{
  "acquisition": {
    "acquired_at": "2026-06-26T09:12:04+00:00",
    "fetched_feature_columns": 30,
    "fetched_rows": 818238,
    "openml_data_id": 45549,
    "openml_name": "ATLAS-Higgs-Boson-Machine-Learning-Challenge-2014",
    "openml_url": "https://www.openml.org/d/45549",
    "row_policy": "stratified_cap_to_final_max",
    "source": "openml",
    "source_rows_after_target_cleanup": 818238,
    "stage_path": "/home/ubuntu/hyper/data/tabular/atlas-higgs-boson-machine-learning-challenge-2014.csv",
    "staged_feature_columns": 30,
    "staged_rows": 2000,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 30,
    "original_columns": 31,
    "original_rows": 2000,
    "rows_after_target_cleanup": 2000,
    "selected_rows": 2000,
    "strata_count": 36,
    "test_rows": 1000,
    "train_rows": 1000
  },
  "created_at": "2026-06-26T09:12:04+00:00",
  "dataset_hash": "a31b5837cb3a919f",
  "dropped_feature_columns": [],
  "feature_columns": [
    "DER_mass_MMC",
    "DER_mass_transverse_met_lep",
    "DER_mass_vis",
    "DER_pt_h",
    "DER_deltaeta_jet_jet",
    "DER_mass_jet_jet",
    "DER_prodeta_jet_jet",
    "DER_deltar_tau_lep",
    "DER_pt_tot",
    "DER_sum_pt",
    "DER_pt_ratio_lep_tau",
    "DER_met_phi_centrality",
    "DER_lep_eta_centrality",
    "PRI_tau_pt",
    "PRI_tau_eta",
    "PRI_tau_phi",
    "PRI_lep_pt",
    "PRI_lep_eta",
    "PRI_lep_phi",
    "PRI_met",
    "PRI_met_phi",
    "PRI_met_sumet",
    "PRI_jet_num",
    "PRI_jet_leading_pt",
    "PRI_jet_leading_eta",
    "PRI_jet_leading_phi",
    "PRI_jet_subleading_pt",
    "PRI_jet_subleading_eta",
    "PRI_jet_subleading_phi",
    "PRI_jet_all_pt"
  ],
  "feature_encodings": {
    "DER_deltaeta_jet_jet": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "DER_deltar_tau_lep": {
      "impute_value": 2.5060000000000002,
      "kind": "numeric"
    },
    "DER_lep_eta_centrality": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "DER_mass_MMC": {
      "impute_value": 104.8725,
      "kind": "numeric"
    },
    "DER_mass_jet_jet": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "DER_mass_transverse_met_lep": {
      "impute_value": 46.882999999999996,
      "kind": "numeric"
    },
    "DER_mass_vis": {
      "impute_value": 73.52799999999999,
      "kind": "numeric"
    },
    "DER_met_phi_centrality": {
      "impute_value": -0.3215,
      "kind": "numeric"
    },
    "DER_prodeta_jet_jet": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "DER_pt_h": {
      "impute_value": 37.1825,
      "kind": "numeric"
    },
    "DER_pt_ratio_lep_tau": {
      "impute_value": 1.2865,
      "kind": "numeric"
    },
    "DER_pt_tot": {
      "impute_value": 11.508,
      "kind": "numeric"
    },
    "DER_sum_pt": {
      "impute_value": 120.9565,
      "kind": "numeric"
    },
    "PRI_jet_all_pt": {
      "impute_value": 40.6115,
      "kind": "numeric"
    },
    "PRI_jet_leading_eta": {
      "impute_value": -1.8475000000000001,
      "kind": "numeric"
    },
    "PRI_jet_leading_phi": {
      "impute_value": -1.994,
      "kind": "numeric"
    },
    "PRI_jet_leading_pt": {
      "impute_value": 38.8865,
      "kind": "numeric"
    },
    "PRI_jet_num": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "PRI_jet_subleading_eta": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "PRI_jet_subleading_phi": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "PRI_jet_subleading_pt": {
      "impute_value": -999.0,
      "kind": "numeric"
    },
    "PRI_lep_eta": {
      "impute_value": 0.028,
      "kind": "numeric"
    },
    "PRI_lep_phi": {
      "impute_value": 0.1095,
      "kind": "numeric"
    },
    "PRI_lep_pt": {
      "impute_value": 40.688500000000005,
      "kind": "numeric"
    },
    "PRI_met": {
      "impute_value": 34.921499999999995,
      "kind": "numeric"
    },
    "PRI_met_phi": {
      "impute_value": 0.047,
      "kind": "numeric"
    },
    "PRI_met_sumet": {
      "impute_value": 178.603,
