{
  "data_dir": "artifacts/synth_v1",
  "split": "test",
  "samples": 256,
  "colour_classes": 10,
  "text_families": {
    "count_words": [
      "a",
      "three",
      "four",
      "two"
    ],
    "colour_words": [
      "red",
      "orange",
      "yellow",
      "green",
      "blue",
      "purple",
      "pink",
      "white",
      "gray",
      "brown"
    ],
    "size_words": [
      [
        "small",
        "large"
      ]
    ]
  },
  "field_correlation_at_truth": 0.678442918934101,
  "note": "The dictionary is derived from disjoint corpora; the correlation is a diagnostic computed with hidden pairs and never used by the pipeline."
}