{
  "acquisition": {
    "acquired_at": "2026-06-27T23:52:18+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "e89fbbf5e29c2ac7411948d6634e6a7ef0a8bcc8",
    "source_dataset_id": "carData/Davis",
    "source_dataset_name": "Self-Reports of Height and Weight",
    "source_platform": "rdatasets",
    "source_rows": 200,
    "source_target_column_original": "weight",
    "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Davis.csv",
    "staged_rows": 200,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-cardata-davis-weight.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 4,
    "original_columns": 5,
    "original_rows": 200,
    "rows_after_target_cleanup": 200,
    "selected_rows": 200,
    "strata_count": 67,
    "test_rows": 34,
    "train_rows": 166
  },
  "created_at": "2026-06-27T23:52:18+00:00",
  "dataset_hash": "71afaa46fcf938d2",
  "dedupe_fingerprint": "e89fbbf5e29c2ac7411948d6634e6a7ef0a8bcc8",
  "dropped_feature_columns": [],
  "feature_columns": [
    "sex",
    "height",
    "repwt",
    "repht"
  ],
  "feature_encodings": {
    "height": {
      "impute_value": 169.5,
      "kind": "numeric"
    },
    "repht": {
      "impute_value": 168.0,
      "kind": "numeric"
    },
    "repwt": {
      "impute_value": 63.0,
      "kind": "numeric"
    },
    "sex": {
      "impute_value": 0.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      1.0,
      197.0,
      124.0,
      200.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      0.0,
      57.0,
      41.0,
      148.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 4,
  "origin": "real",
  "original_headers": [
    "sex",
    "height",
    "repwt",
    "repht",
    "target"
  ],
  "output_headers": [
    "sex",
    "height",
    "repwt",
    "repht",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:51:55+00:00",
  "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": 1889176907,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "71afaa46fcf938d23587aaf782562b4c45b04c68cd5601755ae188e6b11f3ea5",
  "source_dataset_id": "carData/Davis",
  "source_dataset_name": "Self-Reports of Height and Weight",
  "source_family": "self-reports",
  "source_file": "rdatasets-cardata-davis-weight.csv",
  "source_license": "GPL (R package carData)",
  "source_modified_at": "2026-06-27T23:52:18+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-cardata-davis-weight.csv",
  "source_platform": "rdatasets",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 200,
  "source_size_bytes": 5086,
  "source_target_column_original": "weight",
  "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Davis.csv",
  "staged_rows": 200,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-cardata-davis-weight.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 166.0,
    "min": 39.0,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 34,
  "train_rows": 166
}