{
  "acquisition": {
    "acquired_at": "2026-06-27T23:53:11+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "e902426e199dd0218e58fd71216f33bd43098daa",
    "source_dataset_id": "folio/lisiecki2005",
    "source_dataset_name": "Global Benthic delta18O Stack",
    "source_platform": "rdatasets",
    "source_rows": 2115,
    "source_target_column_original": "age",
    "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/folio/lisiecki2005.csv",
    "staged_rows": 1999,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-folio-lisiecki2005-age.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 2,
    "original_columns": 3,
    "original_rows": 1999,
    "rows_after_target_cleanup": 1999,
    "selected_rows": 1999,
    "strata_count": 114,
    "test_rows": 999,
    "train_rows": 1000
  },
  "created_at": "2026-06-27T23:53:11+00:00",
  "dataset_hash": "51d5e3d9bca34669",
  "dedupe_fingerprint": "e902426e199dd0218e58fd71216f33bd43098daa",
  "downsampling": {
    "anchors_kept": 6,
    "corr_frob": 0.023516,
    "ks_features_mean": 0.013085,
    "ks_target": 0.009703,
    "method": "hybrid_coreset",
    "minmax_features_preserved": true,
    "minmax_target_preserved": true,
    "n_bins": 50,
    "original_rows": 2115,
    "selected_rows": 1999
  },
  "dropped_feature_columns": [],
  "feature_columns": [
    "delta",
    "error"
  ],
  "feature_encodings": {
    "delta": {
      "impute_value": 3.71,
      "kind": "numeric"
    },
    "error": {
      "impute_value": 0.06,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      5.08,
      0.14
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      2.65,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 2,
  "origin": "real",
  "original_headers": [
    "delta",
    "error",
    "target"
  ],
  "output_headers": [
    "delta",
    "error",
    "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": 1356907732,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "51d5e3d9bca346692059ed628e539c6689ac6dd244f1e5882c0c37169adbd65f",
  "source_dataset_id": "folio/lisiecki2005",
  "source_dataset_name": "Global Benthic delta18O Stack",
  "source_family": "global-benthic",
  "source_file": "rdatasets-folio-lisiecki2005-age.csv",
  "source_license": "GPL (R package folio)",
  "source_modified_at": "2026-06-27T23:53:11+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-folio-lisiecki2005-age.csv",
  "source_platform": "rdatasets",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 2115,
  "source_size_bytes": 32895,
  "source_target_column_original": "age",
  "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/folio/lisiecki2005.csv",
  "staged_rows": 1999,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-folio-lisiecki2005-age.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 5320.0,
    "min": 0.0,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 999,
  "train_rows": 1000
}