rerank": 0.4275,
        "agg-cocondenser": 0.5054,
        "bm25_splades": 0.5264,
        "cip_run_1": 0.7537,
        "cip_run_2": 0.7537,
        "cip_run_3": 0.7204,
        "cip_run_4": 0.6929,
        "cip_run_5": 0.6885,
        "cip_run_6": 0.7196,
        "cip_run_7": 0.6986,
        "naverloo-frgpt4": 0.7787,
        "naverloo-rgpt4": 0.7836,
        "naverloo_bm25_RR": 0.6071,
        "naverloo_bm25_splades_RR": 0.6894,
        "naverloo_fs": 0.5684,
        "naverloo_fs_RR": 0.7178,
        "naverloo_fs_RR_duo": 0.773,
        "slim-pp-0shot-uw": 0.5454,
        "splade_pp_ensemble_distil": 0.5129,
        "splade_pp_self_distil": 0.5379,
        "uogtr_b_grf_e": 0.5513,
        "uogtr_b_grf_e_gb": 0.5924,
        "uogtr_be": 0.557,
        "uogtr_be_gb": 0.5978,
        "uogtr_dph": 0.3012,
        "uogtr_dph_bo1": 0.2426,
        "uogtr_qr_be": 0.5634,
        "uogtr_qr_be_gb": 0.6071,
        "uogtr_s": 0.5168,
        "uogtr_se": 0.6099,
        "uogtr_se_gb": 0.6124,
        "uot-yahoo_LLMs-blender": 0.3017,
        "uot-yahoo_rankgpt35": 0.3608,
        "uot-yahoo_rankgpt4": 0.4136
      }
    },
    "h2oloo-zeroshot2": {
      "labels": {
        "kappa": 0.2589269983578159,
        "nominalAlpha": 0.2408342119044744,
        "binaryKappa": {
          "0|123": 0.3690883778411417,
          "01|23": 0.3277667977303257,
          "012|3": 0.2788775997560159
        },
        "confusion": [
          [
            1744,
            155,
            74,
            31,
            0,
            0,
            0,
            0,
            0,
            0,
            1
          ],
          [
            729,
            324,
            134,
            46,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            326,
            214,
            194,
            74,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            121,
            78,
            74,
            104,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ],
          [
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0,
            0
          ]
        ],
        "gradeDistribution": [
          2920,
          771,
          476,
          255,
          0,
          0,
          0,
          0,
          0,
          0,
          1
        ],
        "labelsOutside0to3": 1,
        "averageGrade": 0.5647750395659055
      },
      "ranking": {
        "kendallTau": 0.8703703703703703,
        "spearmanRho": 0.9725451743941729,
        "fullTrecKendallTau": 0.8468013468013468,
        "fullTrecSpearmanRho": 0.9665219218377924
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2726,
        "WatS-LLM-Rerank": 0.3633,
        "agg-cocondenser": 0.4449,
        "bm25_splades": 0.4191,
        "cip_run_1": 0.6519,
        "cip_run_2": 0.6518,
        "cip_run_3": 0.6001,
        "cip_run_4": 0.5804,
        "cip_run_5": 0.5871,
        "cip_run_6": 0.5806,
        "cip_run_7": 0.5825,
        "naverloo-frgpt4": 0.6647,
        "naverloo-rgpt4": 0.671,
        "naverloo_bm25_RR": 0.527,
        "naverloo_bm25_splades_RR": 0.6058,
        "naverloo_fs": 0.4621,
        "naverloo_fs_RR": 0.6201,
        "naverloo_fs_RR_duo": 0.6534,
        "slim-pp-0shot-uw": 0.4871,
        "splade_pp_ensemble_distil": 0.4201,
        "splade_pp_self_distil": 0.4291,
        "uogtr_b_grf_e": 0.4725,
        "uogtr_b_grf_e_gb": 0.506,
        "uogtr_be": 0.4745,
        "uogtr_be_gb": 0.5172,
        "uogtr_dph": 0.2339,
        "uogtr_dph_bo1": 0.1922,
        "uogtr_qr_be": 0.4735,
