{
  "source": "/home/dzhou/pic2smiles/data/corpus/chembl_37_smiles.txt",
  "holdout": "/home/dzhou/pic2smiles/data/corpus/decimer_holdout.smi",
  "holdout_removed": 210,
  "scope": {
    "min_heavy_atoms": 4,
    "max_heavy_atoms": 48,
    "allowed_elements": [
      "B",
      "Br",
      "C",
      "Cl",
      "F",
      "I",
      "N",
      "O",
      "P",
      "S",
      "Se",
      "Si"
    ],
    "allow_charges": true,
    "allow_multi_fragment": false,
    "max_smiles_tokens": 160
  },
  "curate_stats": {
    "read": 2897819,
    "rejected": 269119,
    "duplicate": 141,
    "kept": 2628559
  },
  "splits": {
    "train": 2618349,
    "val": 5000,
    "test": 5000
  },
  "vocab_size": 88,
  "val_molecules_with_unknown_tokens": 1,
  "seed": 20260819,
  "generated_at": "2026-08-19T21:54:23"
}