{
  "acquisition": {
    "acquired_at": "2026-06-27T23:57:54+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "c43b05dac08bb2f5145ecce79452ed8098741d4d",
    "source_dataset_id": "522_pm10",
    "source_dataset_name": "522_pm10",
    "source_platform": "pmlb",
    "source_rows": 500,
    "source_target_column_original": "target",
    "source_url": "https://github.com/EpistasisLab/pmlb/raw/master/datasets/522_pm10/522_pm10.tsv.gz",
    "staged_rows": 500,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-522-pm10-target.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 7,
    "original_columns": 8,
    "original_rows": 500,
    "rows_after_target_cleanup": 500,
    "selected_rows": 500,
    "strata_count": 149,
    "test_rows": 84,
    "train_rows": 416
  },
  "created_at": "2026-06-27T23:57:54+00:00",
  "dataset_hash": "aebf5d861a8365b4",
  "dedupe_fingerprint": "c43b05dac08bb2f5145ecce79452ed8098741d4d",
  "dropped_feature_columns": [],
  "feature_columns": [
    "cars_per_hour",
    "temperature_at_2m",
    "wind_speed",
    "temperature_diff_2m_25m",
    "wind_direction",
    "hour_of_day",
    "day"
  ],
  "feature_encodings": {
    "cars_per_hour": {
      "impute_value": 7.523750066757202,
      "kind": "numeric"
    },
    "day": {
      "impute_value": 212.0,
      "kind": "numeric"
    },
    "hour_of_day": {
      "impute_value": 13.0,
      "kind": "numeric"
    },
    "temperature_at_2m": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "temperature_diff_2m_25m": {
      "impute_value": 0.1000000014901161,
      "kind": "numeric"
    },
    "wind_direction": {
      "impute_value": 101.8499984741211,
      "kind": "numeric"
    },
    "wind_speed": {
      "impute_value": 3.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      8.352080345153809,
      21.89999961853028,
      9.899999618530272,
      4.0,
      358.0,
      24.0,
      608.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      3.8066599369049072,
      -19.0,
      0.3000000119209289,
      -5.0,
      5.0,
      1.0,
      32.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 7,
  "origin": "real",
  "original_headers": [
    "cars_per_hour",
    "temperature_at_2m",
    "wind_speed",
    "temperature_diff_2m_25m",
    "wind_direction",
    "hour_of_day",
    "day",
    "target"
  ],
  "output_headers": [
    "cars_per_hour",
    "temperature_at_2m",
    "wind_speed",
    "temperature_diff_2m_25m",
    "wind_direction",
    "hour_of_day",
    "day",
    "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": 2945088139,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "aebf5d861a8365b414869c41507df3f5fb7b72c53c5c2c69aee8e5c131f559b9",
  "source_dataset_id": "522_pm10",
  "source_dataset_name": "522_pm10",
  "source_family": "pm10",
  "source_file": "pmlb-522-pm10-target.csv",
  "source_license": "MIT (PMLB)",
  "source_modified_at": "2026-06-27T23:57:54+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-522-pm10-target.csv",
  "source_platform": "pmlb",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 500,
  "source_size_bytes": 52440,
  "source_target_column_original": "target",
  "source_url": "https://github.com/EpistasisLab/pmlb/raw/master/datasets/522_pm10/522_pm10.tsv.gz",
  "staged_rows": 500,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/pmlb-522-pm10-target.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 5.393630027770996,
    "min": 0.693149983882904,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 84,
  "train_rows": 416
}