        "uogtr_qr_be_gb": 0.5195,
        "uogtr_s": 0.4216,
        "uogtr_se": 0.5224,
        "uogtr_se_gb": 0.5224,
        "uot-yahoo_LLMs-blender": 0.2627,
        "uot-yahoo_rankgpt35": 0.3002,
        "uot-yahoo_rankgpt4": 0.3474
      }
    },
    "prophet-setting1": {
      "labels": {
        "kappa": 0.18229868997736845,
        "nominalAlpha": 0.1758683737215211,
        "binaryKappa": {
          "0|123": 0.3501560573045211,
          "01|23": 0.2902720412133179,
          "012|3": 0.16772057145436353
        },
        "confusion": [
          [
            1528,
            284,
            116,
            77
          ],
          [
            657,
            255,
            208,
            113
          ],
          [
            240,
            267,
            182,
            119
          ],
          [
            81,
            79,
            123,
            94
          ]
        ],
        "gradeDistribution": [
          2506,
          885,
          629,
          403
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.7578566583766674
      },
      "ranking": {
        "kendallTau": 0.9184191641842084,
        "spearmanRho": 0.9873240447211002,
        "fullTrecKendallTau": 0.8881416093209927,
        "fullTrecSpearmanRho": 0.9803207531568989
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2411,
        "WatS-LLM-Rerank": 0.3607,
        "agg-cocondenser": 0.4597,
        "bm25_splades": 0.4626,
        "cip_run_1": 0.6572,
        "cip_run_2": 0.6576,
        "cip_run_3": 0.6312,
        "cip_run_4": 0.6179,
        "cip_run_5": 0.6093,
        "cip_run_6": 0.6429,
        "cip_run_7": 0.6144,
        "naverloo-frgpt4": 0.6863,
        "naverloo-rgpt4": 0.6761,
        "naverloo_bm25_RR": 0.5067,
        "naverloo_bm25_splades_RR": 0.613,
        "naverloo_fs": 0.493,
        "naverloo_fs_RR": 0.6313,
        "naverloo_fs_RR_duo": 0.6839,
        "slim-pp-0shot-uw": 0.4721,
        "splade_pp_ensemble_distil": 0.4534,
        "splade_pp_self_distil": 0.471,
        "uogtr_b_grf_e": 0.4927,
        "uogtr_b_grf_e_gb": 0.519,
        "uogtr_be": 0.4909,
        "uogtr_be_gb": 0.5242,
        "uogtr_dph": 0.2389,
        "uogtr_dph_bo1": 0.1977,
        "uogtr_qr_be": 0.4845,
        "uogtr_qr_be_gb": 0.5331,
        "uogtr_s": 0.4561,
        "uogtr_se": 0.5537,
        "uogtr_se_gb": 0.5548,
        "uot-yahoo_LLMs-blender": 0.2537,
        "uot-yahoo_rankgpt35": 0.2952,
        "uot-yahoo_rankgpt4": 0.3272
      }
    },
    "prophet-setting2": {
      "labels": {
        "kappa": 0.1757445897567502,
        "nominalAlpha": 0.15666398987968344,
        "binaryKappa": {
          "0|123": 0.31021428910582965,
          "01|23": 0.23815865902052424,
          "012|3": 0.028386374725119234
        },
        "confusion": [
          [
            1669,
            208,
            125,
            3
          ],
          [
            740,
            310,
            180,
            3
          ],
          [
            399,
            234,
            171,
            4
          ],
          [
            95,
            100,
            175,
            7
          ]
        ],
        "gradeDistribution": [
          2903,
          852,
          651,
          17
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.49853040922450825
      },
      "ranking": {
        "kendallTau": 0.9587892373351626,
        "spearmanRho": 0.9937670729601654,
        "fullTrecKendallTau": 0.9285116824719469,
