{
  "acquisition": {
    "acquired_at": "2026-06-27T23:57:48+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "63fc6e6b6814bd40d8b23649cd6217ad7df591c4",
    "source_dataset_id": "229_pwLinear",
    "source_dataset_name": "229_pwLinear",
    "source_platform": "pmlb",
    "source_rows": 200,
    "source_target_column_original": "target",
    "source_url": "https://github.com/EpistasisLab/pmlb/raw/master/datasets/229_pwLinear/229_pwLinear.tsv.gz",
    "staged_rows": 200,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-229-pwlinear-target.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 10,
    "original_columns": 11,
    "original_rows": 200,
    "rows_after_target_cleanup": 200,
    "selected_rows": 200,
    "strata_count": 100,
    "test_rows": 34,
    "train_rows": 166
  },
  "created_at": "2026-06-27T23:57:48+00:00",
  "dataset_hash": "1cb97b1d7314d43d",
  "dedupe_fingerprint": "63fc6e6b6814bd40d8b23649cd6217ad7df591c4",
  "dropped_feature_columns": [],
  "feature_columns": [
    "a1",
    "a2",
    "a3",
    "a4",
    "a5",
    "a6",
    "a7",
    "a8",
    "a9",
    "a10"
  ],
  "feature_encodings": {
    "a1": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "a10": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a2": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a3": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a4": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a5": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a6": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a7": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a8": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "a9": {
      "impute_value": 0.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0,
      -1.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 10,
  "origin": "real",
  "original_headers": [
    "a1",
    "a2",
    "a3",
    "a4",
    "a5",
    "a6",
    "a7",
    "a8",
    "a9",
    "a10",
    "target"
  ],
  "output_headers": [
    "a1",
    "a2",
    "a3",
    "a4",
    "a5",
    "a6",
    "a7",
    "a8",
    "a9",
    "a10",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:54:41+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": 495737872,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "1cb97b1d7314d43dee07a1f78f16d74ea27faa0653fd135dfe0084ada3369517",
  "source_dataset_id": "229_pwLinear",
  "source_dataset_name": "229_pwLinear",
  "source_family": "pwlinear",
  "source_file": "pmlb-229-pwlinear-target.csv",
  "source_license": "MIT (PMLB)",
  "source_modified_at": "2026-06-27T23:57:48+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-229-pwlinear-target.csv",
  "source_platform": "pmlb",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 200,
  "source_size_bytes": 12353,
  "source_target_column_original": "target",
  "source_url": "https://github.com/EpistasisLab/pmlb/raw/master/datasets/229_pwLinear/229_pwLinear.tsv.gz",
  "staged_rows": 200,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-229-pwlinear-target.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 12.09000015258789,
    "min": -10.8100004196167,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 34,
  "train_rows": 166
}