{
  "backbone": "ElnaggarLab/ankh-base",
  "dict_dim": 2048,
  "top_k": 128,
  "bank_rows": 575503,
  "distinct_sequences": 487237,
  "donor_annotations": 5880402,
  "annotation_release": "227",
  "annotation_published": "2025-09-04",
  "ontology": "releases/2025-07-22",
  "encoder_trained_at": "2026-08-10T17:46:26Z",
  "built_at": "2026-08-10T18:06:53Z",
  "note": "bank_rows are canonical protein accessions; proteins sharing a sequence are separate rows with their own annotations. distinct_sequences counts the sequences behind them, so bank_rows minus distinct_sequences is the number of rows that duplicate another row's code."
}