        "fullTrecSpearmanRho": 0.9873240447211002
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3079,
        "WatS-LLM-Rerank": 0.3973,
        "agg-cocondenser": 0.4758,
        "bm25_splades": 0.5144,
        "cip_run_1": 0.704,
        "cip_run_2": 0.7032,
        "cip_run_3": 0.6881,
        "cip_run_4": 0.6666,
        "cip_run_5": 0.6732,
        "cip_run_6": 0.6845,
        "cip_run_7": 0.6688,
        "naverloo-frgpt4": 0.7319,
        "naverloo-rgpt4": 0.7349,
        "naverloo_bm25_RR": 0.584,
        "naverloo_bm25_splades_RR": 0.6619,
        "naverloo_fs": 0.5637,
        "naverloo_fs_RR": 0.6704,
        "naverloo_fs_RR_duo": 0.7198,
        "slim-pp-0shot-uw": 0.5636,
        "splade_pp_ensemble_distil": 0.4981,
        "splade_pp_self_distil": 0.5218,
        "uogtr_b_grf_e": 0.5595,
        "uogtr_b_grf_e_gb": 0.6107,
        "uogtr_be": 0.548,
        "uogtr_be_gb": 0.6011,
        "uogtr_dph": 0.3005,
        "uogtr_dph_bo1": 0.2121,
        "uogtr_qr_be": 0.562,
        "uogtr_qr_be_gb": 0.6177,
        "uogtr_s": 0.4984,
        "uogtr_se": 0.596,
        "uogtr_se_gb": 0.597,
        "uot-yahoo_LLMs-blender": 0.2916,
        "uot-yahoo_rankgpt35": 0.3576,
        "uot-yahoo_rankgpt4": 0.4195
      }
    },
    "prophet-setting4": {
      "labels": {
        "kappa": 0.14711407170502935,
        "nominalAlpha": 0.09970729535645684,
        "binaryKappa": {
          "0|123": 0.23748681424056164,
          "01|23": 0.14094635315899326,
          "012|3": 0.03707037535090618
        },
        "confusion": [
          [
            1798,
            169,
            36,
            2
          ],
          [
            867,
            277,
            83,
            6
          ],
          [
            507,
            206,
            92,
            3
          ],
          [
            187,
            111,
            70,
            9
          ]
        ],
        "gradeDistribution": [
          3359,
          763,
          281,
          20
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.3131358806240109
      },
      "ranking": {
        "kendallTau": 0.8814132637958337,
        "spearmanRho": 0.9719168032798574,
        "fullTrecKendallTau": 0.851135708932618,
        "fullTrecSpearmanRho": 0.959030746801727
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2378,
        "WatS-LLM-Rerank": 0.2991,
        "agg-cocondenser": 0.4393,
        "bm25_splades": 0.4644,
        "cip_run_1": 0.5787,
        "cip_run_2": 0.5808,
        "cip_run_3": 0.5772,
        "cip_run_4": 0.5556,
        "cip_run_5": 0.5828,
        "cip_run_6": 0.6048,
        "cip_run_7": 0.5605,
        "naverloo-frgpt4": 0.6497,
        "naverloo-rgpt4": 0.6547,
        "naverloo_bm25_RR": 0.4997,
        "naverloo_bm25_splades_RR": 0.5893,
        "naverloo_fs": 0.5062,
        "naverloo_fs_RR": 0.611,
        "naverloo_fs_RR_duo": 0.6386,
        "slim-pp-0shot-uw": 0.4967,
        "splade_pp_ensemble_distil": 0.4625,
        "splade_pp_self_distil": 0.4718,
        "uogtr_b_grf_e": 0.4847,
        "uogtr_b_grf_e_gb": 0.521,
        "uogtr_be": 0.4803,
        "uogtr_be_gb": 0.5169,
        "uogtr_dph": 0.2502,
        "uogtr_dph_bo1": 0.1687,
        "uogtr_qr_be": 0.5015,
        "uogtr_qr_be_gb": 0.5407,
        "uogtr_s": 0.463,
        "uogtr_se": 0.5489,
        "uogtr_se_gb": 0.5538,
        "uot-yahoo_LLMs-blender": 0.2251,
        "uot-yahoo_rankgpt35": 0.2719,
        "uot-yahoo_rankgpt4": 0.3075
      }
    },
    "willia-umbrela1": {
      "labels": {