      "kind": "numeric"
    },
    "PRI_tau_eta": {
      "impute_value": -0.066,
      "kind": "numeric"
    },
    "PRI_tau_phi": {
      "impute_value": -0.0445,
      "kind": "numeric"
    },
    "PRI_tau_pt": {
      "impute_value": 31.3365,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      684.807,
      318.016,
      460.597,
      437.54,
      7.901,
      3258.232,
      11.677,
      5.481,
      224.16,
      1104.783,
      8.628,
      1.414,
      1.0,
      211.615,
      2.496,
      3.141,
      302.524,
      2.458,
      3.141,
      262.571,
      3.142,
      1201.677,
      3.0,
      569.731,
      4.152,
      3.14,
      355.064,
      4.395,
      3.107,
      1005.169
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      -999.0,
      0.06,
      12.313,
      0.0,
      -999.0,
      -999.0,
      -999.0,
      0.428,
      0.0,
      46.875,
      0.177,
      -1.414,
      -999.0,
      20.004,
      -2.485,
      -3.138,
      26.007,
      -2.473,
      -3.141,
      0.247,
      -3.138,
      21.323,
      0.0,
      -999.0,
      -999.0,
      -999.0,
      -999.0,
      -999.0,
      -999.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 30,
  "origin": "real",
  "original_headers": [
    "DER_mass_MMC",
    "DER_mass_transverse_met_lep",
    "DER_mass_vis",
    "DER_pt_h",
    "DER_deltaeta_jet_jet",
    "DER_mass_jet_jet",
    "DER_prodeta_jet_jet",
    "DER_deltar_tau_lep",
    "DER_pt_tot",
    "DER_sum_pt",
    "DER_pt_ratio_lep_tau",
    "DER_met_phi_centrality",
    "DER_lep_eta_centrality",
    "PRI_tau_pt",
    "PRI_tau_eta",
    "PRI_tau_phi",
    "PRI_lep_pt",
    "PRI_lep_eta",
    "PRI_lep_phi",
    "PRI_met",
    "PRI_met_phi",
    "PRI_met_sumet",
    "PRI_jet_num",
    "PRI_jet_leading_pt",
    "PRI_jet_leading_eta",
    "PRI_jet_leading_phi",
    "PRI_jet_subleading_pt",
    "PRI_jet_subleading_eta",
    "PRI_jet_subleading_phi",
    "PRI_jet_all_pt",
    "target"
  ],
  "output_headers": [
    "DER_mass_MMC",
    "DER_mass_transverse_met_lep",
    "DER_mass_vis",
    "DER_pt_h",
    "DER_deltaeta_jet_jet",
    "DER_mass_jet_jet",
    "DER_prodeta_jet_jet",
    "DER_deltar_tau_lep",
    "DER_pt_tot",
    "DER_sum_pt",
    "DER_pt_ratio_lep_tau",
    "DER_met_phi_centrality",
    "DER_lep_eta_centrality",
    "PRI_tau_pt",
    "PRI_tau_eta",
    "PRI_tau_phi",
    "PRI_lep_pt",
    "PRI_lep_eta",
    "PRI_lep_phi",
    "PRI_met",
    "PRI_met_phi",
    "PRI_met_sumet",
    "PRI_jet_num",
    "PRI_jet_leading_pt",
    "PRI_jet_leading_eta",
    "PRI_jet_leading_phi",
    "PRI_jet_subleading_pt",
    "PRI_jet_subleading_eta",
    "PRI_jet_subleading_phi",
    "PRI_jet_all_pt",
    "target"
  ],
  "sampling": {
    "final_max_rows": 2000,
    "method": "quota stratified by target distribution plus high-variance feature quantile bins",
    "minimum_final_rows": 101,
    "minimum_test_to_train_ratio_when_small": 0.2,
    "seed": 2720956218,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "a31b5837cb3a919f94d4679a437767208f4c0b01fc8981d8924c49f2cbe53ab2",
  "source": "openml",
  "source_file": "atlas-higgs-boson-machine-learning-challenge-2014.csv",
  "source_modified_at": "2026-06-26T09:12:04+00:00",
  "source_openml_data_id": 45549,
  "source_openml_name": "ATLAS-Higgs-Boson-Machine-Learning-Challenge-2014",
  "source_path": "/home/ubuntu/hyper/data/tabular/atlas-higgs-boson-machine-learning-challenge-2014.csv",
  "source_real_data": true,
  "source_size_bytes": 406758,
  "source_url": "https://www.openml.org/d/45549",
  "target_column": "target",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "class_to_code": {
      "0.0": 0,
      "1.0": 1
    },
    "classes": [
      0.0,
      1.0
    ],
    "mode": "classification",
    "n_classes": 2,
    "range": [
      0.0,
      1.0
    ],
    "scaled_code_formula": "code / max(1, n_classes - 1)"
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "binary",
  "test_rows": 1000,
  "train_rows": 1000
}