        "kappa": 0.2862720172192001,
        "nominalAlpha": 0.2840374462627382,
        "binaryKappa": {
          "0|123": 0.41611273667755927,
          "01|23": 0.3985300848089526,
          "012|3": 0.31454306228623025
        },
        "confusion": [
          [
            1521,
            369,
            88,
            27
          ],
          [
            579,
            457,
            157,
            40
          ],
          [
            189,
            280,
            270,
            69
          ],
          [
            46,
            125,
            93,
            113
          ]
        ],
        "gradeDistribution": [
          2335,
          1231,
          608,
          249
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.722134297987791
      },
      "ranking": {
        "kendallTau": 0.9191919191919192,
        "spearmanRho": 0.9859924359153943,
        "fullTrecKendallTau": 0.8956228956228957,
        "fullTrecSpearmanRho": 0.9806695615632441
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.3111,
        "WatS-LLM-Rerank": 0.4178,
        "agg-cocondenser": 0.5122,
        "bm25_splades": 0.5232,
        "cip_run_1": 0.7763,
        "cip_run_2": 0.7763,
        "cip_run_3": 0.7259,
        "cip_run_4": 0.6994,
        "cip_run_5": 0.6955,
        "cip_run_6": 0.7252,
        "cip_run_7": 0.7072,
        "naverloo-frgpt4": 0.794,
        "naverloo-rgpt4": 0.7891,
        "naverloo_bm25_RR": 0.6168,
        "naverloo_bm25_splades_RR": 0.6967,
        "naverloo_fs": 0.5704,
        "naverloo_fs_RR": 0.724,
        "naverloo_fs_RR_duo": 0.791,
        "slim-pp-0shot-uw": 0.5524,
        "splade_pp_ensemble_distil": 0.5147,
        "splade_pp_self_distil": 0.5335,
        "uogtr_b_grf_e": 0.5556,
        "uogtr_b_grf_e_gb": 0.5986,
        "uogtr_be": 0.5608,
        "uogtr_be_gb": 0.6016,
        "uogtr_dph": 0.3216,
        "uogtr_dph_bo1": 0.2552,
        "uogtr_qr_be": 0.5702,
        "uogtr_qr_be_gb": 0.6064,
        "uogtr_s": 0.5182,
        "uogtr_se": 0.6185,
        "uogtr_se_gb": 0.6211,
        "uot-yahoo_LLMs-blender": 0.3114,
        "uot-yahoo_rankgpt35": 0.3617,
        "uot-yahoo_rankgpt4": 0.4179
      }
    },
    "willia-umbrela2": {
      "labels": {
        "kappa": 0.2687521809714315,
        "nominalAlpha": 0.25777259840815847,
        "binaryKappa": {
          "0|123": 0.41087380624278935,
          "01|23": 0.34210937514085527,
          "012|3": 0.3193659656877326
        },
        "confusion": [
          [
            1690,
            235,
            41,
            39
          ],
          [
            684,
            382,
            100,
            67
          ],
          [
            255,
            297,
            157,
            99
          ],
          [
            76,
            115,
            52,
            134
          ]
        ],
        "gradeDistribution": [
          2705,
          1029,
          350,
          339
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.620845579923129
      },
      "ranking": {
        "kendallTau": 0.9049624731338903,
        "spearmanRho": 0.9834022014451475,
        "fullTrecKendallTau": 0.8746849182706746,
        "fullTrecSpearmanRho": 0.9763989098809462
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2738,
        "WatS-LLM-Rerank": 0.4113,
        "agg-cocondenser": 0.4944,
        "bm25_splades": 0.4868,
        "cip_run_1": 0.7566,
        "cip_run_2": 0.7575,
        "cip_run_3": 0.7014,
        "cip_run_4": 0.6839,
        "cip_run_5": 0.677,
        "cip_run_6": 0.7001,
        "cip_run_7": 0.6912,
        "naverloo-frgpt4": 0.7647,
        "naverloo-rgpt4": 0.7614,
        "naverloo_bm25_RR": 0.5938,
        "naverloo_bm25_splades_RR": 0.6703,
        "naverloo_fs": 0.5148,
        "naverloo_fs_RR": 0.6916,
        "naverloo_fs_RR_duo": 0.7579,
        "slim-pp-0shot-uw": 0.5149,
        "splade_pp_ensemble_distil": 0.471,
        "splade_pp_self_distil": 0.4946,
        "uogtr_b_grf_e": 0.5011,
        "uogtr_b_grf_e_gb": 0.5396,
        "uogtr_be": 0.4973,
        "uogtr_be_gb": 0.5389,
        "uogtr_dph": 0.2727,
        "uogtr_dph_bo1": 0.2172,
        "uogtr_qr_be": 0.5071,
        "uogtr_qr_be_gb": 0.5405,
        "uogtr_s": 0.4724,
        "uogtr_se": 0.5615,
        "uogtr_se_gb": 0.563,
        "uot-yahoo_LLMs-blender": 0.2757,
        "uot-yahoo_rankgpt35": 0.335,
        "uot-yahoo_rankgpt4": 0.3976
      }
    },
    "willia-umbrela3": {
      "labels": {
        "kappa": 0.2741436144544114,
        "nominalAlpha": 0.26402108711149885,
        "binaryKappa": {
          "0|123": 0.4114384753906069,
          "01|23": 0.34465374721845526,
          "012|3": 0.32149126935331734
        },
        "confusion": [
          [
            1693,
            237,
            51,
            24
          ],
          [
            684,
            390,
            125,
            34
          ],
          [
            256,
            299,
            195,
            58
          ],
          [
            77,
            115,
            75,
            110
          ]
        ],
        "gradeDistribution": [
          2710,
          1041,
          446,
          226
        ],
        "labelsOutside0to3": 0,
        "averageGrade": 0.5903233099706082
      },
      "ranking": {
        "kendallTau": 0.8956228956228957,
        "spearmanRho": 0.9809497128449363,
        "fullTrecKendallTau": 0.8653198653198653,
        "fullTrecSpearmanRho": 0.9739459308026335
      },
      "systemScores": {
        "WatS-Augmented-BM25": 0.2771,
        "WatS-LLM-Rerank": 0.4064,
        "agg-cocondenser": 0.4889,
        "bm25_splades": 0.4867,
        "cip_run_1": 0.7526,
        "cip_run_2": 0.7526,
        "cip_run_3": 0.6965,
        "cip_run_4": 0.6747,
        "cip_run_5": 0.6699,
        "cip_run_6": 0.6953,
        "cip_run_7": 0.6876,
        "naverloo-frgpt4": 0.7572,
        "naverloo-rgpt4": 0.7508,
        "naverloo_bm25_RR": 0.5952,
        "naverloo_bm25_splades_RR": 0.6695,
        "naverloo_fs": 0.5142,
        "naverloo_fs_RR": 0.6918,
        "naverloo_fs_RR_duo": 0.7491,
        "slim-pp-0shot-uw": 0.5108,
        "splade_pp_ensemble_distil": 0.4685,
        "splade_pp_self_distil": 0.4932,
        "uogtr_b_grf_e": 0.5007,
        "uogtr_b_grf_e_gb": 0.5399,
        "uogtr_be": 0.4972,
        "uogtr_be_gb": 0.541,
        "uogtr_dph": 0.271,
        "uogtr_dph_bo1": 0.2141,
        "uogtr_qr_be": 0.5046,
        "uogtr_qr_be_gb": 0.5429,
        "uogtr_s": 0.47,
        "uogtr_se": 0.5622,
        "uogtr_se_gb": 0.5647,
        "uot-yahoo_LLMs-blender": 0.276,
        "uot-yahoo_rankgpt35": 0.3298,
        "uot-yahoo_rankgpt4": 0.3895
      }
    }
  },
  "usage": {
    "inputTokens": 11484579,
    "outputTokens": 1250402,
    "estimatedUsd": 0.48235231800000006,
    "latencyP50Seconds": 0.2261105420000022,
    "latencyP95Seconds": 0.27716482300000644,
    "truncatedPairs": 44,
    "passageCaps": {
      "0": 11642,
      "30000": 3,
      "60000": 41
    }
  }
}
